TY  - THES
AU  - Sekulić, Aleksandar M.
PY  - 2021-04-09
UR  - http://eteze.bg.ac.rs/application/showtheses?thesesId=8450
UR  - https://fedorabg.bg.ac.rs/fedora/get/o:24776/bdef:Content/download
UR  - http://vbs.rs/scripts/cobiss?command=DISPLAY&base=70036&RID=36506633
UR  - https://nardus.mpn.gov.rs/handle/123456789/18869
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2726
AB  - High resolution daily maps for climate elements are a valuable source of information and serve as aninput for climatology, meteorology, agriculture, hydrology, ecology, and many other research areasand disciplines. Spatio-temporal interpolation methods are o en used for creation of daily mapsfor climate elements. In this research, already existing spatio-temporal geostatistical interpolationmethods and newly developed spatio-temporal interpolation methods based on machine learning algorithms are applied to and evaluated on climate element case studies. A spatio-temporal regressionkriging model for global land areas for mean daily temperature is simpli ed by using only a geometric temperature trend, digital elevation model, and topographic wetness index (without MODISLST) as covariates and adapted for Croatian territories for the year 2008 in this dissertation.  eleave-one-out and 5-fold cross-validation show that the accuracy of the model a er adaptation is97.8% in R2 and 1.2 ◦C in RMSE, which is an improvement of 3.4% in R2 and 0.7 ◦C in RMSE.  eadapted daily mean temperature model also outperforms previously developed models for Croatiaand shows similar or be er accuracy in comparison with models for other local areas.  e resultsshow that the spatio-temporal regression kriging model for global land areas can be adapted to localareas using a national weather station network, thus providing more accurate daily mean temperature maps at a 1 km spatial resolution.  e proposed adapted geostatistical model for Croatia stillprovides larger prediction errors in mountainous regions making it convenient for application inagricultural areas that are at lower altitudes.A di erent approach to spatial or spatio-temporal interpolation of climate elements is to usemachine learning algorithms together with spatial covariates. A novel Random Forest Spatial Interpolation (RFSI) methodology for spatial or spatio-temporal interpolation is proposed and evaluatedin this dissertation.  e RFSI methodology is based on the Random Forest algorithm that uses innovative spatial predictors: observations at n nearest locations and distances to them.  e RFSImethodology is applied and evaluated in three case studies. In the  rst, a synthetic (simulated) casestudy, the accuracy of RFSI is compared with the accuracy of ordinary kriging, Random Forest forspatial prediction (RFsp), inverse distance weighting, nearest neighbour, and trend surface mappinginterpolation methods. In this case study, RFSI outperforms nearest neighbour and trend surfacemapping and has similar accuracy as RFsp and inverse distance weighting. RFSI is outperformed byordinary kriging because this case study is created by geostatistical simulation and consequentiallyordinary kriging is an optimal interpolation method in this case. In the following two real-world casestudies, a daily precipitation for Catalonia for the 2016–2018 period and a daily mean temperaturefor Croatia for the year 2008, the accuracy of RFSI is compared with the accuracy of spatio-temporalregression kriging, inverse distance weighting, standard Random Forest and RFsp using a nestedviiUNIVERSITY OF BELGRADEFaculty of Civil EngineeringDepartment of Geodesy and Geoinformaticsk-fold leave-location-out cross-validation and RFSI outperformed all of them. RFSI is recommendedfor the interpolation of complex variables due to Random Forest’s ability to model non-linear relations between covariates and target variables. RFSI can be used for spatial or spatio-temporalinterpolation of any environmental variable.Next, a MeteoSerbia1km dataset — a  rst gridded dataset for daily climate elements (maximum,minimum, and mean temperature, mean sea level pressure, and total precipitation) at a 1 km spatialresolution for Serbian territories for the 2000–2019 period — is created using RFSI methodologyfor spatio-temporal interpolation. Additionally, monthly and annual summaries and daily, monthly,and annual long term means maps of the climate elements are generated by aggregating the dailyMeteoSerbia1km maps.  e nested 5-fold leave-location-out cross-validation is used to access theaccuracy of the MeteoSerbia1km daily dataset.  e accuracy is high for daily temperature variablesand sea level pressure and lower for daily precipitation which was expected due to its complexity.MeteoSerbia1km daily maps are further compared with the 10-km E-OBS daily maps and show highcorrelation with them except for daily precipitation. e automation of the RFSI methodology is implemented within the R package meteo, in theform of four new R functions for creation, prediction, tuning, and cross-validation processes of RFSImodel.
AB  - Gridovani podaci dnevnih klimatskih elemenata visoke rezolucije predstavljaju znacajan izvor in- ˇformacija koje se koriste kao ulazni podaci za analize u klimatologiji, meteorologiji, poljoprivredi,hidrologiji, ekologiji i ostalim istraziva ˇ ckim oblastima i disciplinama. Prostorno-vremenske inter- ˇpolacione metode cesto se koriste za kreiranje gridovanih dnevnih klimatskih elemenata. Glob- ˇalni model prostorno-vremenskog regresionog kriginga za srednje dnevne temperature iznad povrsi ˇZemlje je pojednostavljen koristeci samo geometrijski temperaturni trend, digitalni model terena ´i topografski indeks vlaznosti (bez MODIS LST snimaka) kao prediktore i kalibrisan za podru ˇ cje ˇHrvatske koristeci podatke iz 2008 godine u ovoj disertaciji. Na osnovu prostorne kros-validacije, ´tacnost kalibrisanog modela iznosi R ˇ 2=97.8% i RMSE=1.2 ◦C, sto je pobolj ˇ sanje od 3.4% i 0.7 ˇ ◦C uodnosu na globalni model. Prilagodeni model srednjih dnevnih temperatura nadmasuje ostale ve ˇ c´razvijene modele za podrucje Hrvatske u pogledu ta ˇ cnosti i ima sli ˇ cnu ili ve ˇ cu ta ´ cnost u odnosu na ˇmodele za druga lokalna podrucja ili dr ˇ zave. Rezultati pokazuju da se globalni model prostorno- ˇvremenskog regresionog kriginga moze prilagoditi lokalnim podru ˇ cjima koriste ˇ ci mre ´ zu nacional- ˇnih meteoroloskih stanica i tako proizvesti gridovane podatke srednjih dnevnih temperatura ve ˇ ce ´tacnosti sa prostornom rezolucijom od 1 km. Kalibrisani model za podru ˇ cje Hrvatske jo ˇ s uvek ima ˇmanju tacnost u planinskim predelima, ˇ sto ga ˇ cini pogodnim za primenu u poljoprivrednim po- ˇdrucjima koja su na ni ˇ zim nadmorskim visinama. ˇAlgoritmi masinskog u ˇ cenja kombinovani sa inovativnim prostornim prediktorima predstavljaju ˇnovi oblik modela za prostornu ili prostorno-vremensku interpolaciju, koji mogu da se koriste i zainterpolaciju klimatskih elemenata. U ovoj disertaciji je predstavljena i testirana inovativna RandomForest Spatial Interpolation (RFSI) metodologija za prostornu ili prostorno-vremensku interpolaciju.RFSI metodologija je bazirana na Random Forest algoritmu masinskog u ˇ cenja koji koristi inovativne ˇprostorne prediktore: opazanja na ˇ n najblizih lokacija i rastojanja do njih. RFSI metodologija je ˇprimenjena i testirana na tri studije slucaja. U prvoj sinteti ˇ ckoj studiji, koja predstavlja simulirani ˇset podataka, tacnost RFSI metodologije je pore ˇ dena sa tacno ˇ sˇcu obi ´ cnog kriging-a, ˇ Random Forestfor spatial prediction (RFsp) metode, metode inverznih distanci (eng. inverse distance weighting), najblizeg suseda (eng. ˇ nearest neighbour) i mapiranja povrsi trenda (eng. ˇ trend surface mapping). Uovom slucaju, RFSI je pokazao ve ˇ cu ta ´ cnost u pore ˇ denju sa metodama najblizeg suseda i mapiranja ˇpovrsi trenda i sli ˇ cnu ta ˇ cnost kao RFsp i metoda inverznih distanci. Obi ˇ cni kriging je o ˇ cekivano dao ˇbolje rezultate od RFSI metodologije iz razloga sto je simulirani set podataka kreiran geostatisti ˇ ckom ˇsimulacijom i samim tim obicni kriging predstavlja optimalnu metodu interpolacije u ovom slu ˇ caju. ˇU ostale dve studije slucaja, koje se odnose na dnevne koli ˇ cine padavina za podru ˇ cje Katalonije ˇza 2016–2018 period i srednje dnevne temperature za podrucje Hrvatske za 2008 godinu, ta ˇ cnost ˇixUNIVERZITET U BEOGRADUGradevinski fakultetOdsek za geodeziju i geoinformatikuRFSI metodologije je poredena sa tacno ˇ sˇcu prostorno-vremenskog regresionog kriginga, metode in- ´verznih distanci, standardnom Random Forest i RFsp metodom koristeci ugnje ´ zdenu prostornu kros- ˇvalidaciju. RFSI metodologija je pokazala najbolje rezultate u ovim studijama. RFSI metodologija sepreporucuje za interpolaciju slo ˇ zenih parametara zbog osobine ˇ Random Forest algoritma da moze da ˇmodelira nelinearne veze izmedu prediktora i modeliranog parametra. RFSI metodologija se takodemoze koristiti za prostornu ili prostorno-vremensku interpolaciju bilo kog drugog parametra ˇ zivotne ˇsredine.Koristeci RFSI metodologiju za prostorno-vremensku interpolaciju, kreiran je MeteoSerbia1km ´set podataka koji predstavlja prvi set gridovanih dnevnih klimatskih elemenata (maksimalne, minimalne i srednje temperature, atmosferskog pritiska na nivou mora i kolicine padavina) sa pros- ˇtornom rezolucijom od 1 km za podrucje Srbije za period 2000–2019. Agregacijom dnevnih gri- ˇdovanih podataka dodatno su kreirani gridovani podaci mesecnih i godi ˇ snjih proseka (ukupne ˇkolicine za padavine) i gridovani podaci dnevnih, mese ˇ cnih i godi ˇ snjih dugoro ˇ cnih proseka kli- ˇmatskih elemenata. Tacnost dnevnih MeteoSerbia1km gridovanih podaka je ocenjena pomo ˇ cu ´ugnjezdene prostorne kros-validacije. Ta ˇ cnost dnevnih temperatura i atmosferskog pritiska na ˇnivou mora je visoka, dok je tacnost dnevnih padavina o ˇ cekivano ne ˇ sto manja zbog slo ˇ zenosti samih ˇpadavina. Dnevni MeteoSerbia1km gridovani podaci su takode poredeni sa E-OBS setom dnevnihgridovanih podataka sa prostornom rezolucijom od 10 km i pokazuju visok stepen korelacije, osimza padavine.RFSI metodolgija je automatizovana i implementirana u okviru R paketa meteo, kroz cetiri ˇnove R funkcije za procese kreiranja, predikcije, kalibrisanja i kros-validacije RFSI modela.
PB  - Универзитет у Београду, Грађевински факултет
T2  - Универзитет у Београду
T1  - Spatio-temporal interpolation of climate elements using geostatistics and machine learning
UR  - https://hdl.handle.net/21.15107/rcub_nardus_18869
ER  - 

