TY  - JOUR
AU  - Bezdan, Atila
AU  - Bezdan, Jovana
AU  - Marković, Monika
AU  - Mirčetić, Dejan
AU  - Baumgertel, Aleksandar
AU  - Salvai, Andrea
AU  - Blagojević, Boško
PY  - 2025
UR  - https://omorika.sfb.bg.ac.rs/handle/123456789/1538
AB  - Waterlogging disasters are one of the most severe and widespread agricultural meteorological disasters. They affect about 15% of land surface globally, causing a significant reduction in crop growth and yields. This paper presents an objective methodology for assessing waterlogging risk, primarily in non-urban, predominantly agricultural areas. The waterlogging risk was assessed by evaluating vulnerability and hazard based on key environmental, anthropogenic, and climatic factors. The weights of factors affecting the waterlogging vulnerability were determined using the entropy weight method (EWM), assuring the objectivity of the overall evaluation results. The obtained waterlogging risk map was validated by comparing it with observed and detected waterlogged sites using Sentinel-2 imagery and Random Forest classification. The key novelties of this study are the use of the entropy weight method to objectively determine the relative importance of factors influencing waterlogging vulnerability, and a two-step validation process which includes field-based comparison and remote sensing validation. The presented methodology was demonstrated in the Vojvodina region, Serbia. The following waterlogging vulnerability factors were used: soil properties, geomorphology, surface depressions, average phreatic water table depth, and land cover. The EWM shows that surface depressions and soil properties have the most significant influence on waterlogging vulnerability. The highest waterlogging hazard classes occur in about 31% of the analyzed territory. The waterlogging hazard was estimated based on water balance for the non-vegetation season and maximum daily precipitation in spring, both modeled using the Generalize Extreme Value distribution function. The highest waterlogging hazard classes occur in about 31% of the analyzed territory. The final risk map shows that the high waterlogging risk occurs in about 11% of the territory. Those are mainly areas in the central, eastern, and southeastern parts of the Vojvodina region, usually along the main watercourses. High agreement between the detected waterlogged areas and the produced waterlogging risk map was achieved, validating the proposed methodology. The presented waterlogging risk assessment methodology is valuable for planning and policy-making for various water management and environmental activities. Although it is demonstrated in Vojvodina, by selecting the appropriate factors of vulnerability and hazard, it can be applied to any other region.
T2  - CATENA
T1  - An objective methodology for waterlogging risk assessment based on the entropy weighting method and machine learning
SP  - 108618
VL  - 249
DO  - 10.1016/j.catena.2024.108618
ER  - 

@article{
author = "Bezdan, Atila and Bezdan, Jovana and Marković, Monika and Mirčetić, Dejan and Baumgertel, Aleksandar and Salvai, Andrea and Blagojević, Boško",
year = "2025",
abstract = "Waterlogging disasters are one of the most severe and widespread agricultural meteorological disasters. They affect about 15% of land surface globally, causing a significant reduction in crop growth and yields. This paper presents an objective methodology for assessing waterlogging risk, primarily in non-urban, predominantly agricultural areas. The waterlogging risk was assessed by evaluating vulnerability and hazard based on key environmental, anthropogenic, and climatic factors. The weights of factors affecting the waterlogging vulnerability were determined using the entropy weight method (EWM), assuring the objectivity of the overall evaluation results. The obtained waterlogging risk map was validated by comparing it with observed and detected waterlogged sites using Sentinel-2 imagery and Random Forest classification. The key novelties of this study are the use of the entropy weight method to objectively determine the relative importance of factors influencing waterlogging vulnerability, and a two-step validation process which includes field-based comparison and remote sensing validation. The presented methodology was demonstrated in the Vojvodina region, Serbia. The following waterlogging vulnerability factors were used: soil properties, geomorphology, surface depressions, average phreatic water table depth, and land cover. The EWM shows that surface depressions and soil properties have the most significant influence on waterlogging vulnerability. The highest waterlogging hazard classes occur in about 31% of the analyzed territory. The waterlogging hazard was estimated based on water balance for the non-vegetation season and maximum daily precipitation in spring, both modeled using the Generalize Extreme Value distribution function. The highest waterlogging hazard classes occur in about 31% of the analyzed territory. The final risk map shows that the high waterlogging risk occurs in about 11% of the territory. Those are mainly areas in the central, eastern, and southeastern parts of the Vojvodina region, usually along the main watercourses. High agreement between the detected waterlogged areas and the produced waterlogging risk map was achieved, validating the proposed methodology. The presented waterlogging risk assessment methodology is valuable for planning and policy-making for various water management and environmental activities. Although it is demonstrated in Vojvodina, by selecting the appropriate factors of vulnerability and hazard, it can be applied to any other region.",
journal = "CATENA",
title = "An objective methodology for waterlogging risk assessment based on the entropy weighting method and machine learning",
pages = "108618",
volume = "249",
doi = "10.1016/j.catena.2024.108618"
}

Bezdan, A., Bezdan, J., Marković, M., Mirčetić, D., Baumgertel, A., Salvai, A.,& Blagojević, B.. (2025). An objective methodology for waterlogging risk assessment based on the entropy weighting method and machine learning. in CATENA, 249, 108618.
https://doi.org/10.1016/j.catena.2024.108618

Bezdan A, Bezdan J, Marković M, Mirčetić D, Baumgertel A, Salvai A, Blagojević B. An objective methodology for waterlogging risk assessment based on the entropy weighting method and machine learning. in CATENA. 2025;249:108618.
doi:10.1016/j.catena.2024.108618 .

Bezdan, Atila, Bezdan, Jovana, Marković, Monika, Mirčetić, Dejan, Baumgertel, Aleksandar, Salvai, Andrea, Blagojević, Boško, "An objective methodology for waterlogging risk assessment based on the entropy weighting method and machine learning" in CATENA, 249 (2025):108618,
https://doi.org/10.1016/j.catena.2024.108618 . .