TY  - CONF
AU  - Bojović, Filip
AU  - Milašinović, Miloš
AU  - Jovanović, Branka
AU  - Krstić, Lazar
AU  - Stojanović, Boban
AU  - Ivanović, Miloš
AU  - Prodanović, Dušan
AU  - Milivojević, Nikola
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2771
AB  - Machine learning methods have been widely and successfully applied in hydrological problems. Most of the methods, such as artificial neural networks, have been focused on estimating hydrological data based on observation over time. Even though these models provide good results, it can be observed that results become unreliable when the training dataset is small or when input data is significantly out of range compared to the training data. Therefore, a new approach is presented, in which artificial neural networks are trained to satisfy physical laws. This is conducted by a novel method called physics-informed neural networks (PINNs), in which physical principles are embedded in a custom loss function. This paper presents the application of physics informed neural networks for solving 1D flood wave propagation in open channels. The research has shown promising results.
C3  - 1st Serbian International Conference on Applied Artificial Intelligence (SICAAI)
T1  - Physics informed neural networks for 1D flood routing
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2771
ER  - 

@conference{
author = "Bojović, Filip and Milašinović, Miloš and Jovanović, Branka and Krstić, Lazar and Stojanović, Boban and Ivanović, Miloš and Prodanović, Dušan and Milivojević, Nikola",
year = "2022",
abstract = "Machine learning methods have been widely and successfully applied in hydrological problems. Most of the methods, such as artificial neural networks, have been focused on estimating hydrological data based on observation over time. Even though these models provide good results, it can be observed that results become unreliable when the training dataset is small or when input data is significantly out of range compared to the training data. Therefore, a new approach is presented, in which artificial neural networks are trained to satisfy physical laws. This is conducted by a novel method called physics-informed neural networks (PINNs), in which physical principles are embedded in a custom loss function. This paper presents the application of physics informed neural networks for solving 1D flood wave propagation in open channels. The research has shown promising results.",
journal = "1st Serbian International Conference on Applied Artificial Intelligence (SICAAI)",
title = "Physics informed neural networks for 1D flood routing",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2771"
}

Bojović, F., Milašinović, M., Jovanović, B., Krstić, L., Stojanović, B., Ivanović, M., Prodanović, D.,& Milivojević, N.. (2022). Physics informed neural networks for 1D flood routing. in 1st Serbian International Conference on Applied Artificial Intelligence (SICAAI).
https://hdl.handle.net/21.15107/rcub_grafar_2771

Bojović F, Milašinović M, Jovanović B, Krstić L, Stojanović B, Ivanović M, Prodanović D, Milivojević N. Physics informed neural networks for 1D flood routing. in 1st Serbian International Conference on Applied Artificial Intelligence (SICAAI). 2022;.
https://hdl.handle.net/21.15107/rcub_grafar_2771 .

Bojović, Filip, Milašinović, Miloš, Jovanović, Branka, Krstić, Lazar, Stojanović, Boban, Ivanović, Miloš, Prodanović, Dušan, Milivojević, Nikola, "Physics informed neural networks for 1D flood routing" in 1st Serbian International Conference on Applied Artificial Intelligence (SICAAI) (2022),
https://hdl.handle.net/21.15107/rcub_grafar_2771 .

TY  - GEN
AU  - Milašinović, Miloš
AU  - Prodanović, Dušan
AU  - Zindović, Budo
AU  - Stojanović, Boban
AU  - Milivojević, Nikola
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2831
PB  - Univerzitet u Beogradu
T1  - CTDA: Control Theory based Data Assimilation – metoda za brzu asimilaciju podataka u modelima otvorenih tokova
UR  - https://hdl.handle.net/21.15107/rcub_grafar_2831
ER  - 

@misc{
author = "Milašinović, Miloš and Prodanović, Dušan and Zindović, Budo and Stojanović, Boban and Milivojević, Nikola",
year = "2022",
publisher = "Univerzitet u Beogradu",
title = "CTDA: Control Theory based Data Assimilation – metoda za brzu asimilaciju podataka u modelima otvorenih tokova",
url = "https://hdl.handle.net/21.15107/rcub_grafar_2831"
}