@phdthesis{
author = "Sekulić, Aleksandar M.",
year = "2021-04-09",
abstract = "High resolution daily maps for climate elements are a valuable source of information and serve as aninput for climatology, meteorology, agriculture, hydrology, ecology, and many other research areasand disciplines. Spatio-temporal interpolation methods are o en used for creation of daily mapsfor climate elements. In this research, already existing spatio-temporal geostatistical interpolationmethods and newly developed spatio-temporal interpolation methods based on machine learning algorithms are applied to and evaluated on climate element case studies. A spatio-temporal regressionkriging model for global land areas for mean daily temperature is simpli ed by using only a geometric temperature trend, digital elevation model, and topographic wetness index (without MODISLST) as covariates and adapted for Croatian territories for the year 2008 in this dissertation.  eleave-one-out and 5-fold cross-validation show that the accuracy of the model a er adaptation is97.8% in R2 and 1.2 ◦C in RMSE, which is an improvement of 3.4% in R2 and 0.7 ◦C in RMSE.  eadapted daily mean temperature model also outperforms previously developed models for Croatiaand shows similar or be er accuracy in comparison with models for other local areas.  e resultsshow that the spatio-temporal regression kriging model for global land areas can be adapted to localareas using a national weather station network, thus providing more accurate daily mean temperature maps at a 1 km spatial resolution.  e proposed adapted geostatistical model for Croatia stillprovides larger prediction errors in mountainous regions making it convenient for application inagricultural areas that are at lower altitudes.A di erent approach to spatial or spatio-temporal interpolation of climate elements is to usemachine learning algorithms together with spatial covariates. A novel Random Forest Spatial Interpolation (RFSI) methodology for spatial or spatio-temporal interpolation is proposed and evaluatedin this dissertation.  e RFSI methodology is based on the Random Forest algorithm that uses innovative spatial predictors: observations at n nearest locations and distances to them.  e RFSImethodology is applied and evaluated in three case studies. In the  rst, a synthetic (simulated) casestudy, the accuracy of RFSI is compared with the accuracy of ordinary kriging, Random Forest forspatial prediction (RFsp), inverse distance weighting, nearest neighbour, and trend surface mappinginterpolation methods. In this case study, RFSI outperforms nearest neighbour and trend surfacemapping and has similar accuracy as RFsp and inverse distance weighting. RFSI is outperformed byordinary kriging because this case study is created by geostatistical simulation and consequentiallyordinary kriging is an optimal interpolation method in this case. In the following two real-world casestudies, a daily precipitation for Catalonia for the 2016–2018 period and a daily mean temperaturefor Croatia for the year 2008, the accuracy of RFSI is compared with the accuracy of spatio-temporalregression kriging, inverse distance weighting, standard Random Forest and RFsp using a nestedviiUNIVERSITY OF BELGRADEFaculty of Civil EngineeringDepartment of Geodesy and Geoinformaticsk-fold leave-location-out cross-validation and RFSI outperformed all of them. RFSI is recommendedfor the interpolation of complex variables due to Random Forest’s ability to model non-linear relations between covariates and target variables. RFSI can be used for spatial or spatio-temporalinterpolation of any environmental variable.Next, a MeteoSerbia1km dataset — a  rst gridded dataset for daily climate elements (maximum,minimum, and mean temperature, mean sea level pressure, and total precipitation) at a 1 km spatialresolution for Serbian territories for the 2000–2019 period — is created using RFSI methodologyfor spatio-temporal interpolation. Additionally, monthly and annual summaries and daily, monthly,and annual long term means maps of the climate elements are generated by aggregating the dailyMeteoSerbia1km maps.  e nested 5-fold leave-location-out cross-validation is used to access theaccuracy of the MeteoSerbia1km daily dataset.  e accuracy is high for daily temperature variablesand sea level pressure and lower for daily precipitation which was expected due to its complexity.MeteoSerbia1km daily maps are further compared with the 10-km E-OBS daily maps and show highcorrelation with them except for daily precipitation. e automation of the RFSI methodology is implemented within the R package meteo, in theform of four new R functions for creation, prediction, tuning, and cross-validation processes of RFSImodel., Gridovani podaci dnevnih klimatskih elemenata visoke rezolucije predstavljaju znacajan izvor in- ˇformacija koje se koriste kao ulazni podaci za analize u klimatologiji, meteorologiji, poljoprivredi,hidrologiji, ekologiji i ostalim istraziva ˇ ckim oblastima i disciplinama. Prostorno-vremenske inter- ˇpolacione metode cesto se koriste za kreiranje gridovanih dnevnih klimatskih elemenata. Glob- ˇalni model prostorno-vremenskog regresionog kriginga za srednje dnevne temperature iznad povrsi ˇZemlje je pojednostavljen koristeci samo geometrijski temperaturni trend, digitalni model terena ´i topografski indeks vlaznosti (bez MODIS LST snimaka) kao prediktore i kalibrisan za podru ˇ cje ˇHrvatske koristeci podatke iz 2008 godine u ovoj disertaciji. Na osnovu prostorne kros-validacije, ´tacnost kalibrisanog modela iznosi R ˇ 2=97.8% i RMSE=1.2 ◦C, sto je pobolj ˇ sanje od 3.4% i 0.7 ˇ ◦C uodnosu na globalni model. Prilagodeni model srednjih dnevnih temperatura nadmasuje ostale ve ˇ c´razvijene modele za podrucje Hrvatske u pogledu ta ˇ cnosti i ima sli ˇ cnu ili ve ˇ cu ta ´ cnost u odnosu na ˇmodele za druga lokalna podrucja ili dr ˇ zave. Rezultati pokazuju da se globalni model prostorno- ˇvremenskog regresionog kriginga moze prilagoditi lokalnim podru ˇ cjima koriste ˇ ci mre ´ zu nacional- ˇnih meteoroloskih stanica i tako proizvesti gridovane podatke srednjih dnevnih temperatura ve ˇ ce ´tacnosti sa prostornom rezolucijom od 1 km. Kalibrisani model za podru ˇ cje Hrvatske jo ˇ s uvek ima ˇmanju tacnost u planinskim predelima, ˇ sto ga ˇ cini pogodnim za primenu u poljoprivrednim po- ˇdrucjima koja su na ni ˇ zim nadmorskim visinama. ˇAlgoritmi masinskog u ˇ cenja kombinovani sa inovativnim prostornim prediktorima predstavljaju ˇnovi oblik modela za prostornu ili prostorno-vremensku interpolaciju, koji mogu da se koriste i zainterpolaciju klimatskih elemenata. U ovoj disertaciji je predstavljena i testirana inovativna RandomForest Spatial Interpolation (RFSI) metodologija za prostornu ili prostorno-vremensku interpolaciju.RFSI metodologija je bazirana na Random Forest algoritmu masinskog u ˇ cenja koji koristi inovativne ˇprostorne prediktore: opazanja na ˇ n najblizih lokacija i rastojanja do njih. RFSI metodologija je ˇprimenjena i testirana na tri studije slucaja. U prvoj sinteti ˇ ckoj studiji, koja predstavlja simulirani ˇset podataka, tacnost RFSI metodologije je pore ˇ dena sa tacno ˇ sˇcu obi ´ cnog kriging-a, ˇ Random Forestfor spatial prediction (RFsp) metode, metode inverznih distanci (eng. inverse distance weighting), najblizeg suseda (eng. ˇ nearest neighbour) i mapiranja povrsi trenda (eng. ˇ trend surface mapping). Uovom slucaju, RFSI je pokazao ve ˇ cu ta ´ cnost u pore ˇ denju sa metodama najblizeg suseda i mapiranja ˇpovrsi trenda i sli ˇ cnu ta ˇ cnost kao RFsp i metoda inverznih distanci. Obi ˇ cni kriging je o ˇ cekivano dao ˇbolje rezultate od RFSI metodologije iz razloga sto je simulirani set podataka kreiran geostatisti ˇ ckom ˇsimulacijom i samim tim obicni kriging predstavlja optimalnu metodu interpolacije u ovom slu ˇ caju. ˇU ostale dve studije slucaja, koje se odnose na dnevne koli ˇ cine padavina za podru ˇ cje Katalonije ˇza 2016–2018 period i srednje dnevne temperature za podrucje Hrvatske za 2008 godinu, ta ˇ cnost ˇixUNIVERZITET U BEOGRADUGradevinski fakultetOdsek za geodeziju i geoinformatikuRFSI metodologije je poredena sa tacno ˇ sˇcu prostorno-vremenskog regresionog kriginga, metode in- ´verznih distanci, standardnom Random Forest i RFsp metodom koristeci ugnje ´ zdenu prostornu kros- ˇvalidaciju. RFSI metodologija je pokazala najbolje rezultate u ovim studijama. RFSI metodologija sepreporucuje za interpolaciju slo ˇ zenih parametara zbog osobine ˇ Random Forest algoritma da moze da ˇmodelira nelinearne veze izmedu prediktora i modeliranog parametra. RFSI metodologija se takodemoze koristiti za prostornu ili prostorno-vremensku interpolaciju bilo kog drugog parametra ˇ zivotne ˇsredine.Koristeci RFSI metodologiju za prostorno-vremensku interpolaciju, kreiran je MeteoSerbia1km ´set podataka koji predstavlja prvi set gridovanih dnevnih klimatskih elemenata (maksimalne, minimalne i srednje temperature, atmosferskog pritiska na nivou mora i kolicine padavina) sa pros- ˇtornom rezolucijom od 1 km za podrucje Srbije za period 2000–2019. Agregacijom dnevnih gri- ˇdovanih podataka dodatno su kreirani gridovani podaci mesecnih i godi ˇ snjih proseka (ukupne ˇkolicine za padavine) i gridovani podaci dnevnih, mese ˇ cnih i godi ˇ snjih dugoro ˇ cnih proseka kli- ˇmatskih elemenata. Tacnost dnevnih MeteoSerbia1km gridovanih podaka je ocenjena pomo ˇ cu ´ugnjezdene prostorne kros-validacije. Ta ˇ cnost dnevnih temperatura i atmosferskog pritiska na ˇnivou mora je visoka, dok je tacnost dnevnih padavina o ˇ cekivano ne ˇ sto manja zbog slo ˇ zenosti samih ˇpadavina. Dnevni MeteoSerbia1km gridovani podaci su takode poredeni sa E-OBS setom dnevnihgridovanih podataka sa prostornom rezolucijom od 10 km i pokazuju visok stepen korelacije, osimza padavine.RFSI metodolgija je automatizovana i implementirana u okviru R paketa meteo, kroz cetiri ˇnove R funkcije za procese kreiranja, predikcije, kalibrisanja i kros-validacije RFSI modela.",
publisher = "Универзитет у Београду, Грађевински факултет",
journal = "Универзитет у Београду",
title = "Spatio-temporal interpolation of climate elements using geostatistics and machine learning",
url = "https://hdl.handle.net/21.15107/rcub_nardus_18869"
}

Sekulić, A. M.. (2021-04-09). Spatio-temporal interpolation of climate elements using geostatistics and machine learning. in Универзитет у Београду
Универзитет у Београду, Грађевински факултет..
https://hdl.handle.net/21.15107/rcub_nardus_18869

Sekulić AM. Spatio-temporal interpolation of climate elements using geostatistics and machine learning. in Универзитет у Београду. 2021;.
https://hdl.handle.net/21.15107/rcub_nardus_18869 .

Sekulić, Aleksandar M., "Spatio-temporal interpolation of climate elements using geostatistics and machine learning" in Универзитет у Београду (2021-04-09),
https://hdl.handle.net/21.15107/rcub_nardus_18869 .

TY  - JOUR
AU  - Sekulić, Aleksandar
AU  - Kilibarda, Milan
AU  - Protić, Dragutin
AU  - Perčec-Tadić, Melita
AU  - Bajat, Branislav
PY  - 2020
UR  - https://link.springer.com/article/10.1007/s00704-019-03077-3
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2257
AB  - High resolution gridded mean daily temperature datasets are valuable for research and applications in agronomy, meteorology, hydrology, ecology, and many other disciplines depending on weather or climate. The gridded datasets and the models used for their estimation are being constantly improved as there is always a need for more accurate datasets as well as for datasets with a higher spatial and temporal resolution. We developed a spatio-temporal regression kriging model for Croatia at 1 km spatial resolution by adapting the spatio-temporal regression kriging model developed for global land areas. A geometrical temperature trend, digital elevation model, and topographic wetness index were used as covariates together with measurements from the Croatian national meteorological network for the year 2008. This model performed better than the global model and previously developed models for Croatia, based on MODIS land surface temperature images. The R2 was 97.8% and RMSE was 1.2 °C for leave-one-out and 5-fold cross-validation. The proposed national model still has a high level of uncertainty at higher altitudes leaving it suitable for agricultural areas that are dominant in lower and medium altitudes.
PB  - Springer Nature
T2  - Theoretical and Applied Climatology
T1  - Spatio-temporal regression kriging model of mean daily temperature for Croatia
EP  - 114
SP  - 101
VL  - 140
DO  - https://doi.org/10.1007/s00704-019-03077-3
ER  - 

@article{
author = "Sekulić, Aleksandar and Kilibarda, Milan and Protić, Dragutin and Perčec-Tadić, Melita and Bajat, Branislav",
year = "2020",
abstract = "High resolution gridded mean daily temperature datasets are valuable for research and applications in agronomy, meteorology, hydrology, ecology, and many other disciplines depending on weather or climate. The gridded datasets and the models used for their estimation are being constantly improved as there is always a need for more accurate datasets as well as for datasets with a higher spatial and temporal resolution. We developed a spatio-temporal regression kriging model for Croatia at 1 km spatial resolution by adapting the spatio-temporal regression kriging model developed for global land areas. A geometrical temperature trend, digital elevation model, and topographic wetness index were used as covariates together with measurements from the Croatian national meteorological network for the year 2008. This model performed better than the global model and previously developed models for Croatia, based on MODIS land surface temperature images. The R2 was 97.8% and RMSE was 1.2 °C for leave-one-out and 5-fold cross-validation. The proposed national model still has a high level of uncertainty at higher altitudes leaving it suitable for agricultural areas that are dominant in lower and medium altitudes.",
publisher = "Springer Nature",
journal = "Theoretical and Applied Climatology",
title = "Spatio-temporal regression kriging model of mean daily temperature for Croatia",
pages = "114-101",
volume = "140",
doi = "https://doi.org/10.1007/s00704-019-03077-3"
}

Sekulić, A., Kilibarda, M., Protić, D., Perčec-Tadić, M.,& Bajat, B.. (2020). Spatio-temporal regression kriging model of mean daily temperature for Croatia. in Theoretical and Applied Climatology
Springer Nature., 140, 101-114.
https://doi.org/https://doi.org/10.1007/s00704-019-03077-3

Sekulić A, Kilibarda M, Protić D, Perčec-Tadić M, Bajat B. Spatio-temporal regression kriging model of mean daily temperature for Croatia. in Theoretical and Applied Climatology. 2020;140:101-114.
doi:https://doi.org/10.1007/s00704-019-03077-3 .

Sekulić, Aleksandar, Kilibarda, Milan, Protić, Dragutin, Perčec-Tadić, Melita, Bajat, Branislav, "Spatio-temporal regression kriging model of mean daily temperature for Croatia" in Theoretical and Applied Climatology, 140 (2020):101-114,
https://doi.org/https://doi.org/10.1007/s00704-019-03077-3 . .

