Flood Sensitivity Assessment Analysis Using Random Forest and Artificial Neural Network: A Case Study of Ilam Province

Gholami, Farzaneh; Entezari, Mojgan; Zakeri Nejad, Reza; Karimi, Haji

doi:10.22111/jneh.2025.51893.2111

Flood Sensitivity Assessment Analysis Using Random Forest and Artificial Neural Network: A Case Study of Ilam Province

Articles in Press

Document Type : Research Article

Authors

¹ PhD Student, Department of Physical Geography, Faculty of Geographical Sciences and Planning, University of Isfahan, Iran.

² Professor, Department of Physical Geography, Faculty of Geographical Sciences and Planning, University of Isfahan, Iran

³ Assistant Professor of GIS and RS, Department of Physical Geography ،Faculty of Geographical Sciences and Planning, University of Isfahan, Iran

⁴ Professor of Hydrogeology, Faculty of Agriculture, Ilam University, Ilam, Iran

10.22111/jneh.2025.51893.2111

Abstract

Flood is one of the most catastrophic natural hazards worldwide that can easily have devastating effects on human lives and property. The frequent occurrence of this hazard makes it necessary to develop accurate flood hazard maps for better information dissemination and disaster preparedness and mitigation. The proposed research work is to analyze the flood susceptibility assessment in a mountainous environment. Therefore, this study aims to apply machine learning models (MLM) and geographic information systems (GIS) techniques to predict flood hazard areas in Ilam province. Two ML algorithms were used for flood susceptibility mapping of Ilam province: random forests (RF) and artificial neural networks (ANN). Sixteen continuous parameters and different categorical variables were identified to assess the correlation between these variables and flood events in the study area and were used as inputs to run the two models. A total of 1042 flood and non-flood points were randomly selected, 70% and 30% of which were used as training and validation datasets. Also, the results of the error rate of the proposed algorithms were considered, clearly showing that in the RF model, MAE, which is equal to 0.0889, and RMSE equal to 0.1872, have the lowest value, R2, which is equal to 0.8423, has the highest value, which performed better compared to the ANN model. The value of the research lies in the fact that the proposed models can also be used to assess natural disasters such as earthquakes, landslides, etc. In addition, this work makes a significant contribution to the efforts to reduce the risk of natural disasters. Therefore, it will help to increase environmental sustainability.

Keywords

Main Subjects

Environmental Hazards

References

References (in Persian)

Salamat Hormozi, Vahid, Omidvar, Kamal, Kavsi, Reza, Hamzenejad. Mojtaba, (2017). Identification and synoptic-dynamic analysis of atmospheric patterns of the November 2015 flood in Ilam and Lorestan provinces. Newar. , 27-9, (97-96)41, 27-9. [In Persian]

References (in English)

Adeyemi, A. B., & Komolafe, A. A. (2025). Flood hazard zones prediction using machine-learning-based geospatial approach in the lower Niger River basin, Nigeria. Natural Hazards Research, 5(2), 399–412. https://doi.org/10.1016/j.nhres.2025.01.002

Arora, A., Arabameri, A., Pandey, M., Siddiqui, M. A., Shukla, U. K., Bui, D. T., ... & Bhardwaj, A. (2021). Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for flood susceptibility prediction mapping in the Middle Ganga Plain, India. Science of the Total Environment, 750, 141565.‏ https://doi.org/10.1016/j.scitotenv.2020.141565

Benkirane, M., Laftouhi, N. E., El Mansouri, B., Salik, I., Snineh, M., El Ghazali, F. E., ... & Zamrane, Z. (2020). An approach for flood assessment by numerical modeling of extreme hydrological events in the Zat watershed (High Atlas, Morocco). Urban Water Journal, 17(5), 381-389.‏

Desai, B., Maskrey, A., Peduzzi, P., De Bono, A., & Herold, C. (2015). Making development sustainable: the future of disaster risk management, global assessment report on disaster risk reduction.

Liu, J., Wang, J., Xiong, J., Cheng, W., Sun, H., Yong, Z., & Wang, N. (2021). Hybrid models incorporating bivariate statistics and machine learning methods for flash flood susceptibility assessment based on remote sensing datasets. Remote Sensing, 13(23), 4945.

Merz, B., Kreibich, H., Schwarze, R., & Thieken, A. (2010). Review article" Assessment of economic flood damage". Natural Hazards and Earth System Sciences, 10(8), 1697-1724.‏

Mishra, A., Mukherjee, S., Merz, B., Singh, V. P., Wright, D. B., Villarini, G., ... & Stedinger, J. R. (2022). An overview of flood concepts, challenges, and future directions. Journal of Hydrologic Engineering, 27(6), 03122001.

Sarkar, D., & Mondal, P. (2020). Flood vulnerability mapping using frequency ratio (FR) model: a case study on Kulik river basin, Indo-Bangladesh Barind region. Applied Water Science, 10(1), 1-13.‏

Wang, Y., Fang, Z., Hong, H., & Peng, L. (2020). Flood susceptibility mapping using convolutional neural network frameworks. Journal of Hydrology, 582, 124482.

Zanchetta, A. D., & Coulibaly, P. (2020). Recent advances in real-time pluvial flash flood forecasting. Water, 12(2), 570.‏

Zhang, M., Fu, X., Liu, S., & Zhang, C. (2025). Integrating Remote Sensing and Machine Learning for Actionable Flood Risk Assessment: Multi-Scenario Projection in the Ili River Basin in China Under Climate Change. Remote Sensing, 17(7), 1189.