Milašinović, M., Prodanović, D., Zindović, B., Stojanović, B.,& Milivojević, N.. (2022). CTDA: Control Theory based Data Assimilation – metoda za brzu asimilaciju podataka u modelima otvorenih tokova. 
Univerzitet u Beogradu..
https://hdl.handle.net/21.15107/rcub_grafar_2831

Milašinović M, Prodanović D, Zindović B, Stojanović B, Milivojević N. CTDA: Control Theory based Data Assimilation – metoda za brzu asimilaciju podataka u modelima otvorenih tokova. 2022;.
https://hdl.handle.net/21.15107/rcub_grafar_2831 .

Milašinović, Miloš, Prodanović, Dušan, Zindović, Budo, Stojanović, Boban, Milivojević, Nikola, "CTDA: Control Theory based Data Assimilation – metoda za brzu asimilaciju podataka u modelima otvorenih tokova" (2022),
https://hdl.handle.net/21.15107/rcub_grafar_2831 .

TY  - JOUR
AU  - Milašinović, Miloš
AU  - Prodanović, Dušan
AU  - Stanić, Miloš
AU  - Zindović, Budo
AU  - Stojanović, Boban
AU  - Milivojević, Nikola
PY  - 2022
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2693
AB  - Reliable water resources management requires decision support tools to successfully forecast hydraulic data (stage and flow hydrographs). Even though data-driven methods are nowadays trendy to apply, they still fail to provide reliable forecasts during extreme periods due to a lack of training data. Therefore, model-driven forecasting is still needed. However, the model-driven forecasting approach is affected by numerous uncertainties in initial and boundary conditions. To improve the real-time model's operation, it can be regularly updated using measured data in the data assimilation (DA) procedure. Widely used DA techniques are computationally expensive, which reduce their real-time applications. Previous research shows that tailor-made, time-efficient DA methods based on the control theory could be used instead. This paper presents further insights into the control theory-based DA for 1D hydraulic models. This method uses Proportional–Integrative–Derivative (PID) controllers to assimilate computed water levels and observed data. This paper describes the two-stage PID controllers’ tuning procedure. Multi-objective optimization by Nondominated Sorting Genetic Algorithm II (NSGA-II) was used to determine optimal parameters for PID controllers. The proposed tuning procedure is tested on a hydraulic model used as a decision support tool for the transboundary Iron Gate 1 hydropower system on the Danube River, showing that the average discrepancy between modeled and observed water levels can be less than 0.05 m for more than 97% of assimilation window.
PB  - IWA Publishing
T2  - Journal of Hydroinformatics
T1  - Control theory-based data assimilation for open channel hydraulic models: tuning PID controllers using multi-objective optimization
IS  - 4
VL  - 24
DO  - 10.2166/hydro.2022.034
ER  - 

@article{
author = "Milašinović, Miloš and Prodanović, Dušan and Stanić, Miloš and Zindović, Budo and Stojanović, Boban and Milivojević, Nikola",
year = "2022",
abstract = "Reliable water resources management requires decision support tools to successfully forecast hydraulic data (stage and flow hydrographs). Even though data-driven methods are nowadays trendy to apply, they still fail to provide reliable forecasts during extreme periods due to a lack of training data. Therefore, model-driven forecasting is still needed. However, the model-driven forecasting approach is affected by numerous uncertainties in initial and boundary conditions. To improve the real-time model's operation, it can be regularly updated using measured data in the data assimilation (DA) procedure. Widely used DA techniques are computationally expensive, which reduce their real-time applications. Previous research shows that tailor-made, time-efficient DA methods based on the control theory could be used instead. This paper presents further insights into the control theory-based DA for 1D hydraulic models. This method uses Proportional–Integrative–Derivative (PID) controllers to assimilate computed water levels and observed data. This paper describes the two-stage PID controllers’ tuning procedure. Multi-objective optimization by Nondominated Sorting Genetic Algorithm II (NSGA-II) was used to determine optimal parameters for PID controllers. The proposed tuning procedure is tested on a hydraulic model used as a decision support tool for the transboundary Iron Gate 1 hydropower system on the Danube River, showing that the average discrepancy between modeled and observed water levels can be less than 0.05 m for more than 97% of assimilation window.",
publisher = "IWA Publishing",
journal = "Journal of Hydroinformatics",
title = "Control theory-based data assimilation for open channel hydraulic models: tuning PID controllers using multi-objective optimization",
number = "4",
volume = "24",
doi = "10.2166/hydro.2022.034"
}