TY  - JOUR
AU  - Sekulić, Aleksandar
AU  - Kilibarda, Milan
AU  - Heuvelink, Gerard B. M.
AU  - Nikolić, Mladen
AU  - Bajat, Branislav
PY  - 2020
UR  - https://www.mdpi.com/2072-4292/12/10/1687
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1973
AB  - For many decades, kriging and deterministic interpolation techniques, such as inverse distance weighting and nearest neighbour interpolation, have been the most popular spatial interpolation techniques. Kriging with external drift and regression kriging have become basic techniques that benefit both from spatial autocorrelation and covariate information. More recently, machine learning techniques, such as random forest and gradient boosting, have become increasingly popular and are now often used for spatial interpolation. Some attempts have been made to explicitly take the spatial component into account in machine learning, but so far, none of these approaches have taken the natural route of incorporating the nearest observations and their distances to the prediction location as covariates. In this research, we explored the value of including observations at the nearest locations and their distances from the prediction location by introducing Random Forest Spatial Interpolation (RFSI). We compared RFSI with deterministic interpolation methods, ordinary kriging, regression kriging, Random Forest and Random Forest for spatial prediction (RFsp) in three case studies. The first case study made use of synthetic data, i.e., simulations from normally distributed stationary random fields with a known semivariogram, for which ordinary kriging is known to be optimal. The second and third case studies evaluated the performance of the various interpolation methods using daily precipitation data for the 2016–2018 period in Catalonia, Spain, and mean daily temperature for the year 2008 in Croatia. Results of the synthetic case study showed that RFSI outperformed most simple deterministic interpolation techniques and had similar performance as inverse distance weighting and RFsp. As expected, kriging was the most accurate technique in the synthetic case study. In the precipitation and temperature case studies, RFSI mostly outperformed regression kriging, inverse distance weighting, random forest, and RFsp. Moreover, RFSI was substantially faster than RFsp, particularly when the training dataset was large and high-resolution prediction maps were made.
PB  - MDPI
T2  - Remote Sensing
T1  - Random Forest Spatial Interpolation
IS  - 10
SP  - 1687
VL  - 12
DO  - 10.3390/rs12101687
ER  - 

@article{
author = "Sekulić, Aleksandar and Kilibarda, Milan and Heuvelink, Gerard B. M. and Nikolić, Mladen and Bajat, Branislav",
year = "2020",
abstract = "For many decades, kriging and deterministic interpolation techniques, such as inverse distance weighting and nearest neighbour interpolation, have been the most popular spatial interpolation techniques. Kriging with external drift and regression kriging have become basic techniques that benefit both from spatial autocorrelation and covariate information. More recently, machine learning techniques, such as random forest and gradient boosting, have become increasingly popular and are now often used for spatial interpolation. Some attempts have been made to explicitly take the spatial component into account in machine learning, but so far, none of these approaches have taken the natural route of incorporating the nearest observations and their distances to the prediction location as covariates. In this research, we explored the value of including observations at the nearest locations and their distances from the prediction location by introducing Random Forest Spatial Interpolation (RFSI). We compared RFSI with deterministic interpolation methods, ordinary kriging, regression kriging, Random Forest and Random Forest for spatial prediction (RFsp) in three case studies. The first case study made use of synthetic data, i.e., simulations from normally distributed stationary random fields with a known semivariogram, for which ordinary kriging is known to be optimal. The second and third case studies evaluated the performance of the various interpolation methods using daily precipitation data for the 2016–2018 period in Catalonia, Spain, and mean daily temperature for the year 2008 in Croatia. Results of the synthetic case study showed that RFSI outperformed most simple deterministic interpolation techniques and had similar performance as inverse distance weighting and RFsp. As expected, kriging was the most accurate technique in the synthetic case study. In the precipitation and temperature case studies, RFSI mostly outperformed regression kriging, inverse distance weighting, random forest, and RFsp. Moreover, RFSI was substantially faster than RFsp, particularly when the training dataset was large and high-resolution prediction maps were made.",
publisher = "MDPI",
journal = "Remote Sensing",
title = "Random Forest Spatial Interpolation",
number = "10",
pages = "1687",
volume = "12",
doi = "10.3390/rs12101687"
}

Sekulić, A., Kilibarda, M., Heuvelink, G. B. M., Nikolić, M.,& Bajat, B.. (2020). Random Forest Spatial Interpolation. in Remote Sensing
MDPI., 12(10), 1687.
https://doi.org/10.3390/rs12101687

Sekulić A, Kilibarda M, Heuvelink GBM, Nikolić M, Bajat B. Random Forest Spatial Interpolation. in Remote Sensing. 2020;12(10):1687.
doi:10.3390/rs12101687 .

Sekulić, Aleksandar, Kilibarda, Milan, Heuvelink, Gerard B. M., Nikolić, Mladen, Bajat, Branislav, "Random Forest Spatial Interpolation" in Remote Sensing, 12, no. 10 (2020):1687,
https://doi.org/10.3390/rs12101687 . .

TY  - JOUR
AU  - Višnjevac, Nenad
AU  - Mihajlović, Rajica
AU  - Šoškić, Mladen
AU  - Cvijetinović, Željko
AU  - Bajat, Branislav
PY  - 2019
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1761
AB  - 3D cadastral systems are more complex than traditional cadastral systems and they require more complex technical solutions and innovative use of developing technologies. Regarding data integrity and data consistency, 3D cadastral data should be maintained by a Database Management System (DBMS). Furthermore, there are still challenges regarding visualization of 3D cadastral data. A prototype of the 3D cadastral system based on a NoSQL database and a JavaScript application for 3D visualization is designed and tested in order to investigate the possibilities of using new technical solutions. It is assumed that this approach, with further development, could be a good basis for the development of a modern 3D cadastral system. MongoDB database is used for storing data and Cesium JavaScript library is used for 3D visualization. The system uses an LADM (Land Administration Domain Model) based data model. Additionally, script languages, libraries, application programming interfaces (APIs), software and data formats are used for the system development. The case study is based on the real cadastral data. The underground object and building units located below and above the ground level are used to test the proposed data model and the system’s functionality. The proposed system needs further development in order to provide full support to a modern 3D cadastral system. However, it allows maintenance of 3D cadastral data and basic 3D visualization with the interactive approach.
T1  - Prototype of the 3D Cadastral System Based on a NoSQL Database and a JavaScript Visualization Application
VL  - 8
DO  - 10.3390/ijgi8050227
ER  - 

@article{
author = "Višnjevac, Nenad and Mihajlović, Rajica and Šoškić, Mladen and Cvijetinović, Željko and Bajat, Branislav",
year = "2019",
abstract = "3D cadastral systems are more complex than traditional cadastral systems and they require more complex technical solutions and innovative use of developing technologies. Regarding data integrity and data consistency, 3D cadastral data should be maintained by a Database Management System (DBMS). Furthermore, there are still challenges regarding visualization of 3D cadastral data. A prototype of the 3D cadastral system based on a NoSQL database and a JavaScript application for 3D visualization is designed and tested in order to investigate the possibilities of using new technical solutions. It is assumed that this approach, with further development, could be a good basis for the development of a modern 3D cadastral system. MongoDB database is used for storing data and Cesium JavaScript library is used for 3D visualization. The system uses an LADM (Land Administration Domain Model) based data model. Additionally, script languages, libraries, application programming interfaces (APIs), software and data formats are used for the system development. The case study is based on the real cadastral data. The underground object and building units located below and above the ground level are used to test the proposed data model and the system’s functionality. The proposed system needs further development in order to provide full support to a modern 3D cadastral system. However, it allows maintenance of 3D cadastral data and basic 3D visualization with the interactive approach.",
title = "Prototype of the 3D Cadastral System Based on a NoSQL Database and a JavaScript Visualization Application",
volume = "8",
doi = "10.3390/ijgi8050227"
}

Višnjevac, N., Mihajlović, R., Šoškić, M., Cvijetinović, Ž.,& Bajat, B.. (2019). Prototype of the 3D Cadastral System Based on a NoSQL Database and a JavaScript Visualization Application. , 8.
https://doi.org/10.3390/ijgi8050227

Višnjevac N, Mihajlović R, Šoškić M, Cvijetinović Ž, Bajat B. Prototype of the 3D Cadastral System Based on a NoSQL Database and a JavaScript Visualization Application. 2019;8.
doi:10.3390/ijgi8050227 .

Višnjevac, Nenad, Mihajlović, Rajica, Šoškić, Mladen, Cvijetinović, Željko, Bajat, Branislav, "Prototype of the 3D Cadastral System Based on a NoSQL Database and a JavaScript Visualization Application", 8 (2019),
https://doi.org/10.3390/ijgi8050227 . .

TY  - CONF
AU  - Dragojević, Marko
AU  - Stančić, Nikola
PY  - 2019
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1920
AB  - The market value of apartments is, as the name itself suggests, defined by the sellers and the buyers through supply and demand – elements that collectively make up the market. Observing a large number of factors affecting the price of real estate is not an  easy  job.  Price  formation  depends  on  both  the  characteristics  of  the  apartment  and  the  buyer’s  value-system.  The  basic  question  that  a  rational  customer  asks  himself  is  "why  would  I  pay  a  larger  sum  of  money  for  the  same  or  practically  same  thing  than  what someone else paid for it just recently?". This fact leads to the conclusion that it is necessary  to  know  the  characteristics  and  prices  of  the  real  estates  traded  in  the  near  past and in the close surrounding. A comparative way of customer’s thinking is the basic principle  for  defining  one  such  model.  This  is  a  necessary  but  not  sufficient  condition.  Models  based  on  the  machine  learning  algorithms  (among  them  k-Nearest  Neighbors  algorithm) require having a larger amount of data, so that the made conclusions can be reliable, accurate, and precise.
AB  - Tržišnu vrednost stanova, kao što sama reč govori, definišu prodavci i kupci kroz ponudu i tražnju, koje u osnovi i čine samo tržište. Sagledavanje velikog broja faktora uticaja na cenu nepokretnosti nije nimalo lak posao. Formiranje cena zavisi kako od karakteristika stana, tako i od sistema vrednosti kupaca. „Zašto bih ja za istu ili sličnu stvar platio veći iznos nego što je neko drugi platio u neposrednoj prošlosti“ jeste osnovno pitanje koje racionalan kupac postavlja sebi. Ova činjenica dovodi do zaključka da je potrebno znati karakteristike i cene nepokretnosti koje su oglašene ili prometovane u neposrednoj prošlosti u bliskom okruženju. Komparativni način razmišljanja kupca je osnovni uslov i princip za definisanje jednog ovakvog modela. Ovo je neophodan, ali ne i dovoljan uslov. Modeli bazirani na algoritmima mašinskog učenja, kao što je i k-najbližih suseda, podrazumevaju poznavanje nešto veće količine kvalitetnih podataka, kako bi doneti zaključci bili pouzdani, tačni i precizni.
PB  - Subotica : Građevinski fakultet Subotica
C3  - 7th International Conference 'Contemporary Achievements in Civil Engineering 2019'
T1  - Estimating Market Value of Apartments Using the k-Nearest Neighbors Algorithm
T1  - Procena tržišne vrednosti stana metodom k-najbližih suseda
EP  - 1069
SP  - 1059
VL  - 7
DO  - 10.14415/konferencijaGFS2019.098
ER  - 

@conference{
author = "Dragojević, Marko and Stančić, Nikola",
year = "2019",
abstract = "The market value of apartments is, as the name itself suggests, defined by the sellers and the buyers through supply and demand – elements that collectively make up the market. Observing a large number of factors affecting the price of real estate is not an  easy  job.  Price  formation  depends  on  both  the  characteristics  of  the  apartment  and  the  buyer’s  value-system.  The  basic  question  that  a  rational  customer  asks  himself  is  "why  would  I  pay  a  larger  sum  of  money  for  the  same  or  practically  same  thing  than  what someone else paid for it just recently?". This fact leads to the conclusion that it is necessary  to  know  the  characteristics  and  prices  of  the  real  estates  traded  in  the  near  past and in the close surrounding. A comparative way of customer’s thinking is the basic principle  for  defining  one  such  model.  This  is  a  necessary  but  not  sufficient  condition.  Models  based  on  the  machine  learning  algorithms  (among  them  k-Nearest  Neighbors  algorithm) require having a larger amount of data, so that the made conclusions can be reliable, accurate, and precise., Tržišnu vrednost stanova, kao što sama reč govori, definišu prodavci i kupci kroz ponudu i tražnju, koje u osnovi i čine samo tržište. Sagledavanje velikog broja faktora uticaja na cenu nepokretnosti nije nimalo lak posao. Formiranje cena zavisi kako od karakteristika stana, tako i od sistema vrednosti kupaca. „Zašto bih ja za istu ili sličnu stvar platio veći iznos nego što je neko drugi platio u neposrednoj prošlosti“ jeste osnovno pitanje koje racionalan kupac postavlja sebi. Ova činjenica dovodi do zaključka da je potrebno znati karakteristike i cene nepokretnosti koje su oglašene ili prometovane u neposrednoj prošlosti u bliskom okruženju. Komparativni način razmišljanja kupca je osnovni uslov i princip za definisanje jednog ovakvog modela. Ovo je neophodan, ali ne i dovoljan uslov. Modeli bazirani na algoritmima mašinskog učenja, kao što je i k-najbližih suseda, podrazumevaju poznavanje nešto veće količine kvalitetnih podataka, kako bi doneti zaključci bili pouzdani, tačni i precizni.",
publisher = "Subotica : Građevinski fakultet Subotica",
journal = "7th International Conference 'Contemporary Achievements in Civil Engineering 2019'",
title = "Estimating Market Value of Apartments Using the k-Nearest Neighbors Algorithm, Procena tržišne vrednosti stana metodom k-najbližih suseda",
pages = "1069-1059",
volume = "7",
doi = "10.14415/konferencijaGFS2019.098"
}

Dragojević, M.,& Stančić, N.. (2019). Estimating Market Value of Apartments Using the k-Nearest Neighbors Algorithm. in 7th International Conference 'Contemporary Achievements in Civil Engineering 2019'
Subotica : Građevinski fakultet Subotica., 7, 1059-1069.
https://doi.org/10.14415/konferencijaGFS2019.098

Dragojević M, Stančić N. Estimating Market Value of Apartments Using the k-Nearest Neighbors Algorithm. in 7th International Conference 'Contemporary Achievements in Civil Engineering 2019'. 2019;7:1059-1069.
doi:10.14415/konferencijaGFS2019.098 .

Dragojević, Marko, Stančić, Nikola, "Estimating Market Value of Apartments Using the k-Nearest Neighbors Algorithm" in 7th International Conference 'Contemporary Achievements in Civil Engineering 2019', 7 (2019):1059-1069,
https://doi.org/10.14415/konferencijaGFS2019.098 . .

