Enhancing Flood Susceptibility Mapping using Statistical and Machine Learning Approaches: A Case Study of the Wang River Basin, Thailand
Article Sidebar
Main Article Content
Abstract
In flood vulnerable regions like the Wang River Basin, Thailand, flood susceptibility mapping (FSM) plays a key role in flood disaster risk management. This research investigates the performance of Shannon’s Entropy (SE), a statistical model, and Random Forest (RF), a machine learning (ML) algorithm for the prediction of flood-potential areas. Multicollinearity analysis together with SE-based weighting identified a total of seven significant flood conditioning factors (FCFs) which are curvature, slope, elevation, geology, soil permeability, precipitation, and stream power index (SPI). The models were trained and validated using 3,000 flood and 3,000 non-flood points with a ratio of 70:30. Results showed that the RF model outperformed SE with AUC-ROC values of 0.929 (training) and 0.931 (verification), compared to SE of which are 0.874 and 0.870, indicating the superiority of ML in handling complex environmental data, which can offer advantages in flood risk prediction. This study also presents the promise of ML in enhancing FSM accuracy and confidence, enabling risk mitigation strategies in the Wang River Basin and similar areas.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
Akay, H. (2024). Flood Susceptibility Mapping Using Information Fusion Paradigm Integrated with Decision Trees. Water Resources Management, 38(13), 5365-5383. https://doi.org/10.1007/s11269-024-03918-5
Al-Kindi, K. M., & Alabri, Z. (2024). Investigating the Role of the Key Conditioning Factors in Flood Susceptibility Mapping Through Machine Learning Approaches. Earth Systems and Environment, 8(1), 63-81. https://doi.org/10.1007/s41748-023-00369-7
Bhattarai, Y., Duwal, S., Sharma, S., & Talchabhadel, R. (2024). Leveraging machine learning and open-source spatial datasets to enhance flood susceptibility mapping in transboundary river basin. International Journal of Digital Earth, 17(1).
https://doi.org/10.1080/17538947.2024.2313857
Bidorn, B., Chanyotha, S., Kish, S. A., Donoghue, J. F., Bidorn, K., & Mama, R. (2015). The effects of Thailand׳s Great Flood of 2011 on river sediment discharge in the upper Chao Phraya River basin, Thailand. International Journal of Sediment Research, 30(4), 328-337. https://doi.org/10.1016/j.ijsrc.2015.10.001
Charoenlerkthawin, W., Namsai, M., Bidorn, K., Rukvichai, C., Panneerselvam, B., & Bidorn, B. (2021). Effects of Dam Construction in the Wang River on Sediment Regimes in the Chao Phraya River Basin. Water, 13(16). https://doi.org/10.3390/w13162146
Dey, H., Shao, W., Moradkhani, H., Keim, B. D., & Peter, B. G. (2024). Urban flood susceptibility mapping using frequency ratio and multiple decision tree-based machine learning models. Natural Hazards, 120(11), 10365-10393. https://doi.org/10.1007/s11069-024-06609-x
Gohil, M., Mehta, D., & Shaikh, M. (2024). An integration of geospatial and fuzzy-logic techniques for flood-hazard mapping. Journal of Earth System Science, 133(2). https://doi.org/10.1007/s12040-024-02288-1
Haghizadeh, A., Siahkamari, S., Haghiabi, A. H., & Rahmati, O. (2017). Forecasting flood-prone areas using Shannon’s entropy model. Journal of Earth System Science, 126(3). https://doi.org/10.1007/s12040-017-0819-x
Kaya, C. M., & Derin, L. (2023). Parameters and methods used in flood susceptibility mapping: a review. Journal of Water and Climate Change, 14(6), 1935-1960. https://doi.org/10.2166/wcc.2023.035
Long, G., Tantanee, S., Nusit, K., & Sooraksa, P. (2025). Flood susceptibility mapping in the Yom River Basin, Thailand: stacking ensemble learning using multi-year flood inventory data. Geocarto International, 40(1). https://doi.org/10.1080/10106049.2025.2461531
Pham, B. T., Jaafari, A., Phong, T. V., Yen, H. P. H., Tuyen, T. T., Luong, V. V., Nguyen, H. D., Le, H. V., & Foong, L. K. (2021). Improved flood susceptibility mapping using a best first decision tree integrated with ensemble learning techniques. Geoscience Frontiers, 12(3). https://doi.org/10.1016/j.gsf.2020.11.003
Rahaman, A., Venkatesan, M. S., & Ayyamperumal, R. (2021). GIS-based landslide susceptibility mapping method and Shannon entropy model: a case study on Sakaleshapur Taluk, Western Ghats, Karnataka, India. Arabian Journal of Geosciences, 14(20). https://doi.org/10.1007/s12517-021-08422-3
Rahmati, O., Darabi, H., Panahi, M., Kalantari, Z., Naghibi, S. A., Ferreira, C. S. S., Kornejady, A., Karimidastenaei, Z., Mohammadi, F., Stefanidis, S., Tien Bui, D., & Haghighi, A. T. (2020). Development of novel hybridized models for urban flood susceptibility mapping. Sci Rep, 10(1), 12937. https://doi.org/10.1038/s41598-020-69703-7
Raveephinit, D., Rittima, A., Phankamolsil, Y., Tabucanon, A. S., Sawangphol, W., Kraisangka, J., Talaluxmana, Y., & Vudhivanich, a. V. (2021). Assessment of Weap Model in Simulating Rainfall-Runoff Relation in The Ping and Wang River Basins, Thailand The 8th National Conference on Water Resources Engineering & The 5th International Conference on Water Resources Engineering, Department of irrigation engineering, Faculty of engineering at kamphaeng saen, Kasetsart University.
Riche, A., Drias, A., Guermoui, M., Gherib, T., Boulmaiz, T., Souissi, B., & Melgani, F. (2024). A Novel Hybrid Deep-Learning Approach for Flood-Susceptibility Mapping. Remote Sensing, 16(19). https://doi.org/10.3390/rs16193673
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). https://doi.org/10.3390/rs15010192
Tehrany, M. S., Jones, S., & Shabani, F. (2019). Identifying the essential flood conditioning factors for flood prone area mapping using machine learning techniques. Catena, 175, 174-192. https://doi.org/10.1016/j.catena.2018.12.011
Wahba, M., Sharaan, M., Elsadek, W. M., Kanae, S., & Hassan, H. S. (2024). Examination of the efficacy of machine learning approaches in the generation of flood susceptibility maps. Environmental Earth Sciences, 83(14). https://doi.org/10.1007/s12665-024-11696-x
Yu, H., Luo, Z., Wang, L., Ding, X., & Wang, S. (2023). Improving the Accuracy of Flood Susceptibility Prediction by Combining Machine Learning Models and the Expanded Flood Inventory Data. Remote Sensing, 15(14). https://doi.org/10.3390/rs15143601