Milašinović, M., Prodanović, D., Stanić, M., Zindović, B., Stojanović, B.,& Milivojević, N.. (2022). Control theory-based data assimilation for open channel hydraulic models: tuning PID controllers using multi-objective optimization. in Journal of Hydroinformatics
IWA Publishing., 24(4).
https://doi.org/10.2166/hydro.2022.034

Milašinović M, Prodanović D, Stanić M, Zindović B, Stojanović B, Milivojević N. Control theory-based data assimilation for open channel hydraulic models: tuning PID controllers using multi-objective optimization. in Journal of Hydroinformatics. 2022;24(4).
doi:10.2166/hydro.2022.034 .

Milašinović, Miloš, Prodanović, Dušan, Stanić, Miloš, Zindović, Budo, Stojanović, Boban, Milivojević, Nikola, "Control theory-based data assimilation for open channel hydraulic models: tuning PID controllers using multi-objective optimization" in Journal of Hydroinformatics, 24, no. 4 (2022),
https://doi.org/10.2166/hydro.2022.034 . .

TY  - JOUR
AU  - Milašinović, Miloš
AU  - Prodanović, Dušan
AU  - Zindović, Budo
AU  - Stojanović, Boban
AU  - Milivojević, Nikola
PY  - 2021
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/2363
AB  - Increasing renewable energy usage puts extra pressure on decision-making in river hydropower systems. Decision support tools are used for near-future forecasting of the water available. Model-driven forecasting used for river state estimation often provides bad results due to numerous uncertainties. False inflows and poor initialization are some of the uncertainty sources. To overcome this, standard data assimilation (DA) techniques (e.g., ensemble Kalman filter) are used, which are not always applicable in real systems. This paper presents further insight into the novel, tailor-made model update algorithm based on control theory. According to water-level measurements over the system, the model is controlled and continuously updated using proportional–integrative–derivative (PID) controller(s). Implementation of the PID controllers requires the controllers’ parameters estimation (tuning). This research deals with this task by presenting sequential, multi-metric procedure, applicable for controllers’ initial tuning. The proposed tuning method is tested on the Iron Gate hydropower system in Serbia, showing satisfying results.
PB  - IWA Publishing
T2  - Journal of Hydroinformatics
T1  - Control theory-based data assimilation for hydraulic models as a decision support tool for hydropower systems: sequential, multi-metric tuning of the controllers
IS  - 3
VL  - 23
DO  - 10.2166/hydro.2021.078
ER  - 

@article{
author = "Milašinović, Miloš and Prodanović, Dušan and Zindović, Budo and Stojanović, Boban and Milivojević, Nikola",
year = "2021",
abstract = "Increasing renewable energy usage puts extra pressure on decision-making in river hydropower systems. Decision support tools are used for near-future forecasting of the water available. Model-driven forecasting used for river state estimation often provides bad results due to numerous uncertainties. False inflows and poor initialization are some of the uncertainty sources. To overcome this, standard data assimilation (DA) techniques (e.g., ensemble Kalman filter) are used, which are not always applicable in real systems. This paper presents further insight into the novel, tailor-made model update algorithm based on control theory. According to water-level measurements over the system, the model is controlled and continuously updated using proportional–integrative–derivative (PID) controller(s). Implementation of the PID controllers requires the controllers’ parameters estimation (tuning). This research deals with this task by presenting sequential, multi-metric procedure, applicable for controllers’ initial tuning. The proposed tuning method is tested on the Iron Gate hydropower system in Serbia, showing satisfying results.",
publisher = "IWA Publishing",
journal = "Journal of Hydroinformatics",
title = "Control theory-based data assimilation for hydraulic models as a decision support tool for hydropower systems: sequential, multi-metric tuning of the controllers",
number = "3",
volume = "23",
doi = "10.2166/hydro.2021.078"
}