TY  - JOUR
AU  - Sekulić, Aleksandar
AU  - Kilibarda, Milan
AU  - Protić, Dragutin
AU  - Perčec-Tadić, Melita
AU  - Bajat, Branislav
PY  - 2019
UR  - https://link.springer.com/article/10.1007/s00704-019-03077-3
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1847
AB  - High resolution gridded mean daily temperature datasets are valuable for research and applications in agronomy, meteorology, hydrology, ecology, and many other disciplines depending on weather or climate. The gridded datasets and the models used for their estimation are being constantly improved as there is always a need for more accurate datasets as well as for datasets with a higher spatial and temporal resolution. We developed a spatio-temporal regression kriging model for Croatia at 1 km spatial resolution by adapting the spatio-temporal regression kriging model developed for global land areas. A geometrical temperature trend, digital elevation model, and topographic wetness index were used as covariates together with measurements from the Croatian national meteorological network for the year 2008. This model performed better than the global model and previously developed models for Croatia, based on MODIS land surface temperature images. The R2 was 97.8% and RMSE was 1.2 °C for leave-one-out and 5-fold cross-validation. The proposed national model still has a high level of uncertainty at higher altitudes leaving it suitable for agricultural areas that are dominant in lower and medium altitudes.
PB  - Springer
T2  - Theoretical and Applied Climatology
T1  - Spatio-temporal regression kriging model of mean daily temperature for Croatia
DO  - 10.1007/s00704-019-03077-3
ER  - 

@article{
author = "Sekulić, Aleksandar and Kilibarda, Milan and Protić, Dragutin and Perčec-Tadić, Melita and Bajat, Branislav",
year = "2019",
abstract = "High resolution gridded mean daily temperature datasets are valuable for research and applications in agronomy, meteorology, hydrology, ecology, and many other disciplines depending on weather or climate. The gridded datasets and the models used for their estimation are being constantly improved as there is always a need for more accurate datasets as well as for datasets with a higher spatial and temporal resolution. We developed a spatio-temporal regression kriging model for Croatia at 1 km spatial resolution by adapting the spatio-temporal regression kriging model developed for global land areas. A geometrical temperature trend, digital elevation model, and topographic wetness index were used as covariates together with measurements from the Croatian national meteorological network for the year 2008. This model performed better than the global model and previously developed models for Croatia, based on MODIS land surface temperature images. The R2 was 97.8% and RMSE was 1.2 °C for leave-one-out and 5-fold cross-validation. The proposed national model still has a high level of uncertainty at higher altitudes leaving it suitable for agricultural areas that are dominant in lower and medium altitudes.",
publisher = "Springer",
journal = "Theoretical and Applied Climatology",
title = "Spatio-temporal regression kriging model of mean daily temperature for Croatia",
doi = "10.1007/s00704-019-03077-3"
}

Sekulić, A., Kilibarda, M., Protić, D., Perčec-Tadić, M.,& Bajat, B.. (2019). Spatio-temporal regression kriging model of mean daily temperature for Croatia. in Theoretical and Applied Climatology
Springer..
https://doi.org/10.1007/s00704-019-03077-3

Sekulić A, Kilibarda M, Protić D, Perčec-Tadić M, Bajat B. Spatio-temporal regression kriging model of mean daily temperature for Croatia. in Theoretical and Applied Climatology. 2019;.
doi:10.1007/s00704-019-03077-3 .

Sekulić, Aleksandar, Kilibarda, Milan, Protić, Dragutin, Perčec-Tadić, Melita, Bajat, Branislav, "Spatio-temporal regression kriging model of mean daily temperature for Croatia" in Theoretical and Applied Climatology (2019),
https://doi.org/10.1007/s00704-019-03077-3 . .

TY  - CONF
AU  - Višnjevac, Nenad
AU  - Mihajlović, Rajica
AU  - Šoškić, Mladen
AU  - Cvijetinović, Željko
AU  - Marošan, Stevan
AU  - Bajat, Branislav
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1642
AB  - The  real  estate  cadastre  in  the  Republic  of  Serbia  is  based  on  2D  cadastral  maps  and procedures  that  do  not  support  unequivocal  registration  and  visualization  of  complex  3D property  situations  or  complex  objects  located  on/below  several  parcels,  especially  in  urban areas.   Within   this   study,   we   analyzed   and   documented   specific   situations   concerning registration   challenges   for   the   current   cadastral   system   in   the   Republic   of   Serbia.Furthermore,  the  analysis  of  additional  functionalities  which  will  enable  overcoming  the limitations of the current cadastre in the short to the medium-termtime period is represented. Themain  objective  is  to  use  the  current  cadastral  data  and  procedures  as  far  as  possible  in order  to  keep  the  transition  smoother  and  economicallyfeasible. Having  in  mindthis objective,thevariation  ofthe hybridapproach  as  the  solution  for  Serbian  3D  real  estate cadastrewas  analyzed.  One  of  the  preliminary  assumptions  of  this  research  is  that  it  is possible to develop a systemthat is simple enoughforimplementationand maintenance,but at  the  same  comprehensive  enough to  overcome  the  difficulties ofthe  current  real  estate cadastre.Within  the  case study,3D  objects  based  ondata  currently  provided  by  licensed surveying agenciesare presented.
PB  - FIG (International Federation of Surveyors), Delft
C3  - Proceedings of the 6th International FIG 3D Cadastre Workshop
T1  - Developing Serbian 3D Cadastre System - Challenges and Directions
EP  - 406
SP  - 383
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1642
ER  - 

@conference{
author = "Višnjevac, Nenad and Mihajlović, Rajica and Šoškić, Mladen and Cvijetinović, Željko and Marošan, Stevan and Bajat, Branislav",
year = "2018",
abstract = "The  real  estate  cadastre  in  the  Republic  of  Serbia  is  based  on  2D  cadastral  maps  and procedures  that  do  not  support  unequivocal  registration  and  visualization  of  complex  3D property  situations  or  complex  objects  located  on/below  several  parcels,  especially  in  urban areas.   Within   this   study,   we   analyzed   and   documented   specific   situations   concerning registration   challenges   for   the   current   cadastral   system   in   the   Republic   of   Serbia.Furthermore,  the  analysis  of  additional  functionalities  which  will  enable  overcoming  the limitations of the current cadastre in the short to the medium-termtime period is represented. Themain  objective  is  to  use  the  current  cadastral  data  and  procedures  as  far  as  possible  in order  to  keep  the  transition  smoother  and  economicallyfeasible. Having  in  mindthis objective,thevariation  ofthe hybridapproach  as  the  solution  for  Serbian  3D  real  estate cadastrewas  analyzed.  One  of  the  preliminary  assumptions  of  this  research  is  that  it  is possible to develop a systemthat is simple enoughforimplementationand maintenance,but at  the  same  comprehensive  enough to  overcome  the  difficulties ofthe  current  real  estate cadastre.Within  the  case study,3D  objects  based  ondata  currently  provided  by  licensed surveying agenciesare presented.",
publisher = "FIG (International Federation of Surveyors), Delft",
journal = "Proceedings of the 6th International FIG 3D Cadastre Workshop",
title = "Developing Serbian 3D Cadastre System - Challenges and Directions",
pages = "406-383",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1642"
}

Višnjevac, N., Mihajlović, R., Šoškić, M., Cvijetinović, Ž., Marošan, S.,& Bajat, B.. (2018). Developing Serbian 3D Cadastre System - Challenges and Directions. in Proceedings of the 6th International FIG 3D Cadastre Workshop
FIG (International Federation of Surveyors), Delft., 383-406.
https://hdl.handle.net/21.15107/rcub_grafar_1642

Višnjevac N, Mihajlović R, Šoškić M, Cvijetinović Ž, Marošan S, Bajat B. Developing Serbian 3D Cadastre System - Challenges and Directions. in Proceedings of the 6th International FIG 3D Cadastre Workshop. 2018;:383-406.
https://hdl.handle.net/21.15107/rcub_grafar_1642 .

Višnjevac, Nenad, Mihajlović, Rajica, Šoškić, Mladen, Cvijetinović, Željko, Marošan, Stevan, Bajat, Branislav, "Developing Serbian 3D Cadastre System - Challenges and Directions" in Proceedings of the 6th International FIG 3D Cadastre Workshop (2018):383-406,
https://hdl.handle.net/21.15107/rcub_grafar_1642 .

TY  - JOUR
AU  - Pejović, Milutin
AU  - Nikolić, Mladen
AU  - Heuvelink, Gerard B. M.
AU  - Hengl, Tomislav
AU  - Kilibarda, Milan
AU  - Bajat, Branislav
PY  - 2018
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/943
AB  - An approach for using lasso (Least Absolute Shrinkage and Selection Operator) regression in creating sparse 3D models of soil properties for spatial prediction at multiple depths is presented. Modeling soil properties in 3D benefits from interactions of spatial predictors with soil depth and its polynomial expansion, which yields a large number of model variables (and corresponding model parameters). Lasso is able to perform variable selection, hence reducing the number of model parameters and making the model more easily interpretable. This also prevents overfitting, which makes the model more accurate. The presented approach was tested using four variable selection approaches - none, stepwise, lasso and hierarchical lasso, on four kinds of models - standard linear model, linear model with polynomial expansion of depth, linear model with interactions of covariates with depth and linear model with interactions of covariates with depth and its polynomial expansion. This framework was used to predict Soil Organic Carbon (SOC) in three contrasting study areas: Bor (Serbia), Edgeroi (Australia) and the Netherlands. Results show that lasso yields substantial improvements in accuracy over standard and stepwise regression - up to 50 % of total variance. It yields models which contain up to five times less nonzero parameters than the full models and that are usually more sparse than models obtained by stepwise regression, up to three times. Extension of the standard linear model by including interactions typically improves the accuracy of models produced by lasso, but is detrimental to standard and stepwise regression. Regarding computation time, it was demonstrated that lasso is several orders of magnitude more efficient than stepwise regression for models with tens or hundreds of variables (including interactions). Proper model evaluation is emphasized. Considering the fact that lasso requires meta-parameter tuning, standard cross-validation does not suffice for adequate model evaluation, hence a nested cross-validation was employed. The presented approach is implemented as publicly available sparsereg3D R package.
PB  - Elsevier Ltd
T2  - Computers & Geosciences
T1  - Sparse regression interaction models for spatial prediction of soil properties in 3D
EP  - 13
SP  - 1
VL  - 118
DO  - 10.1016/j.cageo.2018.05.008
ER  - 

@article{
author = "Pejović, Milutin and Nikolić, Mladen and Heuvelink, Gerard B. M. and Hengl, Tomislav and Kilibarda, Milan and Bajat, Branislav",
year = "2018",
abstract = "An approach for using lasso (Least Absolute Shrinkage and Selection Operator) regression in creating sparse 3D models of soil properties for spatial prediction at multiple depths is presented. Modeling soil properties in 3D benefits from interactions of spatial predictors with soil depth and its polynomial expansion, which yields a large number of model variables (and corresponding model parameters). Lasso is able to perform variable selection, hence reducing the number of model parameters and making the model more easily interpretable. This also prevents overfitting, which makes the model more accurate. The presented approach was tested using four variable selection approaches - none, stepwise, lasso and hierarchical lasso, on four kinds of models - standard linear model, linear model with polynomial expansion of depth, linear model with interactions of covariates with depth and linear model with interactions of covariates with depth and its polynomial expansion. This framework was used to predict Soil Organic Carbon (SOC) in three contrasting study areas: Bor (Serbia), Edgeroi (Australia) and the Netherlands. Results show that lasso yields substantial improvements in accuracy over standard and stepwise regression - up to 50 % of total variance. It yields models which contain up to five times less nonzero parameters than the full models and that are usually more sparse than models obtained by stepwise regression, up to three times. Extension of the standard linear model by including interactions typically improves the accuracy of models produced by lasso, but is detrimental to standard and stepwise regression. Regarding computation time, it was demonstrated that lasso is several orders of magnitude more efficient than stepwise regression for models with tens or hundreds of variables (including interactions). Proper model evaluation is emphasized. Considering the fact that lasso requires meta-parameter tuning, standard cross-validation does not suffice for adequate model evaluation, hence a nested cross-validation was employed. The presented approach is implemented as publicly available sparsereg3D R package.",
publisher = "Elsevier Ltd",
journal = "Computers & Geosciences",
title = "Sparse regression interaction models for spatial prediction of soil properties in 3D",
pages = "13-1",
volume = "118",
doi = "10.1016/j.cageo.2018.05.008"
}

Pejović, M., Nikolić, M., Heuvelink, G. B. M., Hengl, T., Kilibarda, M.,& Bajat, B.. (2018). Sparse regression interaction models for spatial prediction of soil properties in 3D. in Computers & Geosciences
Elsevier Ltd., 118, 1-13.
https://doi.org/10.1016/j.cageo.2018.05.008

Pejović M, Nikolić M, Heuvelink GBM, Hengl T, Kilibarda M, Bajat B. Sparse regression interaction models for spatial prediction of soil properties in 3D. in Computers & Geosciences. 2018;118:1-13.
doi:10.1016/j.cageo.2018.05.008 .

Pejović, Milutin, Nikolić, Mladen, Heuvelink, Gerard B. M., Hengl, Tomislav, Kilibarda, Milan, Bajat, Branislav, "Sparse regression interaction models for spatial prediction of soil properties in 3D" in Computers & Geosciences, 118 (2018):1-13,
https://doi.org/10.1016/j.cageo.2018.05.008 . .

