Irrigation and Water Engineering

Irrigation and Water Engineering

Comparing the Performance of Machine Learning Models in Flood Risk Zoning in Nekarood Watershed

Document Type : Original Article

Authors
Seidmohamad Mousavi 1
Karim Soleimani 1
Fatemeh Shokrian 1
Omid Ghorbanzadeh 2
1 Department of Watershed Engineering - Faculty of Natural Resources of Sari - Sari University of Agricultural Sciences and Natural Resources - Sari - Iran
2 Institute of Geomatics, University of Natural Resources and Life Sciences, Vienna, Austria
10.22125/iwe.2026.562734.1911
Abstract
Flooding stands as one of the most destructive hydro-climatic hazards, inflicting substantial annual losses on human communities and economic infrastructure. Identifying flood-prone zones and creating sensitivity maps are crucial for effective risk management and natural resource planning. This study focused on assessing the performance of three machine learning algorithms—logistic regression (LR), support vector machine (SVM), and gradient boosting (GB)—for flood risk mapping in the Nekarood watershed of Mazandaran province. Thirteen environmental and hydrological factors, including rainfall, slope, elevation, proximity to waterways, land use, and morphometric indices, were analyzed alongside 152 recorded flood occurrence points. The models were evaluated using metrics such as AUC, overall accuracy, and the kappa coefficient. Results indicated that the GB model achieved the highest performance, with an AUC of 0.896, an overall accuracy of 87%, and a kappa coefficient of 0.84. The SVM model followed with an AUC of 0.872 and an accuracy of 83%, while the LR model, scoring an AUC of 0.853 and an accuracy of 80%, showed the weakest performance among the three. Analysis of variable importance revealed that rainfall, slope, distance from waterways, and elevation are the most significant factors influencing flood occurrence. Consequently, reinforcement learning-based algorithms could serve as effective tools for enhancing predictive accuracy and minimizing uncertainty in flood risk mapping efforts. The findings from this study offer valuable insights for strengthening early warning systems, restricting development in high-risk zones, and reducing both human and economic damages caused by flooding in similar regions.
Keywords
Flood
Machine Learning
Gradient Boosting
Support Vector Machine
Nekarood
Subjects
قره داغی، ب و ا. قاسم زاده. (1403). رویکرد پیش‌بینی جدید با استفاده از ترکیب یادگیری ماشین برای پیش بینی مناطق حساس به وقوع سیل (مطالعه موردی: حوضۀ آبریز کارون).  نشریه سنجش از دور و GIS ایران، دوره 16، شماره 2، ص 1-18
حنیفی نیا، ع و ه. عبقری. (1404). پیش‌‌بینی مناطق مستعد سیل با استفاده از مدل‌‌های یادگیری ماشین خطی تعمیم یافته و بیشینه آنتروپی. مخاطرات محیط طبیعی، دوره 14، شماره 43، ص 34-19.
کرمی، پ.، اسلامی نژاد، س. ا.، افتخاری، م.، اکبری، م و م. راستگو. (1402). پهنه‌بندی حساسیت سیل با استفاده از روش‌های یادگیری ماشین بهبودیافته توسط الگوریتم ژنتیک. نشریه محیط زیست طبیعی، دوره 76، شماره 1، ص 60-43.
سلیمانی، ک و ب. محسنی. (1403). تعیین اولویت پهنه بندی خطر وقوع سیل با استفاده از سیستم اطلاعات جغرافیایی در حوزه آبخیز بابل‌رود (استان مازندران). نشریه سنجش از دور وسیستم اطلاعات جغرافیایی در منایع طبیعی، دوره 2، شماره 15، ص 28-53.
شادمانی، م.، معروفی، ص.، سبزی پرور، ع. ا و ک. محمدی. (1387). مدل ژئومورفولوژیکی سیلاب و پهنه بندی خطر سیل با استفاده از شبکه عصبی مصنوعی و GIS. کنفرانس بین المللی بحران آب. SID. https://sid.ir/paper/814344/fa
Ali, R., Kuriqi, A., Abubaker, S., & Kisi, O. (2019). Long-term trends and seasonality detection of the observed flow in Yangtze River using Mann-Kendall and Sen’s innovative trend method. Water, 11(9), 1855.
Arabameri, A., Pradhan, B., Rezaei, K., et al. (2021). Comparison of multi-criteria decision making and machine learning methods for flood susceptibility mapping. Journal of Hydrology, 597, 126164.
Botzen, W. W., de Boer, J., & Terpstra, T. (2013). Framing of risk and preferences for annual and multi-year flood insurance. Journal of economic psychology, 39, 357-375.
Bui, D. T., Hoang, N. D., Martínez-Álvarez, F., Ngo, P. T. T., Hoa, P. V., Pham, T. D., ... & Costache, R. (2020). A novel deep learning neural network approach for predicting flash flood susceptibility: A case study at a high frequency tropical storm area. Science of The Total Environment, 701, 134413.
Bui, D. T., Pradhan, B., & Lofman, O. Revhaug. I., 2012. Landslide susceptibility assessment in vietnam using support vector machines, decision tree, and Naive Bayes Models. Mathematical Problems in Engineering, 2012.
Chen, J., Li, Q., Wang, H., & Deng, M. (2020). A machine learning ensemble approach based on random forest and radial basis function neural network for risk evaluation of regional flood disaster: a case study of the Yangtze River Delta, China. International journal of environmental research and public health, 17(1), 49.
Costache, R. (2019). Flash-flood Potential Index mapping using weights of evidence, decision Trees models and their novel hybrid integration. Stochastic Environmental Research and Risk Assessment, 33(7), 1375-1402.