Milašinović, M., Prodanović, D., Zindović, B., Stojanović, B.,& Milivojević, N.. (2021). Control theory-based data assimilation for hydraulic models as a decision support tool for hydropower systems: sequential, multi-metric tuning of the controllers. in Journal of Hydroinformatics
IWA Publishing., 23(3).
https://doi.org/10.2166/hydro.2021.078

Milašinović M, Prodanović D, Zindović B, Stojanović B, Milivojević N. Control theory-based data assimilation for hydraulic models as a decision support tool for hydropower systems: sequential, multi-metric tuning of the controllers. in Journal of Hydroinformatics. 2021;23(3).
doi:10.2166/hydro.2021.078 .

Milašinović, Miloš, Prodanović, Dušan, Zindović, Budo, Stojanović, Boban, Milivojević, Nikola, "Control theory-based data assimilation for hydraulic models as a decision support tool for hydropower systems: sequential, multi-metric tuning of the controllers" in Journal of Hydroinformatics, 23, no. 3 (2021),
https://doi.org/10.2166/hydro.2021.078 . .

TY  - JOUR
AU  - Rosić, Nikola
AU  - Prodanović, Dušan
AU  - Stojanović, Boban
AU  - Obradović, Dragana
PY  - 2017
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/820
AB  - In this paper, a novel data assimilation method for operational reservoir management on the Danube river section between Novi Sad and Iron Gate I is presented. The proposed data assimilation method allows discharges of river flow simulation model to be updated in near real time according to results of continuous water surface levels measurements. The model discharges are adjusted according to difference between measured and calculated water surface elevations using so-called PI controllers at locations where water levels measurements take place. The effect of different number of PI controllers on method effectiveness and stability are studied for different scenarios. The recommendations for method improvement are given at the end of the paper.
AB  - U radu se predstavlja jedna od mogućih metoda asimilacije, korišćenja kontinualnih merenja nivoa vode duž Dunava za ažuriranje numeričkog modela tečenja Dunavom od Novog Sada do HE "Đerdap 1", napravljenog za potrebe HIS "Đerdap". Opisana metoda omogućava kontinualno, u realnom vremenu, usaglašavanje stanja računskog modela i stvarnog sistema, putem postepene korekcije nivoa promenom nepouzdanih dotoka u modelu. Korekcije se izračunavaju korišćenjem PI (eng. Proportional Integral) kontrolera koji su postavljeni na mestima gde postoje pouzdana merenja nivoa. U radu se prikazuju dobijeni rezultati testiranja primenjene metode za asimilaciju podataka pri različitim scenarijima promene protoka (odnosno, nepoznatog dotoka) na delu Dunava od Novog Sada do hidroelektrane "Đerdap". Testiranja su sprovedena sa različitim brojem kontrolera, kako bi se jasno video njihov efekat, stabilnost i efikasnost asimilacije. Na kraju rada se daju preporuke za dalja poboljšanja metodologije.
PB  - Jugoslovensko društvo za odvodnjavanje i navodnjavanje, Beograd
T2  - Vodoprivreda
T1  - Near real time data assimilation of numerical simulation model for Danube river from Novi Sad to Iron Gate I: Test results
T1  - Asimilacija računskog modela Dunava od Novog Sada do HE "Đerdap 1" u približno realnom vremenu - rezultati testiranja
EP  - 261
IS  - 4-6
SP  - 253
VL  - 49
UR  - https://hdl.handle.net/21.15107/rcub_grafar_820
ER  - 