TY  - JOUR
AU  - Pejović, Milutin
AU  - Bajat, Branislav
AU  - Gospavić, Zagorka
AU  - Saljnikov, Elmira
AU  - Kilibarda, Milan
AU  - Cakmak, Dragan
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/821
AB  - Prevailing climatic conditions and local topography can be classified as the most influential environmental factors that affect the spatial dispersion of pollutants emanating from industrial sources. In this study, the combined effects of these factors were considered with respect to terrain exposure in order to explain the complex, spatial trend of Arsenic (As) concentration that was atmospherically-deposited from one of the largest Copper Mining and Smelting Complexes in Europe, Bor in Serbia. Several exposure parameters were created and employed as spatial covariates within the so-called "Spline-Then-Krige" approach for producing maps of As concentration at three standard soil depth layers (0-5 cm, 5-15 cm and 15-30 cm). The exposure parameters were created to quantify two different aspects of terrain exposure: Geometrical (Proximity) and Topographical exposure. Regression analysis confirmed the presence of a significant statistical association between the As data and all exposure parameters. The trend model showed good overall accuracy explaining 52% of the variance in As data for the surface soil layer, 49% for the middle layer and 35% for the deepest layer. Relative importance analysis revealed the importance of considering a more general model that includes interactions between exposure parameters. The kriging interpolation improved, to some extent, the regression accuracy for all three layers with R-2 values ranging from 55% for the surface layer to the 36% for the deepest soil layer. The prediction maps show that As contamination levels are well above allowable Serbian agricultural concentration limits (As lt mg/kg) for approximately 78% of the mapping area, thereby indicating that long term smelting activity leaves significant consequences on soil even on deeper unexposed layers.
PB  - Elsevier B.V.
T2  - Journal of Geochemical Exploration
T1  - Layer-specific spatial prediction of As concentration in copper smelter vicinity considering the terrain exposure
EP  - 35
SP  - 25
VL  - 179
DO  - 10.1016/j.gexplo.2017.05.004
ER  - 

@article{
author = "Pejović, Milutin and Bajat, Branislav and Gospavić, Zagorka and Saljnikov, Elmira and Kilibarda, Milan and Cakmak, Dragan",
year = "2017",
abstract = "Prevailing climatic conditions and local topography can be classified as the most influential environmental factors that affect the spatial dispersion of pollutants emanating from industrial sources. In this study, the combined effects of these factors were considered with respect to terrain exposure in order to explain the complex, spatial trend of Arsenic (As) concentration that was atmospherically-deposited from one of the largest Copper Mining and Smelting Complexes in Europe, Bor in Serbia. Several exposure parameters were created and employed as spatial covariates within the so-called "Spline-Then-Krige" approach for producing maps of As concentration at three standard soil depth layers (0-5 cm, 5-15 cm and 15-30 cm). The exposure parameters were created to quantify two different aspects of terrain exposure: Geometrical (Proximity) and Topographical exposure. Regression analysis confirmed the presence of a significant statistical association between the As data and all exposure parameters. The trend model showed good overall accuracy explaining 52% of the variance in As data for the surface soil layer, 49% for the middle layer and 35% for the deepest layer. Relative importance analysis revealed the importance of considering a more general model that includes interactions between exposure parameters. The kriging interpolation improved, to some extent, the regression accuracy for all three layers with R-2 values ranging from 55% for the surface layer to the 36% for the deepest soil layer. The prediction maps show that As contamination levels are well above allowable Serbian agricultural concentration limits (As lt mg/kg) for approximately 78% of the mapping area, thereby indicating that long term smelting activity leaves significant consequences on soil even on deeper unexposed layers.",
publisher = "Elsevier B.V.",
journal = "Journal of Geochemical Exploration",
title = "Layer-specific spatial prediction of As concentration in copper smelter vicinity considering the terrain exposure",
pages = "35-25",
volume = "179",
doi = "10.1016/j.gexplo.2017.05.004"
}

Pejović, M., Bajat, B., Gospavić, Z., Saljnikov, E., Kilibarda, M.,& Cakmak, D.. (2017). Layer-specific spatial prediction of As concentration in copper smelter vicinity considering the terrain exposure. in Journal of Geochemical Exploration
Elsevier B.V.., 179, 25-35.
https://doi.org/10.1016/j.gexplo.2017.05.004

Pejović M, Bajat B, Gospavić Z, Saljnikov E, Kilibarda M, Cakmak D. Layer-specific spatial prediction of As concentration in copper smelter vicinity considering the terrain exposure. in Journal of Geochemical Exploration. 2017;179:25-35.
doi:10.1016/j.gexplo.2017.05.004 .

Pejović, Milutin, Bajat, Branislav, Gospavić, Zagorka, Saljnikov, Elmira, Kilibarda, Milan, Cakmak, Dragan, "Layer-specific spatial prediction of As concentration in copper smelter vicinity considering the terrain exposure" in Journal of Geochemical Exploration, 179 (2017):25-35,
https://doi.org/10.1016/j.gexplo.2017.05.004 . .

TY  - JOUR
AU  - Samardžić-Petrović, Mileva
AU  - Kovačević, Miloš
AU  - Bajat, Branislav
AU  - Dragićević, Suzana
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/865
AB  - The representation of land use change (LUC) is often achieved by using data-driven methods that include machine learning (ML) techniques. The main objectives of this research study are to implement three ML techniques, Decision Trees (DT), Neural Networks (NN), and Support Vector Machines (SVM) for LUC modeling, in order to compare these three ML techniques and to find the appropriate data representation. The ML techniques are applied on the case study of LUC in three municipalities of the City of Belgrade, the Republic of Serbia, using historical geospatial data sets and considering nine land use classes. The ML models were built and assessed using two different time intervals. The information gain ranking technique and the recursive attribute elimination procedure were implemented to find the most informative attributes that were related to LUC in the study area. The results indicate that all three ML techniques can be used effectively for short-term forecasting of LUC, but the SVM achieved the highest agreement of predicted changes.
PB  - MDPI AG
T2  - Isprs International Journal of Geo-Information
T1  - Machine Learning Techniques for Modelling Short Term Land-Use Change
IS  - 12
VL  - 6
DO  - 10.3390/ijgi6120387
ER  - 

@article{
author = "Samardžić-Petrović, Mileva and Kovačević, Miloš and Bajat, Branislav and Dragićević, Suzana",
year = "2017",
abstract = "The representation of land use change (LUC) is often achieved by using data-driven methods that include machine learning (ML) techniques. The main objectives of this research study are to implement three ML techniques, Decision Trees (DT), Neural Networks (NN), and Support Vector Machines (SVM) for LUC modeling, in order to compare these three ML techniques and to find the appropriate data representation. The ML techniques are applied on the case study of LUC in three municipalities of the City of Belgrade, the Republic of Serbia, using historical geospatial data sets and considering nine land use classes. The ML models were built and assessed using two different time intervals. The information gain ranking technique and the recursive attribute elimination procedure were implemented to find the most informative attributes that were related to LUC in the study area. The results indicate that all three ML techniques can be used effectively for short-term forecasting of LUC, but the SVM achieved the highest agreement of predicted changes.",
publisher = "MDPI AG",
journal = "Isprs International Journal of Geo-Information",
title = "Machine Learning Techniques for Modelling Short Term Land-Use Change",
number = "12",
volume = "6",
doi = "10.3390/ijgi6120387"
}

Samardžić-Petrović, M., Kovačević, M., Bajat, B.,& Dragićević, S.. (2017). Machine Learning Techniques for Modelling Short Term Land-Use Change. in Isprs International Journal of Geo-Information
MDPI AG., 6(12).
https://doi.org/10.3390/ijgi6120387

Samardžić-Petrović M, Kovačević M, Bajat B, Dragićević S. Machine Learning Techniques for Modelling Short Term Land-Use Change. in Isprs International Journal of Geo-Information. 2017;6(12).
doi:10.3390/ijgi6120387 .

Samardžić-Petrović, Mileva, Kovačević, Miloš, Bajat, Branislav, Dragićević, Suzana, "Machine Learning Techniques for Modelling Short Term Land-Use Change" in Isprs International Journal of Geo-Information, 6, no. 12 (2017),
https://doi.org/10.3390/ijgi6120387 . .

TY  - JOUR
AU  - Samardžić-Petrović, Mileva
AU  - Dragićević, Suzana
AU  - Kovačević, Miloš
AU  - Bajat, Branislav
PY  - 2016
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/777
AB  - Support Vector Machines (SVM) is a machine learning (ML) algorithm commonly applied to the classification of remotely sensing data and more recently for modeling land use changes. However, in most geospatial applications the current literature does not elaborate on specifications of the SVM method with respect to data sampling, attribute selection and optimal parameters choices. Therefore the main objective of this study is to present and investigate the SVM technique for modeling urban land use change. The SVM model building procedure is presented together with the detailed evaluation of the output results with respect to the choice of datasets, attributes and the change of SVM parameters. Geospatial datasets containing nine land use classes and spatial attributes for the Municipality of Zemun, Republic of Serbia were used for years 2001, 2003, 2007 and 2011. The Correlation-based Feature Subset method, kappa coefficient, Area Under Receiver Operating Characteristic Curve (AUC) and kappa simulation were used to perform the model evaluation and compare the model outputs with the real land use datasets. The obtained results indicate that the SVM-based models perform better when implementing balanced data sampling, reduced data sets to informative subsets of attributes and properly identify the optimal learning parameters.
PB  - Blackwell Publishing Ltd
T2  - Transactions in Gis
T1  - Modeling Urban Land Use Changes Using Support Vector Machines
EP  - 734
IS  - 5
SP  - 718
VL  - 20
DO  - 10.1111/tgis.12174
ER  - 

@article{
author = "Samardžić-Petrović, Mileva and Dragićević, Suzana and Kovačević, Miloš and Bajat, Branislav",
year = "2016",
abstract = "Support Vector Machines (SVM) is a machine learning (ML) algorithm commonly applied to the classification of remotely sensing data and more recently for modeling land use changes. However, in most geospatial applications the current literature does not elaborate on specifications of the SVM method with respect to data sampling, attribute selection and optimal parameters choices. Therefore the main objective of this study is to present and investigate the SVM technique for modeling urban land use change. The SVM model building procedure is presented together with the detailed evaluation of the output results with respect to the choice of datasets, attributes and the change of SVM parameters. Geospatial datasets containing nine land use classes and spatial attributes for the Municipality of Zemun, Republic of Serbia were used for years 2001, 2003, 2007 and 2011. The Correlation-based Feature Subset method, kappa coefficient, Area Under Receiver Operating Characteristic Curve (AUC) and kappa simulation were used to perform the model evaluation and compare the model outputs with the real land use datasets. The obtained results indicate that the SVM-based models perform better when implementing balanced data sampling, reduced data sets to informative subsets of attributes and properly identify the optimal learning parameters.",
publisher = "Blackwell Publishing Ltd",
journal = "Transactions in Gis",
title = "Modeling Urban Land Use Changes Using Support Vector Machines",
pages = "734-718",
number = "5",
volume = "20",
doi = "10.1111/tgis.12174"
}

Samardžić-Petrović, M., Dragićević, S., Kovačević, M.,& Bajat, B.. (2016). Modeling Urban Land Use Changes Using Support Vector Machines. in Transactions in Gis
Blackwell Publishing Ltd., 20(5), 718-734.
https://doi.org/10.1111/tgis.12174

Samardžić-Petrović M, Dragićević S, Kovačević M, Bajat B. Modeling Urban Land Use Changes Using Support Vector Machines. in Transactions in Gis. 2016;20(5):718-734.
doi:10.1111/tgis.12174 .

Samardžić-Petrović, Mileva, Dragićević, Suzana, Kovačević, Miloš, Bajat, Branislav, "Modeling Urban Land Use Changes Using Support Vector Machines" in Transactions in Gis, 20, no. 5 (2016):718-734,
https://doi.org/10.1111/tgis.12174 . .

TY  - JOUR
AU  - Samardžić-Petrović, Mileva
AU  - Dragićević, Suzana
AU  - Bajat, Branislav
AU  - Kovačević, Miloš
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1043
T2  - Geomatica
T1  - Exploring the Decision Tree Method for Modelling Urban Land Use Change
EP  - 325
IS  - 3
SP  - 313
VL  - 69
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1043
ER  - 

@article{
author = "Samardžić-Petrović, Mileva and Dragićević, Suzana and Bajat, Branislav and Kovačević, Miloš",
year = "2015",
journal = "Geomatica",
title = "Exploring the Decision Tree Method for Modelling Urban Land Use Change",
pages = "325-313",
number = "3",
volume = "69",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1043"
}

Samardžić-Petrović, M., Dragićević, S., Bajat, B.,& Kovačević, M.. (2015). Exploring the Decision Tree Method for Modelling Urban Land Use Change. in Geomatica, 69(3), 313-325.
https://hdl.handle.net/21.15107/rcub_grafar_1043

Samardžić-Petrović M, Dragićević S, Bajat B, Kovačević M. Exploring the Decision Tree Method for Modelling Urban Land Use Change. in Geomatica. 2015;69(3):313-325.
https://hdl.handle.net/21.15107/rcub_grafar_1043 .

Samardžić-Petrović, Mileva, Dragićević, Suzana, Bajat, Branislav, Kovačević, Miloš, "Exploring the Decision Tree Method for Modelling Urban Land Use Change" in Geomatica, 69, no. 3 (2015):313-325,
https://hdl.handle.net/21.15107/rcub_grafar_1043 .