Costache, R., Hong, H., & Pham, Q. B. (2020). Comparative assessment of the flash-flood potential within small mountain catchments using bivariate statistics and their novel hybrid integration with machine learning models. Science of the Total Environment, 711, 134514.
Friedman, J. H. (2001). Greedy function approximation: a gradient boosting machine. Annals of statistics, 1189-1232.
Hoa, P. V., Binh, N. A., Hong, P. V., An, N. N., Thao, G. T. P., Hanh, N. C., ... & Bui, D. T. (2024). One-dimensional deep learning driven geospatial analysis for flash flood susceptibility mapping: a case study in North Central Vietnam. Earth Science Informatics, 17(5), 4419-4440.
Islam, A. R. M. T., Talukdar, S., Mahato, S., Kundu, S., Eibek, K. U., Pham, Q. B., ... & Linh, N. T. T. (2021). Flood susceptibility modelling using advanced ensemble machine learning models. Geoscience Frontiers, 12(3), 101075.
Kaur, H., Gupta, S., Parkash, S., Thapa, R., & Mandal, R. (2017). Geospatial modelling of flood susceptibility pattern in a subtropical area of West Bengal, India. Environmental Earth Sciences, 76(9), 339.
Kia, M. B., Pirasteh, S., Pradhan, B., Mahmud, A. R., Sulaiman, W. N. A., & Moradi, A. (2012). An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia. Environmental earth sciences, 67(1), 251-264.
Kubra, A., Lokesh, K. J., Shakthi, G., Surya, M., Mohammad Jawad, A., & Melquier, A. (2024, October). Enhanced Flood Prediction and Management for Urban Underpass Using Machine Learning. In International Conference on Computer & Communication Technologies (pp. 385-395). Singapore: Springer Nature Singapore.
Meliho, M., Khattabi, A., & Asinyo, J. (2021). Spatial modeling of flood susceptibility using machine learning algorithms. Arabian Journal of Geosciences, 14(21), 2243.
Parizi, E., Khojeh, S., Hosseini, S. M., & Moghadam, Y. J. (2022). Application of Unmanned Aerial Vehicle DEM in flood modeling and comparison with global DEMs: Case study of Atrak River Basin, Iran. Journal of environmental management, 317, 115492.
Parsian, S., Amani, M., Moghimi, A., Ghorbanian, A., & Mahdavi, S. (2021). Flood hazard mapping using fuzzy logic, analytical hierarchy process, and multi-source geospatial datasets. Remote Sensing, 13(23), 4761.
Pham, B. T., Prakash, I., Khosravi, K., et al. (2020). A comparison of machine learning methods for flood susceptibility mapping: A case study of India. Science of the Total Environment, 701, 134413.
Pollack, A. B., Sue Wing, I., & Nolte, C. (2022). Aggregation bias and its drivers in large‐scale flood loss estimation: A Massachusetts case study. Journal of Flood Risk Management, 15(4), e12851.
Pourghasemi, H. R., Razavi-Termeh, S. V., Kariminejad, N., Hong, H., & Chen, W. (2020). An assessment of metaheuristic approaches for flood assessment. Journal of Hydrology, 582, 124536.
Rahman, Z. U., Ullah, W., Bai, S., Ullah, S., Jan, M. A., Khan, M., & Tayyab, M. (2023). GIS-based flood susceptibility mapping using bivariate statistical model in Swat River Basin, Eastern Hindukush region, Pakistan. Frontiers in Environmental Science, 11, 1178540.
Rahmati, O., Pourghasemi, H. R., & Melesse, A. M. (2016). Application of GIS-based data-driven random forest and maximum entropy models for flood susceptibility mapping. Geomatics, Natural Hazards and Risk, 7(4), 1309–1331.
Rifath, A. R., Muktadir, M. G., Hasan, M., & Islam, M. A. (2024). Flash flood prediction modeling in the hilly regions of Southeastern Bangladesh: A machine learning attempt on present and future climate scenarios. Environmental Challenges, 17, 101029.
Saleh, A., Yuzir, A., & Sabtu, N. (2022). Flash flood susceptibility mapping of sungai pinang catchment using frequency ratio. Sains Malaysiana, 51(1), 51-65.
Samanta, S., Pal, D. K., & Palsamanta, B. (2018). Flood susceptibility analysis through remote sensing, GIS and frequency ratio model. Applied Water Science, 8(2), 66.
Serraj, R., & Pingali, P. (Eds.). (2018). Agriculture & food systems to 2050: global trends, challenges and opportunities.
Seydi, S. T., Kanani-Sadat, Y., Hasanlou, M., Sahraei, R., Chanussot, J., & Amani, M. (2022). Comparison of machine learning algorithms for flood susceptibility mapping. Remote Sensing, 15(1), 192.
Tehrany, M. S., Pradhan, B., & Jebur, M. N. (2015). Flood susceptibility mapping using a novel ensemble approach of evidential belief function and support vector machine. Journal of Hydrology, 512, 332–343.
ehrany, M. S., Pradhan, B., Mansor, S., & Ahmad, N. (2015). Flood susceptibility assessment using GIS-based support vector machine model with different kernel types. Catena, 125, 91-101.
Vapnik, V. (2013). The nature of statistical learning theory. Springer science & business media.
Waleed, M., & Sajjad, M. (2025). Advancing flood susceptibility prediction: A comparative assessment and scalability analysis of machine learning algorithms via artificial intelligence in high‐risk regions of Pakistan. Journal of Flood Risk Management, 18(1), e13047.
Zeng, Z., Tang, G., Hong, Y., Zeng, C., & Yang, Y. (2017). Development of an NRCS curve number global dataset using the latest geospatial remote sensing data for worldwide hydrologic applications. Remote Sensing Letters, 8(6), 528-536.