@article{
author = "Rosić, Nikola and Prodanović, Dušan and Stojanović, Boban and Obradović, Dragana",
year = "2017",
abstract = "In this paper, a novel data assimilation method for operational reservoir management on the Danube river section between Novi Sad and Iron Gate I is presented. The proposed data assimilation method allows discharges of river flow simulation model to be updated in near real time according to results of continuous water surface levels measurements. The model discharges are adjusted according to difference between measured and calculated water surface elevations using so-called PI controllers at locations where water levels measurements take place. The effect of different number of PI controllers on method effectiveness and stability are studied for different scenarios. The recommendations for method improvement are given at the end of the paper., U radu se predstavlja jedna od mogućih metoda asimilacije, korišćenja kontinualnih merenja nivoa vode duž Dunava za ažuriranje numeričkog modela tečenja Dunavom od Novog Sada do HE "Đerdap 1", napravljenog za potrebe HIS "Đerdap". Opisana metoda omogućava kontinualno, u realnom vremenu, usaglašavanje stanja računskog modela i stvarnog sistema, putem postepene korekcije nivoa promenom nepouzdanih dotoka u modelu. Korekcije se izračunavaju korišćenjem PI (eng. Proportional Integral) kontrolera koji su postavljeni na mestima gde postoje pouzdana merenja nivoa. U radu se prikazuju dobijeni rezultati testiranja primenjene metode za asimilaciju podataka pri različitim scenarijima promene protoka (odnosno, nepoznatog dotoka) na delu Dunava od Novog Sada do hidroelektrane "Đerdap". Testiranja su sprovedena sa različitim brojem kontrolera, kako bi se jasno video njihov efekat, stabilnost i efikasnost asimilacije. Na kraju rada se daju preporuke za dalja poboljšanja metodologije.",
publisher = "Jugoslovensko društvo za odvodnjavanje i navodnjavanje, Beograd",
journal = "Vodoprivreda",
title = "Near real time data assimilation of numerical simulation model for Danube river from Novi Sad to Iron Gate I: Test results, Asimilacija računskog modela Dunava od Novog Sada do HE "Đerdap 1" u približno realnom vremenu - rezultati testiranja",
pages = "261-253",
number = "4-6",
volume = "49",
url = "https://hdl.handle.net/21.15107/rcub_grafar_820"
}

Rosić, N., Prodanović, D., Stojanović, B.,& Obradović, D.. (2017). Near real time data assimilation of numerical simulation model for Danube river from Novi Sad to Iron Gate I: Test results. in Vodoprivreda
Jugoslovensko društvo za odvodnjavanje i navodnjavanje, Beograd., 49(4-6), 253-261.
https://hdl.handle.net/21.15107/rcub_grafar_820

Rosić N, Prodanović D, Stojanović B, Obradović D. Near real time data assimilation of numerical simulation model for Danube river from Novi Sad to Iron Gate I: Test results. in Vodoprivreda. 2017;49(4-6):253-261.
https://hdl.handle.net/21.15107/rcub_grafar_820 .

Rosić, Nikola, Prodanović, Dušan, Stojanović, Boban, Obradović, Dragana, "Near real time data assimilation of numerical simulation model for Danube river from Novi Sad to Iron Gate I: Test results" in Vodoprivreda, 49, no. 4-6 (2017):253-261,
https://hdl.handle.net/21.15107/rcub_grafar_820 .