TY  - JOUR
AU  - Bajat, Branislav
AU  - Blagojević, Dragan
AU  - Kilibarda, Milan
AU  - Luković, Jelena
AU  - Tosić, Ivana
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/721
AB  - The spatial analysis of annual and seasonal temperature trends in Serbia during the period 1961-2010 was carried out using mean monthly data from 64 meteorological stations. Change year detection was achieved using cumulative sum charts. The magnitude of trends was derived from the slopes of linear trends using the least square method. The same formalism of least square method was used to assess the statistical significance of the determined trends. Maps of temperature trends were generated by applying a spatial regression method to visualize the detected tendencies. The obtained results indicate a negative temperature trend for the period before the change year except for winter and a more pronounced positive trend after the change year. Besides being more pronounced, the vast majority of trends after the change year were also clearly statistically significant. Our estimate of the average temperature trend over Serbia is in agreement with those obtained at the global and European scale. Calculated global autocorrelation statistics (Moran's I) indicate an apparent random spatial pattern of temperature trends across the Serbia for both periods before and after the change year.
PB  - Springer-Verlag Wien
T2  - Theoretical and Applied Climatology
T1  - Spatial analysis of the temperature trends in Serbia during the period 1961-2010
EP  - 301
IS  - 1-2
SP  - 289
VL  - 121
DO  - 10.1007/s00704-014-1243-7
ER  - 

@article{
author = "Bajat, Branislav and Blagojević, Dragan and Kilibarda, Milan and Luković, Jelena and Tosić, Ivana",
year = "2015",
abstract = "The spatial analysis of annual and seasonal temperature trends in Serbia during the period 1961-2010 was carried out using mean monthly data from 64 meteorological stations. Change year detection was achieved using cumulative sum charts. The magnitude of trends was derived from the slopes of linear trends using the least square method. The same formalism of least square method was used to assess the statistical significance of the determined trends. Maps of temperature trends were generated by applying a spatial regression method to visualize the detected tendencies. The obtained results indicate a negative temperature trend for the period before the change year except for winter and a more pronounced positive trend after the change year. Besides being more pronounced, the vast majority of trends after the change year were also clearly statistically significant. Our estimate of the average temperature trend over Serbia is in agreement with those obtained at the global and European scale. Calculated global autocorrelation statistics (Moran's I) indicate an apparent random spatial pattern of temperature trends across the Serbia for both periods before and after the change year.",
publisher = "Springer-Verlag Wien",
journal = "Theoretical and Applied Climatology",
title = "Spatial analysis of the temperature trends in Serbia during the period 1961-2010",
pages = "301-289",
number = "1-2",
volume = "121",
doi = "10.1007/s00704-014-1243-7"
}

Bajat, B., Blagojević, D., Kilibarda, M., Luković, J.,& Tosić, I.. (2015). Spatial analysis of the temperature trends in Serbia during the period 1961-2010. in Theoretical and Applied Climatology
Springer-Verlag Wien., 121(1-2), 289-301.
https://doi.org/10.1007/s00704-014-1243-7

Bajat B, Blagojević D, Kilibarda M, Luković J, Tosić I. Spatial analysis of the temperature trends in Serbia during the period 1961-2010. in Theoretical and Applied Climatology. 2015;121(1-2):289-301.
doi:10.1007/s00704-014-1243-7 .

Bajat, Branislav, Blagojević, Dragan, Kilibarda, Milan, Luković, Jelena, Tosić, Ivana, "Spatial analysis of the temperature trends in Serbia during the period 1961-2010" in Theoretical and Applied Climatology, 121, no. 1-2 (2015):289-301,
https://doi.org/10.1007/s00704-014-1243-7 . .

TY  - JOUR
AU  - Luković, Jelena
AU  - Blagojević, Dragan
AU  - Kilibarda, Milan
AU  - Bajat, Branislav
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/726
AB  - This study examines the spatial pattern of relationships between annual, seasonal and monthly rainfall in Serbia, and the North Atlantic Oscillation (NAO) for the period of 1961-2009. The first correlation analysis between rainfall and the NAO was performed using a Pearson product-moment test. Results suggested negative, mainly statistically significant correlations at annual and winter scales as was expected. However, the highest percentage of stations showed significant result in October suggesting a strong impact of a large scale atmospheric mode throughout a wet season in Serbia. Further spatial analysis that incorporated a spatial autocorrelation statistic of correlation coefficients showed significant clustering at all temporal scales.
PB  - Elsevier
T2  - Spatial Statistics
T1  - Spatial pattern of North Atlantic Oscillation impact on rainfall in Serbia
EP  - 52
SP  - 39
VL  - 14
DO  - 10.1016/j.spasta.2015.04.007
ER  - 

@article{
author = "Luković, Jelena and Blagojević, Dragan and Kilibarda, Milan and Bajat, Branislav",
year = "2015",
abstract = "This study examines the spatial pattern of relationships between annual, seasonal and monthly rainfall in Serbia, and the North Atlantic Oscillation (NAO) for the period of 1961-2009. The first correlation analysis between rainfall and the NAO was performed using a Pearson product-moment test. Results suggested negative, mainly statistically significant correlations at annual and winter scales as was expected. However, the highest percentage of stations showed significant result in October suggesting a strong impact of a large scale atmospheric mode throughout a wet season in Serbia. Further spatial analysis that incorporated a spatial autocorrelation statistic of correlation coefficients showed significant clustering at all temporal scales.",
publisher = "Elsevier",
journal = "Spatial Statistics",
title = "Spatial pattern of North Atlantic Oscillation impact on rainfall in Serbia",
pages = "52-39",
volume = "14",
doi = "10.1016/j.spasta.2015.04.007"
}

Luković, J., Blagojević, D., Kilibarda, M.,& Bajat, B.. (2015). Spatial pattern of North Atlantic Oscillation impact on rainfall in Serbia. in Spatial Statistics
Elsevier., 14, 39-52.
https://doi.org/10.1016/j.spasta.2015.04.007

Luković J, Blagojević D, Kilibarda M, Bajat B. Spatial pattern of North Atlantic Oscillation impact on rainfall in Serbia. in Spatial Statistics. 2015;14:39-52.
doi:10.1016/j.spasta.2015.04.007 .

Luković, Jelena, Blagojević, Dragan, Kilibarda, Milan, Bajat, Branislav, "Spatial pattern of North Atlantic Oscillation impact on rainfall in Serbia" in Spatial Statistics, 14 (2015):39-52,
https://doi.org/10.1016/j.spasta.2015.04.007 . .

TY  - JOUR
AU  - Luković, Jelena
AU  - Bajat, Branislav
AU  - Kilibarda, Milan
AU  - Filipović, Dejan J.
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/699
AB  - Solar radiation is a key driving force for many natural processes. At the Earth's surface solar radiation is the result of complex interactions between the atmosphere and Earth's surface. Our study highlights the development and evaluation of a data base of potential solar radiation that is based on a digital elevation model with a resolution of 90 m over Serbia. The main aim of this paper is to map solar radiation in Serbia using digital elevation model. This is so far the finest resolution being applied and presented using this model. The final results of the potential direct, diffuse and total solar radiation as well as duration of insolation databases of Serbia are portrayed as thematic maps that can be communicated and shared easily through the cartographic web map-based service.
PB  - Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd
T2  - Thermal Science
T1  - High resolution grid of potential incoming solar radiation for Serbia
VL  - 19
DO  - 10.2298/TSCI150430134L
ER  - 

@article{
author = "Luković, Jelena and Bajat, Branislav and Kilibarda, Milan and Filipović, Dejan J.",
year = "2015",
abstract = "Solar radiation is a key driving force for many natural processes. At the Earth's surface solar radiation is the result of complex interactions between the atmosphere and Earth's surface. Our study highlights the development and evaluation of a data base of potential solar radiation that is based on a digital elevation model with a resolution of 90 m over Serbia. The main aim of this paper is to map solar radiation in Serbia using digital elevation model. This is so far the finest resolution being applied and presented using this model. The final results of the potential direct, diffuse and total solar radiation as well as duration of insolation databases of Serbia are portrayed as thematic maps that can be communicated and shared easily through the cartographic web map-based service.",
publisher = "Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd",
journal = "Thermal Science",
title = "High resolution grid of potential incoming solar radiation for Serbia",
volume = "19",
doi = "10.2298/TSCI150430134L"
}

Luković, J., Bajat, B., Kilibarda, M.,& Filipović, D. J.. (2015). High resolution grid of potential incoming solar radiation for Serbia. in Thermal Science
Univerzitet u Beogradu - Institut za nuklearne nauke Vinča, Beograd., 19.
https://doi.org/10.2298/TSCI150430134L

Luković J, Bajat B, Kilibarda M, Filipović DJ. High resolution grid of potential incoming solar radiation for Serbia. in Thermal Science. 2015;19.
doi:10.2298/TSCI150430134L .

Luković, Jelena, Bajat, Branislav, Kilibarda, Milan, Filipović, Dejan J., "High resolution grid of potential incoming solar radiation for Serbia" in Thermal Science, 19 (2015),
https://doi.org/10.2298/TSCI150430134L . .

TY  - JOUR
AU  - Burić, D.
AU  - Luković, Jelena
AU  - Bajat, Branislav
AU  - Kilibarda, Milan
AU  - Živković, N.
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/720
AB  - More intense rainfall may cause a range of negative impacts upon society and the environment. In this study we analysed trends in extreme ETCCDI (Expert Team on Climate Change Detection and Indices) rainfall indices in Montenegro for the period between 1951 and 2010. Montenegro has been poorly studied in terms of rainfall extremes, yet it contains the wettest Mediterranean region known as Krivosije. Several indices of precipitation extremes were assessed including the number of dry days and rainfall totals in order to identify trends and possible changes. A spatial pattern relationship between extreme rainfall indices and the North Atlantic Oscillation has also been examined. The results generally suggest that the number of days with precipitation decreased while rainfall intensity increased, particularly in south-western parts of the country. A slight tendency towards intense rainfall events is suggested. The examined rainfall indices and North Atlantic Oscillation over Montenegro seemed to be directly linked to changes in one of the major large-scale circulation modes such as the NAO pattern that is particularly evident during the winter season.
PB  - Copernicus GmbH
T2  - Natural Hazards and Earth System Sciences
T1  - Recent trends in daily rainfall extremes over Montenegro (1951-2010)
EP  - 2077
IS  - 9
SP  - 2069
VL  - 15
DO  - 10.5194/nhess-15-2069-2015
ER  - 

@article{
author = "Burić, D. and Luković, Jelena and Bajat, Branislav and Kilibarda, Milan and Živković, N.",
year = "2015",
abstract = "More intense rainfall may cause a range of negative impacts upon society and the environment. In this study we analysed trends in extreme ETCCDI (Expert Team on Climate Change Detection and Indices) rainfall indices in Montenegro for the period between 1951 and 2010. Montenegro has been poorly studied in terms of rainfall extremes, yet it contains the wettest Mediterranean region known as Krivosije. Several indices of precipitation extremes were assessed including the number of dry days and rainfall totals in order to identify trends and possible changes. A spatial pattern relationship between extreme rainfall indices and the North Atlantic Oscillation has also been examined. The results generally suggest that the number of days with precipitation decreased while rainfall intensity increased, particularly in south-western parts of the country. A slight tendency towards intense rainfall events is suggested. The examined rainfall indices and North Atlantic Oscillation over Montenegro seemed to be directly linked to changes in one of the major large-scale circulation modes such as the NAO pattern that is particularly evident during the winter season.",
publisher = "Copernicus GmbH",
journal = "Natural Hazards and Earth System Sciences",
title = "Recent trends in daily rainfall extremes over Montenegro (1951-2010)",
pages = "2077-2069",
number = "9",
volume = "15",
doi = "10.5194/nhess-15-2069-2015"
}

Burić, D., Luković, J., Bajat, B., Kilibarda, M.,& Živković, N.. (2015). Recent trends in daily rainfall extremes over Montenegro (1951-2010). in Natural Hazards and Earth System Sciences
Copernicus GmbH., 15(9), 2069-2077.
https://doi.org/10.5194/nhess-15-2069-2015

Burić D, Luković J, Bajat B, Kilibarda M, Živković N. Recent trends in daily rainfall extremes over Montenegro (1951-2010). in Natural Hazards and Earth System Sciences. 2015;15(9):2069-2077.
doi:10.5194/nhess-15-2069-2015 .

Burić, D., Luković, Jelena, Bajat, Branislav, Kilibarda, Milan, Živković, N., "Recent trends in daily rainfall extremes over Montenegro (1951-2010)" in Natural Hazards and Earth System Sciences, 15, no. 9 (2015):2069-2077,
https://doi.org/10.5194/nhess-15-2069-2015 . .

