Land-use suitability analysis of Belgrade city suburbs using machine learning algorithm
Само за регистроване кориснике
2013
Аутори
Đurić, UrošMarjanović, Miloš
Šušić, Vladimir
Petrović, Rastko
Abolmasov, Biljana
Zečević, Snežana
Basarić, Irena
Остала ауторства
Ivan, IgorLongley, Paul
Horák, Jiří
Fritsch, Dieter
Cheshire, James
Inspektor, Tomáš
Конференцијски прилог (Објављена верзија)
,
Institute of geoinformatics VŠB - Technical University of Ostrava
Метаподаци
Приказ свих података о документуАпстракт
This paper treats development issues of the suburban areas of Belgrade city. A considerable growth that the city had experienced has led to excessive consumption of land and also to degradation of the landscape and loss of the natural biodiversity. This is why an augmentation of the current Master Plan within the administrative extents of the city is considered to be vital for consistent planning of suburban areas development. Model used in this paper considered defining land-use suitability, relying on available thematic data, including the following sources: topography, land-cover, geology, protected areas and some synthetic maps derived from these sources in a GIS environment. For this purpose Support Vector Machines (SVM) algorithm has been implemented in a typical supervised classification learning task. Two modelling schemes have been involved (since the main problem of the study was the unavailability of the land-use suitability in the testing area): MODEL1 has been built in the... extents of the training area having only two land-use suitability classes at disposal (Unsuitable and Very Unsuitable) and extrapolated to the testing area within which the same two classes were known (thus available for model performance evaluation), while MODEL2 has been trained on all four land-use suitability classes, and extrapolated to the testing area, with unknown land-use classes. The second model was then correlated with the first one in order to estimate its otherwise disputable performance. Results of MODEL1 were satisfactory, with high overall accuracy (85%). MODEL2 visually shows a good tendency, and since it has at least 85% accuracy for those coincident two classes (Unsuitable and Very Unsuitable) with MODEL1, it is justified to assume that remaining two classes match similar accuracy rates. The model could be improved by more thorough optimization of the classifier parameters, which will require much longer experimenting costs.
Кључне речи:
land-use / suitability / machine learning / GIS / BelgradeИзвор:
Proceeding of 10th International Symposium, Geoinformatics for City transformations, GIS Ostrava 2013, 2013, 49-61Издавач:
- Institute of geoinformatics VŠB - Technical University of Ostrava
Финансирање / пројекти:
- Примена GNSS и LIDAR технологије у мониторингу стабилности инфраструктурних објеката и терена (RS-MESTD-Technological Development (TD or TR)-36009)
Институција/група
GraFarTY - CONF AU - Đurić, Uroš AU - Marjanović, Miloš AU - Šušić, Vladimir AU - Petrović, Rastko AU - Abolmasov, Biljana AU - Zečević, Snežana AU - Basarić, Irena PY - 2013 UR - https://grafar.grf.bg.ac.rs/handle/123456789/1916 AB - This paper treats development issues of the suburban areas of Belgrade city. A considerable growth that the city had experienced has led to excessive consumption of land and also to degradation of the landscape and loss of the natural biodiversity. This is why an augmentation of the current Master Plan within the administrative extents of the city is considered to be vital for consistent planning of suburban areas development. Model used in this paper considered defining land-use suitability, relying on available thematic data, including the following sources: topography, land-cover, geology, protected areas and some synthetic maps derived from these sources in a GIS environment. For this purpose Support Vector Machines (SVM) algorithm has been implemented in a typical supervised classification learning task. Two modelling schemes have been involved (since the main problem of the study was the unavailability of the land-use suitability in the testing area): MODEL1 has been built in the extents of the training area having only two land-use suitability classes at disposal (Unsuitable and Very Unsuitable) and extrapolated to the testing area within which the same two classes were known (thus available for model performance evaluation), while MODEL2 has been trained on all four land-use suitability classes, and extrapolated to the testing area, with unknown land-use classes. The