TY  - JOUR
AU  - Prodanović, Dušan
AU  - Stanić, Miloš
AU  - Milivojević, Nikola
AU  - Simić, Zoran
AU  - Stojanović, Boban
PY  - 2009
UR  - https://grafar.grf.bg.ac.rs/handle/123456789/257
AB  - The particularity of 'Vlasina' hydropower plants catchment is a big number of gravitation channels used to collect the water from neighboring natural catchments. The overall catchment size is thus increased, compared to the natural catchment. At the bifurcations where the gravitation channels with mild slope are intersecting the steep natural hydrographic network, the natural surface and subsurface water flows are significantly altered. The channel which intersects the river flow will hold the water at higher elevations, filling the storages or transferring the water to another catchment. Under such conditions, the concept of rainfall to runoff transformation in SWAT-based model had to be modified in a way that the channel does not capture all the water from the natural watercourse, but will allow a certain volume of water to run downstream, both for the surface and subsurface flow. New SWAT-related objects were introduced: HPN (hydro-profile on the natural watercourse), HPC (hydro-profile on the channel), HPI (hydro-profile on the channel, the intake) and HPS (storage hydro-profile). For each object the water balance and transformation equations were derived, adapting SWAT model to simulate the flow in the bifurcating network of natural streams and channels. The new model was calibrated on the catchment area of the 'Vlasina' hydropower plants system. This paper presents the adaptations of the SWAT-based model and results of its application on the northern part of the system (catchments of the channels 'Strvna' and 'Čemernik').
PB  - Univerzitet u Kragujevcu - Fakultet inženjerskih nauka, Kragujevac
T2  - Journal of Serbian Society for Computational Mechanics
T1  - Modified rainfall-runoff model for bifurcations caused by channels embedded in catchments
EP  - 126
IS  - 1
SP  - 111
VL  - 3
UR  - https://hdl.handle.net/21.15107/rcub_grafar_257
ER  - 

@article{
author = "Prodanović, Dušan and Stanić, Miloš and Milivojević, Nikola and Simić, Zoran and Stojanović, Boban",
year = "2009",
abstract = "The particularity of 'Vlasina' hydropower plants catchment is a big number of gravitation channels used to collect the water from neighboring natural catchments. The overall catchment size is thus increased, compared to the natural catchment. At the bifurcations where the gravitation channels with mild slope are intersecting the steep natural hydrographic network, the natural surface and subsurface water flows are significantly altered. The channel which intersects the river flow will hold the water at higher elevations, filling the storages or transferring the water to another catchment. Under such conditions, the concept of rainfall to runoff transformation in SWAT-based model had to be modified in a way that the channel does not capture all the water from the natural watercourse, but will allow a certain volume of water to run downstream, both for the surface and subsurface flow. New SWAT-related objects were introduced: HPN (hydro-profile on the natural watercourse), HPC (hydro-profile on the channel), HPI (hydro-profile on the channel, the intake) and HPS (storage hydro-profile). For each object the water balance and transformation equations were derived, adapting SWAT model to simulate the flow in the bifurcating network of natural streams and channels. The new model was calibrated on the catchment area of the 'Vlasina' hydropower plants system. This paper presents the adaptations of the SWAT-based model and results of its application on the northern part of the system (catchments of the channels 'Strvna' and 'Čemernik').",
publisher = "Univerzitet u Kragujevcu - Fakultet inženjerskih nauka, Kragujevac",
journal = "Journal of Serbian Society for Computational Mechanics",
title = "Modified rainfall-runoff model for bifurcations caused by channels embedded in catchments",
pages = "126-111",
number = "1",
volume = "3",
url = "https://hdl.handle.net/21.15107/rcub_grafar_257"
}

Prodanović, D., Stanić, M., Milivojević, N., Simić, Z.,& Stojanović, B.. (2009). Modified rainfall-runoff model for bifurcations caused by channels embedded in catchments. in Journal of Serbian Society for Computational Mechanics
Univerzitet u Kragujevcu - Fakultet inženjerskih nauka, Kragujevac., 3(1), 111-126.
https://hdl.handle.net/21.15107/rcub_grafar_257

Prodanović D, Stanić M, Milivojević N, Simić Z, Stojanović B. Modified rainfall-runoff model for bifurcations caused by channels embedded in catchments. in Journal of Serbian Society for Computational Mechanics. 2009;3(1):111-126.
https://hdl.handle.net/21.15107/rcub_grafar_257 .

Prodanović, Dušan, Stanić, Miloš, Milivojević, Nikola, Simić, Zoran, Stojanović, Boban, "Modified rainfall-runoff model for bifurcations caused by channels embedded in catchments" in Journal of Serbian Society for Computational Mechanics, 3, no. 1 (2009):111-126,
https://hdl.handle.net/21.15107/rcub_grafar_257 .