TY  - JOUR
AU  - Nedeljković, Zoran
AU  - Sekulić, Aleksandar
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/686
AB  - There are many users of spatial information, and quite large interest about the nature and genesis of such information. Different users found spatial information in the form of maps, plans or alphanumerical tables. Recently, there are more often in the form of spatial databases, and in the form of geographic information systems. What is behind these spatial data? On what foundation are they designed? In this article we look at the basic aspects of space, dimensionality and global coordinate systems in applications of global geospatial research. Here is explained the definition of the coordinate system as an abstract entity and, consequently, its implementation or establishment in the form of a geodetic reference frame, as real geodetic reference network. The applicative aspect of coordinate systems in this article is emphasized through recommendations and considerations during usage of their different implementations. .
AB  - Brojni su korisnici informacija o prostoru, čije je interesovanje o samoj njihovoj prirodi i nastanku, prilično veliko. Same prostorne informacije različiti korisnici pronalaze u vidu karata, planova ili alfanumeričkih tabela. U novije vreme, sve češće u vidu prostornih baza podataka, u obliku geografskih informacionih sistema. Šta stoji u osnovi ovakvih prostornih podloga? Na kakvim temeljima su one zasnovane? U ovom članku se posmatraju osnovni aspekti prostora, dimenzionalnost i globalni koordinatni sistemi u primenama kod globanih geoprostornih istraživanja. Objašnjava se definisanje koordinatnog sistema kao apstraktnog entiteta i posledično, njihova realizacija ili uspostavljanje u vidu geodetskog referentnog okvira, kao realne referentne geodetske mreže. Aplikativni aspekt koordinatnih sistema se u članku apostrofira kroz preporuke i obazrivost u postupku korišćenja njihovih različitih realizacija. .
PB  - Srpsko geografsko društvo, Beograd
T2  - Glasnik Srpskog geografskog društva
T1  - Concept of spatial coordinate systems, their defining and implementation as a precondition in geospatial applications
T1  - Koncept prostornih koordinatnih sistema, njihovo definisanje i realizacija kao preduslov u geoprostornim primenama
EP  - 102
IS  - 4
SP  - 77
VL  - 95
DO  - 10.2298/GSGD1504077N
ER  - 

@article{
author = "Nedeljković, Zoran and Sekulić, Aleksandar",
year = "2015",
abstract = "There are many users of spatial information, and quite large interest about the nature and genesis of such information. Different users found spatial information in the form of maps, plans or alphanumerical tables. Recently, there are more often in the form of spatial databases, and in the form of geographic information systems. What is behind these spatial data? On what foundation are they designed? In this article we look at the basic aspects of space, dimensionality and global coordinate systems in applications of global geospatial research. Here is explained the definition of the coordinate system as an abstract entity and, consequently, its implementation or establishment in the form of a geodetic reference frame, as real geodetic reference network. The applicative aspect of coordinate systems in this article is emphasized through recommendations and considerations during usage of their different implementations. ., Brojni su korisnici informacija o prostoru, čije je interesovanje o samoj njihovoj prirodi i nastanku, prilično veliko. Same prostorne informacije različiti korisnici pronalaze u vidu karata, planova ili alfanumeričkih tabela. U novije vreme, sve češće u vidu prostornih baza podataka, u obliku geografskih informacionih sistema. Šta stoji u osnovi ovakvih prostornih podloga? Na kakvim temeljima su one zasnovane? U ovom članku se posmatraju osnovni aspekti prostora, dimenzionalnost i globalni koordinatni sistemi u primenama kod globanih geoprostornih istraživanja. Objašnjava se definisanje koordinatnog sistema kao apstraktnog entiteta i posledično, njihova realizacija ili uspostavljanje u vidu geodetskog referentnog okvira, kao realne referentne geodetske mreže. Aplikativni aspekt koordinatnih sistema se u članku apostrofira kroz preporuke i obazrivost u postupku korišćenja njihovih različitih realizacija. .",
publisher = "Srpsko geografsko društvo, Beograd",
journal = "Glasnik Srpskog geografskog društva",
title = "Concept of spatial coordinate systems, their defining and implementation as a precondition in geospatial applications, Koncept prostornih koordinatnih sistema, njihovo definisanje i realizacija kao preduslov u geoprostornim primenama",
pages = "102-77",
number = "4",
volume = "95",
doi = "10.2298/GSGD1504077N"
}

Nedeljković, Z.,& Sekulić, A.. (2015). Concept of spatial coordinate systems, their defining and implementation as a precondition in geospatial applications. in Glasnik Srpskog geografskog društva
Srpsko geografsko društvo, Beograd., 95(4), 77-102.
https://doi.org/10.2298/GSGD1504077N

Nedeljković Z, Sekulić A. Concept of spatial coordinate systems, their defining and implementation as a precondition in geospatial applications. in Glasnik Srpskog geografskog društva. 2015;95(4):77-102.
doi:10.2298/GSGD1504077N .

Nedeljković, Zoran, Sekulić, Aleksandar, "Concept of spatial coordinate systems, their defining and implementation as a precondition in geospatial applications" in Glasnik Srpskog geografskog društva, 95, no. 4 (2015):77-102,
https://doi.org/10.2298/GSGD1504077N . .

TY  - CONF
AU  - Bajat, Branislav
AU  - Krunić, Nikola
AU  - Kilibarda, Milan
AU  - Sekulić, Aleksandar
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1279
PB  - University of Belgrade, Faculty of Mining and Geology, Belgrade
C3  - Procedings / 2nd Regional Symposium on Landslides in the Adriatic-Balkan Region : 2nd ReSyLAB 2015
T1  - Assessment of population vulnerability in risk analysis using dasymetric database of Serbia
EP  - 96
SP  - 93
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1279
ER  - 

@conference{
author = "Bajat, Branislav and Krunić, Nikola and Kilibarda, Milan and Sekulić, Aleksandar",
year = "2015",
publisher = "University of Belgrade, Faculty of Mining and Geology, Belgrade",
journal = "Procedings / 2nd Regional Symposium on Landslides in the Adriatic-Balkan Region : 2nd ReSyLAB 2015",
title = "Assessment of population vulnerability in risk analysis using dasymetric database of Serbia",
pages = "96-93",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1279"
}

Bajat, B., Krunić, N., Kilibarda, M.,& Sekulić, A.. (2015). Assessment of population vulnerability in risk analysis using dasymetric database of Serbia. in Procedings / 2nd Regional Symposium on Landslides in the Adriatic-Balkan Region : 2nd ReSyLAB 2015
University of Belgrade, Faculty of Mining and Geology, Belgrade., 93-96.
https://hdl.handle.net/21.15107/rcub_grafar_1279

Bajat B, Krunić N, Kilibarda M, Sekulić A. Assessment of population vulnerability in risk analysis using dasymetric database of Serbia. in Procedings / 2nd Regional Symposium on Landslides in the Adriatic-Balkan Region : 2nd ReSyLAB 2015. 2015;:93-96.
https://hdl.handle.net/21.15107/rcub_grafar_1279 .

Bajat, Branislav, Krunić, Nikola, Kilibarda, Milan, Sekulić, Aleksandar, "Assessment of population vulnerability in risk analysis using dasymetric database of Serbia" in Procedings / 2nd Regional Symposium on Landslides in the Adriatic-Balkan Region : 2nd ReSyLAB 2015 (2015):93-96,
https://hdl.handle.net/21.15107/rcub_grafar_1279 .

TY  - JOUR
AU  - Kilibarda, Milan
AU  - Tadić-Percec, Melita
AU  - Hengl, Tomislav
AU  - Luković, Jelena
AU  - Bajat, Branislav
PY  - 2015
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/695
AB  - This article highlights the results of an assessment of representation and usability of global temperature station data for global spatio-temporal analysis. Datasets from the Global Surface Summary of Day (GSOD) and the European Climate Assessment & Dataset (ECA&D) were merged and consisted of 10,695 global stations for the year 2011. Three aspects of data quality were considered: (a) representation in the geographical domain, (b) representation in the feature space (based on the MaxEnt method), and
PB  - Elsevier
T2  - Spatial Statistics
T1  - Global geographic and feature space coverage of temperature data in the context of spatio-temporal interpolation
EP  - 38
SP  - 22
VL  - 14
DO  - 10.1016/j.spasta.2015.04.005
ER  - 

@article{
author = "Kilibarda, Milan and Tadić-Percec, Melita and Hengl, Tomislav and Luković, Jelena and Bajat, Branislav",
year = "2015",
abstract = "This article highlights the results of an assessment of representation and usability of global temperature station data for global spatio-temporal analysis. Datasets from the Global Surface Summary of Day (GSOD) and the European Climate Assessment & Dataset (ECA&D) were merged and consisted of 10,695 global stations for the year 2011. Three aspects of data quality were considered: (a) representation in the geographical domain, (b) representation in the feature space (based on the MaxEnt method), and",
publisher = "Elsevier",
journal = "Spatial Statistics",
title = "Global geographic and feature space coverage of temperature data in the context of spatio-temporal interpolation",
pages = "38-22",
volume = "14",
doi = "10.1016/j.spasta.2015.04.005"
}

Kilibarda, M., Tadić-Percec, M., Hengl, T., Luković, J.,& Bajat, B.. (2015). Global geographic and feature space coverage of temperature data in the context of spatio-temporal interpolation. in Spatial Statistics
Elsevier., 14, 22-38.
https://doi.org/10.1016/j.spasta.2015.04.005

Kilibarda M, Tadić-Percec M, Hengl T, Luković J, Bajat B. Global geographic and feature space coverage of temperature data in the context of spatio-temporal interpolation. in Spatial Statistics. 2015;14:22-38.
doi:10.1016/j.spasta.2015.04.005 .

Kilibarda, Milan, Tadić-Percec, Melita, Hengl, Tomislav, Luković, Jelena, Bajat, Branislav, "Global geographic and feature space coverage of temperature data in the context of spatio-temporal interpolation" in Spatial Statistics, 14 (2015):22-38,
https://doi.org/10.1016/j.spasta.2015.04.005 . .

TY  - THES
AU  - Samardžić-Petrović, Mileva
PY  - 2014
UR  - http://eteze.bg.ac.rs/application/showtheses?thesesId=3529
UR  - https://fedorabg.bg.ac.rs/fedora/get/o:12234/bdef:Content/download
UR  - http://vbs.rs/scripts/cobiss?command=DISPLAY&base=70036&RID=46210831
UR  - http://nardus.mpn.gov.rs/123456789/6136
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1985
AB  - One of the main tasks of data-driven modelling methods is to induce arepresentative model of underlying spatial - temporal processes using past dataand data mining and machine learning approach. As relatively new methods,known to be capable of solving complex nonlinear problems, data-driven methodsare insufficiently researched in the field of land use. The main objective of thisdissertation is to develop a methodology for predictive urban land use changemodels using data-driven approach together with evaluation of the performance ofdifferent data-driven methods, which in the stage of finding patterns of land usechanges use three different machine learning techniques: Decision Trees, NeuralNetworks and Support Vector Machines. The proposed methodology of data-drivenmethods was presented and special attention was paid to different datarepresentation, data sampling and the selection of attributes by four methods (χ2,Info Gain, Gain Ratio and Correlation-based Feature Subset) that best describe theprocess of land use change. Additionally, a sensitivity analysis of the SupportVector Machines -based models was performed with regards to attribute selectionand parameter changes. Development and evaluation of the methodology wasperformed using data on three Belgrade municipalities (Zemun, New Belgrade andSurčin), which are represented as 10×10 m grid cells in four different moments intime (2001, 2003, 2007 and 2010).The obtained results indicate that the proposed data-driven methodology providespredictive models which could be successfully used for creation of possiblescenarios of urban land use changes in the future. All three examined machinelearning techniques are suitable for modeling land use change. Accuracy andperformance of models can be improved using proposed balanced data sampling,including the information about neighbourhood and history in datarepresentations and relevant attribute selections. Additionally, using selectedsubset of attributes resulted in a simple model and with less possibility to beoverfitted with higher values of Support Vector Machines parameters.
AB  - Један од главних задатака моделирања метода вођених подацима (Data-driven methods) је проналажење репрезентативног модела испитивног просторно временског процеса, применом података из прошлости и Data Mining и Machine Learning приступа...
PB  - Универзитет у Београду, Грађевински факултет
T2  - Универзитет у Београду
T1  - Predicting land use change with data-driven models
T1  - Predviđanje promena u korišćenju zemljišta primenom modela vođenih podacima (DATA-DRIVEN MODELS)
UR  - https://hdl.handle.net/21.15107/rcub_nardus_6136
ER  - 

@phdthesis{
author = "Samardžić-Petrović, Mileva",
year = "2014",
abstract = "One of the main tasks of data-driven modelling methods is to induce arepresentative model of underlying spatial - temporal processes using past dataand data mining and machine learning approach. As relatively new methods,known to be capable of solving complex nonlinear problems, data-driven methodsare insufficiently researched in the field of land use. The main objective of thisdissertation is to develop a methodology for predictive urban land use changemodels using data-driven approach together with evaluation of the performance ofdifferent data-driven methods, which in the stage of finding patterns of land usechanges use three different machine learning techniques: Decision Trees, NeuralNetworks and Support Vector Machines. The proposed methodology of data-drivenmethods was presented and special attention was paid to different datarepresentation, data sampling and the selection of attributes by four methods (χ2,Info Gain, Gain Ratio and Correlation-based Feature Subset) that best describe theprocess of land use change. Additionally, a sensitivity analysis of the SupportVector Machines -based models was performed with regards to attribute selectionand parameter changes. Development and evaluation of the methodology wasperformed using data on three Belgrade municipalities (Zemun, New Belgrade andSurčin), which are represented as 10×10 m grid cells in four different moments intime (2001, 2003, 2007 and 2010).The obtained results indicate that the proposed data-driven methodology providespredictive models which could be successfully used for creation of possiblescenarios of urban land use changes in the future. All three examined machinelearning techniques are suitable for modeling land use change. Accuracy andperformance of models can be improved using proposed balanced data sampling,including the information about neighbourhood and history in datarepresentations and relevant attribute selections. Additionally, using selectedsubset of attributes resulted in a simple model and with less possibility to beoverfitted with higher values of Support Vector Machines parameters., Један од главних задатака моделирања метода вођених подацима (Data-driven methods) је проналажење репрезентативног модела испитивног просторно временског процеса, применом података из прошлости и Data Mining и Machine Learning приступа...",
publisher = "Универзитет у Београду, Грађевински факултет",
journal = "Универзитет у Београду",
title = "Predicting land use change with data-driven models, Predviđanje promena u korišćenju zemljišta primenom modela vođenih podacima (DATA-DRIVEN MODELS)",
url = "https://hdl.handle.net/21.15107/rcub_nardus_6136"
}

Samardžić-Petrović, M.. (2014). Predicting land use change with data-driven models. in Универзитет у Београду
Универзитет у Београду, Грађевински факултет..
https://hdl.handle.net/21.15107/rcub_nardus_6136

Samardžić-Petrović M. Predicting land use change with data-driven models. in Универзитет у Београду. 2014;.
https://hdl.handle.net/21.15107/rcub_nardus_6136 .

Samardžić-Petrović, Mileva, "Predicting land use change with data-driven models" in Универзитет у Београду (2014),
https://hdl.handle.net/21.15107/rcub_nardus_6136 .