second model was then correlated with the first one in order to estimate its otherwise disputable performance. Results of MODEL1 were satisfactory, with high overall accuracy (85%). MODEL2 visually shows a good tendency, and since it has at least 85% accuracy for those coincident two classes (Unsuitable and Very Unsuitable) with MODEL1, it is justified to assume that remaining two classes match similar accuracy rates. The model could be improved by more thorough optimization of the classifier parameters, which will require much longer experimenting costs. PB - Institute of geoinformatics VŠB - Technical University of Ostrava C3 - Proceeding of 10th International Symposium, Geoinformatics for City transformations, GIS Ostrava 2013 T1 - Land-use suitability analysis of Belgrade city suburbs using machine learning algorithm EP - 61 SP - 49 UR - https://hdl.handle.net/21.15107/rcub_grafar_1916 ER -
@conference{ author = "Đurić, Uroš and Marjanović, Miloš and Šušić, Vladimir and Petrović, Rastko and Abolmasov, Biljana and Zečević, Snežana and Basarić, Irena", year = "2013", abstract = "This paper treats development issues of the suburban areas of Belgrade city. A considerable growth that the city had experienced has led to excessive consumption of land and also to degradation of the landscape and loss of the natural biodiversity. This is why an augmentation of the current Master Plan within the administrative extents of the city is considered to be vital for consistent planning of suburban areas development. Model used in this paper considered defining land-use suitability, relying on available thematic data, including the following sources: topography, land-cover, geology, protected areas and some synthetic maps derived from these sources in a GIS environment. For this purpose Support Vector Machines (SVM) algorithm has been implemented in a typical supervised classification learning task. Two modelling schemes have been involved (since the main problem of the study was the unavailability of the land-use suitability in the testing area): MODEL1 has been built in the extents of the training area having only two land-use suitability classes at disposal (Unsuitable and Very Unsuitable) and extrapolated to the testing area within which the same two classes were known (thus available for model performance evaluation), while MODEL2 has been trained on all four land-use suitability classes, and extrapolated to the testing area, with unknown land-use classes. The second model was then correlated with the first one in order to estimate its otherwise disputable performance. Results of MODEL1 were satisfactory, with high overall accuracy (85%). MODEL2 visually shows a good tendency, and since it has at least 85% accuracy for those coincident two classes (Unsuitable and Very Unsuitable) with MODEL1, it is justified to assume that remaining two classes match similar accuracy rates. The model could be improved by more thorough optimization of the classifier parameters, which will require much longer experimenting costs.", publisher = "Institute of geoinformatics VŠB - Technical University of Ostrava", journal = "Proceeding of 10th International Symposium, Geoinformatics for City transformations, GIS Ostrava 2013", title = "Land-use suitability analysis of Belgrade city suburbs using machine learning algorithm", pages = "61-49", url = "https://hdl.handle.net/21.15107/rcub_grafar_1916" }
Đurić, U., Marjanović, M., Šušić, V., Petrović, R., Abolmasov, B., Zečević, S.,& Basarić, I.. (2013). Land-use suitability analysis of Belgrade city suburbs using machine learning algorithm. in Proceeding of 10th International Symposium, Geoinformatics for City transformations, GIS Ostrava 2013 Institute of geoinformatics VŠB - Technical University of Ostrava., 49-61. https://hdl.handle.net/21.15107/rcub_grafar_1916
Đurić U, Marjanović M, Šušić V, Petrović R, Abolmasov B, Zečević S, Basarić I. Land-use suitability analysis of Belgrade city suburbs using machine learning algorithm. in Proceeding of 10th International Symposium, Geoinformatics for City transformations, GIS Ostrava 2013. 2013;:49-61. https://hdl.handle.net/21.15107/rcub_grafar_1916 .
Đurić, Uroš, Marjanović, Miloš, Šušić, Vladimir, Petrović, Rastko, Abolmasov, Biljana, Zečević, Snežana, Basarić, Irena, "Land-use suitability analysis of Belgrade city suburbs using machine learning algorithm" in Proceeding of 10th International Symposium, Geoinformatics for City transformations, GIS Ostrava 2013 (2013):49-61, https://hdl.handle.net/21.15107/rcub_grafar_1916 .