TY  - CONF
AU  - Samardžić-Petrović, Mileva
AU  - Bajat, Branislav
AU  - Kovačević, Miloš
AU  - Dragićević, Suzana
PY  - 2014
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1196
PB  - Department of Geodesy and Geoinformation, Vienna University of Technology, Vienna
C3  - Extended Abstract Proceedings of the GIScience 2014, 23-26 September, Vienna, Austria
T1  - Sensitivity analysis of Support Vector Machine land use change modelling method
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1196
ER  - 

@conference{
author = "Samardžić-Petrović, Mileva and Bajat, Branislav and Kovačević, Miloš and Dragićević, Suzana",
year = "2014",
publisher = "Department of Geodesy and Geoinformation, Vienna University of Technology, Vienna",
journal = "Extended Abstract Proceedings of the GIScience 2014, 23-26 September, Vienna, Austria",
title = "Sensitivity analysis of Support Vector Machine land use change modelling method",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1196"
}

Samardžić-Petrović, M., Bajat, B., Kovačević, M.,& Dragićević, S.. (2014). Sensitivity analysis of Support Vector Machine land use change modelling method. in Extended Abstract Proceedings of the GIScience 2014, 23-26 September, Vienna, Austria
Department of Geodesy and Geoinformation, Vienna University of Technology, Vienna..
https://hdl.handle.net/21.15107/rcub_grafar_1196

Samardžić-Petrović M, Bajat B, Kovačević M, Dragićević S. Sensitivity analysis of Support Vector Machine land use change modelling method. in Extended Abstract Proceedings of the GIScience 2014, 23-26 September, Vienna, Austria. 2014;.
https://hdl.handle.net/21.15107/rcub_grafar_1196 .

Samardžić-Petrović, Mileva, Bajat, Branislav, Kovačević, Miloš, Dragićević, Suzana, "Sensitivity analysis of Support Vector Machine land use change modelling method" in Extended Abstract Proceedings of the GIScience 2014, 23-26 September, Vienna, Austria (2014),
https://hdl.handle.net/21.15107/rcub_grafar_1196 .

TY  - JOUR
AU  - Luković, Jelena
AU  - Bajat, Branislav
AU  - Blagojević, Dragan
AU  - Kilibarda, Milan
PY  - 2014
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/616
AB  - This paper examines a spatial pattern of annual, seasonal and monthly rainfall trends in Serbia. The study used data from 63 weather stations between the period of 1961-2009. The rainfall series was examined by applying the nonparametric method of the Mann-Kendall test and Sen's method to determine the significance and magnitude of the trends. Significant trends have not been detected for the whole country at an annual scale. Seasonal trends at the confidence level of 97.5 %, however, indicate a slight decrease in winter (5 stations out of 63) and spring (7 stations out of 63) precipitation and an increase in autumn precipitation (10 stations out of 63). Results for monthly rainfall trends also generally showed a nonsignificant trend with the exception of a negative trend in May (6 stations out of 63) and positive trend for October (9 stations out of 63). Calculated global autocorrelation statistics (Moran's I) indicate a random spatial pattern of rainfall trends on annual, seasonal and monthly timescales with exceptions for March, June and November. Overall, results suggest that only weak, mostly nonsignificant trends are present in Serbia in the period 1961-2009.
PB  - Springer Verlag
T2  - Regional Environmental Change
T1  - Spatial pattern of recent rainfall trends in Serbia (1961-2009)
EP  - 1799
IS  - 5
SP  - 1789
VL  - 14
DO  - 10.1007/s10113-013-0459-x
ER  - 

@article{
author = "Luković, Jelena and Bajat, Branislav and Blagojević, Dragan and Kilibarda, Milan",
year = "2014",
abstract = "This paper examines a spatial pattern of annual, seasonal and monthly rainfall trends in Serbia. The study used data from 63 weather stations between the period of 1961-2009. The rainfall series was examined by applying the nonparametric method of the Mann-Kendall test and Sen's method to determine the significance and magnitude of the trends. Significant trends have not been detected for the whole country at an annual scale. Seasonal trends at the confidence level of 97.5 %, however, indicate a slight decrease in winter (5 stations out of 63) and spring (7 stations out of 63) precipitation and an increase in autumn precipitation (10 stations out of 63). Results for monthly rainfall trends also generally showed a nonsignificant trend with the exception of a negative trend in May (6 stations out of 63) and positive trend for October (9 stations out of 63). Calculated global autocorrelation statistics (Moran's I) indicate a random spatial pattern of rainfall trends on annual, seasonal and monthly timescales with exceptions for March, June and November. Overall, results suggest that only weak, mostly nonsignificant trends are present in Serbia in the period 1961-2009.",
publisher = "Springer Verlag",
journal = "Regional Environmental Change",
title = "Spatial pattern of recent rainfall trends in Serbia (1961-2009)",
pages = "1799-1789",
number = "5",
volume = "14",
doi = "10.1007/s10113-013-0459-x"
}

Luković, J., Bajat, B., Blagojević, D.,& Kilibarda, M.. (2014). Spatial pattern of recent rainfall trends in Serbia (1961-2009). in Regional Environmental Change
Springer Verlag., 14(5), 1789-1799.
https://doi.org/10.1007/s10113-013-0459-x

Luković J, Bajat B, Blagojević D, Kilibarda M. Spatial pattern of recent rainfall trends in Serbia (1961-2009). in Regional Environmental Change. 2014;14(5):1789-1799.
doi:10.1007/s10113-013-0459-x .

Luković, Jelena, Bajat, Branislav, Blagojević, Dragan, Kilibarda, Milan, "Spatial pattern of recent rainfall trends in Serbia (1961-2009)" in Regional Environmental Change, 14, no. 5 (2014):1789-1799,
https://doi.org/10.1007/s10113-013-0459-x . .

TY  - CONF
AU  - Bajat, Branislav
AU  - Kilibarda, Milan
AU  - Pejović, Milutin
AU  - Samardžić-Petrović, Mileva
PY  - 2014
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/1227
PB  - Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb ; Faculty of Civil Engineering, University of Rijeka, Zagreb ; Rijeka
C3  - Landslide and Flood Hazard Assessment, Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region
T1  - The Preliminary Damage Assessment of Properties Based on Massive Appraisal Maps
UR  - https://hdl.handle.net/21.15107/rcub_grafar_1227
ER  - 

@conference{
author = "Bajat, Branislav and Kilibarda, Milan and Pejović, Milutin and Samardžić-Petrović, Mileva",
year = "2014",
publisher = "Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb ; Faculty of Civil Engineering, University of Rijeka, Zagreb ; Rijeka",
journal = "Landslide and Flood Hazard Assessment, Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region",
title = "The Preliminary Damage Assessment of Properties Based on Massive Appraisal Maps",
url = "https://hdl.handle.net/21.15107/rcub_grafar_1227"
}

Bajat, B., Kilibarda, M., Pejović, M.,& Samardžić-Petrović, M.. (2014). The Preliminary Damage Assessment of Properties Based on Massive Appraisal Maps. in Landslide and Flood Hazard Assessment, Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region
Faculty of Mining, Geology and Petroleum Engineering, University of Zagreb ; Faculty of Civil Engineering, University of Rijeka, Zagreb ; Rijeka..
https://hdl.handle.net/21.15107/rcub_grafar_1227

Bajat B, Kilibarda M, Pejović M, Samardžić-Petrović M. The Preliminary Damage Assessment of Properties Based on Massive Appraisal Maps. in Landslide and Flood Hazard Assessment, Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region. 2014;.
https://hdl.handle.net/21.15107/rcub_grafar_1227 .

Bajat, Branislav, Kilibarda, Milan, Pejović, Milutin, Samardžić-Petrović, Mileva, "The Preliminary Damage Assessment of Properties Based on Massive Appraisal Maps" in Landslide and Flood Hazard Assessment, Proceedings of the 1st Regional Symposium on Landslides in the Adriatic-Balkan Region (2014),
https://hdl.handle.net/21.15107/rcub_grafar_1227 .

TY  - CONF
AU  - Samardžić-Petrović, Mileva
AU  - Bajat, Branislav
AU  - Kovačević, Miloš
PY  - 2013
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/533
AB  - Techniques for evaluating similarities between categorical maps obtained by different spatial modeling techniques or representing similar space in different time instances are still developing. This paper reviews a current approach for assessing the similarity in land use maps that are used in city planning processes. The performance of recently designed kappa location and kappa histo measures as well as fuzzy set map comparison approach were tested on a case study area that comprises three cities of Belgrade's municipalities with different urban characteristics. By assessing similarities between the land use map of the Master plan designed for the year 2021 and the map representing the currently observed land use conditions, the level of realized planned activities as well as the level of discrepancy from the Master plan could be evaluated.
PB  - Technical University of Ostrava, Czech Rebublic
C3  - Gis Ostrava 2013 - Geoinformatics for City Transformation
T1  - Assesing similarities between planned and observed land use maps: the Belgrade's municipalities case study
EP  - 23
SP  - 13
UR  - https://hdl.handle.net/21.15107/rcub_grafar_533
ER  - 

@conference{
author = "Samardžić-Petrović, Mileva and Bajat, Branislav and Kovačević, Miloš",
year = "2013",
abstract = "Techniques for evaluating similarities between categorical maps obtained by different spatial modeling techniques or representing similar space in different time instances are still developing. This paper reviews a current approach for assessing the similarity in land use maps that are used in city planning processes. The performance of recently designed kappa location and kappa histo measures as well as fuzzy set map comparison approach were tested on a case study area that comprises three cities of Belgrade's municipalities with different urban characteristics. By assessing similarities between the land use map of the Master plan designed for the year 2021 and the map representing the currently observed land use conditions, the level of realized planned activities as well as the level of discrepancy from the Master plan could be evaluated.",
publisher = "Technical University of Ostrava, Czech Rebublic",
journal = "Gis Ostrava 2013 - Geoinformatics for City Transformation",
title = "Assesing similarities between planned and observed land use maps: the Belgrade's municipalities case study",
pages = "23-13",
url = "https://hdl.handle.net/21.15107/rcub_grafar_533"
}

Samardžić-Petrović, M., Bajat, B.,& Kovačević, M.. (2013). Assesing similarities between planned and observed land use maps: the Belgrade's municipalities case study. in Gis Ostrava 2013 - Geoinformatics for City Transformation
Technical University of Ostrava, Czech Rebublic., 13-23.
https://hdl.handle.net/21.15107/rcub_grafar_533

Samardžić-Petrović M, Bajat B, Kovačević M. Assesing similarities between planned and observed land use maps: the Belgrade's municipalities case study. in Gis Ostrava 2013 - Geoinformatics for City Transformation. 2013;:13-23.
https://hdl.handle.net/21.15107/rcub_grafar_533 .

Samardžić-Petrović, Mileva, Bajat, Branislav, Kovačević, Miloš, "Assesing similarities between planned and observed land use maps: the Belgrade's municipalities case study" in Gis Ostrava 2013 - Geoinformatics for City Transformation (2013):13-23,
https://hdl.handle.net/21.15107/rcub_grafar_533 .

TY  - JOUR
AU  - Bajat, Branislav
AU  - Pejović, Milutin
AU  - Luković, Jelena
AU  - Manojlović, Predrag
AU  - Ducić, Vladan
AU  - Mustafić, Sanja
PY  - 2013
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/545
AB  - The appearence of geostatistics and geographical information systems has made it possible to analyze complex spatial patterns of meteorological elements over large areas in the applied climatology. The objective of this study is to use geostatistics to characterize the spatial structure and map the spatial variation of average values of precipitation for a 30-year period in Serbia. New, recently introduced, geostatistical algorithms facilitate utilization of auxiliary variables especially remote sensing data or freely available global datasets. The data from Advanced Spaceborn Thermal Emission and Reflection Radiometer global digital elevation model are incorporated as ancillary variables into spatial prediction of average annual precipitation using geostatistical method known as regression kriging. The R (2) value of 0.842 proves high performance result of the prediction of the proposed method.
PB  - Springer-Verlag Wien
T2  - Theoretical and Applied Climatology
T1  - Mapping average annual precipitation in Serbia (1961-1990) by using regression kriging
EP  - 13
IS  - 1-2
SP  - 1
VL  - 112
DO  - 10.1007/s00704-012-0702-2
ER  - 

@article{
author = "Bajat, Branislav and Pejović, Milutin and Luković, Jelena and Manojlović, Predrag and Ducić, Vladan and Mustafić, Sanja",
year = "2013",
abstract = "The appearence of geostatistics and geographical information systems has made it possible to analyze complex spatial patterns of meteorological elements over large areas in the applied climatology. The objective of this study is to use geostatistics to characterize the spatial structure and map the spatial variation of average values of precipitation for a 30-year period in Serbia. New, recently introduced, geostatistical algorithms facilitate utilization of auxiliary variables especially remote sensing data or freely available global datasets. The data from Advanced Spaceborn Thermal Emission and Reflection Radiometer global digital elevation model are incorporated as ancillary variables into spatial prediction of average annual precipitation using geostatistical method known as regression kriging. The R (2) value of 0.842 proves high performance result of the prediction of the proposed method.",
publisher = "Springer-Verlag Wien",
journal = "Theoretical and Applied Climatology",
title = "Mapping average annual precipitation in Serbia (1961-1990) by using regression kriging",
pages = "13-1",
number = "1-2",
volume = "112",
doi = "10.1007/s00704-012-0702-2"
}

Bajat, B., Pejović, M., Luković, J., Manojlović, P., Ducić, V.,& Mustafić, S.. (2013). Mapping average annual precipitation in Serbia (1961-1990) by using regression kriging. in Theoretical and Applied Climatology
Springer-Verlag Wien., 112(1-2), 1-13.
https://doi.org/10.1007/s00704-012-0702-2

Bajat B, Pejović M, Luković J, Manojlović P, Ducić V, Mustafić S. Mapping average annual precipitation in Serbia (1961-1990) by using regression kriging. in Theoretical and Applied Climatology. 2013;112(1-2):1-13.
doi:10.1007/s00704-012-0702-2 .

Bajat, Branislav, Pejović, Milutin, Luković, Jelena, Manojlović, Predrag, Ducić, Vladan, Mustafić, Sanja, "Mapping average annual precipitation in Serbia (1961-1990) by using regression kriging" in Theoretical and Applied Climatology, 112, no. 1-2 (2013):1-13,
https://doi.org/10.1007/s00704-012-0702-2 . .