Predicting Urban Flood Susceptibility Using Machine Learning and Geospatial Indicators for Climate-Resilient Infrastructure Planning

Muhammad Farhan Akbar; Intan Permata Sari; Arif Rahman Hakim; Dewi Lestari Wulandari

Authors

Muhammad Farhan Akbar Universitas Indonesia Author
Intan Permata Sari Universitas Indonesia Author
Arif Rahman Hakim Universitas Indonesia Author
Dewi Lestari Wulandari Universitas Indonesia Author

Keywords:

urban flood susceptibility, machine learning, geospatial indicators, climate-resilient infrastructure, Semarang City

Abstract

Purpose – This study predicts urban flood susceptibility in Semarang City, Indonesia, by integrating machine-learning algorithms with hydroclimatic, topographic, land-surface, and built-environment geospatial indicators and translating the results into climate-resilient infrastructure priorities.

Methodology – A quantitative spatial-predictive design used a 10 m × 10 m raster grid and 2020–2025 geospatial observations. Logistic Regression, Support Vector Machine, Random Forest, XGBoost, and LightGBM were evaluated through repeated spatial block cross-validation and an independent test dataset. SHapley Additive exPlanations interpreted predictor contributions, while susceptibility was integrated with infrastructure criticality and exposure.

Findings – In the simulated analytical scenario, XGBoost achieved the strongest performance with an AUC of 0.962, accuracy of 0.908, and F1-score of 0.910. Elevation, 72-hour antecedent rainfall, Topographic Wetness Index, impervious-surface ratio, and river distance were the dominant predictors. High or very high susceptibility covered 31.8% of Semarang City, while 29.5% had high or very high infrastructure adaptation priority.

Implications – The framework supports prioritization of drainage improvement, infrastructure strengthening, blue-green infrastructure, land-use management, and detailed engineering assessment.

Originality – The study integrates multidimensional geospatial indicators, interpretable machine learning, spatially robust validation, and infrastructure-priority assessment in a unified climate-resilient planning framework.

References

Adnan, M. S. G., Siam, Z. S., Kabir, I., Kabir, Z., Ahmed, M. R., Hassan, Q. K., Rahman, R. M., & Dewan, A. (2023). A novel framework for addressing uncertainties in machine learning-based geospatial approaches for flood prediction. Journal of Environmental Management, 326, 116813. https://doi.org/10.1016/j.jenvman.2022.116813

Ahmad, S., Peng, X., Ashraf, A., Yin, D., Chen, Z., Ahmed, R., Israr, M., & Jia, H. (2025). Building resilient urban drainage systems by integrated flood risk index for evidence-based planning. Journal of Environmental Management, 374, 124130. https://doi.org/10.1016/j.jenvman.2025.124130

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, 63–81. https://doi.org/10.1007/s41748-023-00369-7

Ambily, P., Chithra, N. R., & Mohammed Firoz, C. (2024). A framework for urban pluvial flood resilient spatial planning through blue-green infrastructure. International Journal of Disaster Risk Reduction, 103, 104342. https://doi.org/10.1016/j.ijdrr.2024.104342

Amiri, A., Soltani, K., Ebtehaj, I., & Bonakdari, H. (2024). A novel machine learning tool for current and future flood susceptibility mapping by integrating remote sensing and geographic information systems. Journal of Hydrology, 632, 130936. https://doi.org/10.1016/j.jhydrol.2024.130936

Anik, M. S. B. M., An, C., & Li, S. S. (2025). Evolution from the physical process-based approaches to machine learning approaches to predicting urban floods: A literature review. Environmental Systems Research, 14, 15. https://doi.org/10.1186/s40068-025-00409-3

Azadgar, A., Nyka, L., & Salata, S. (2024). Advancing urban flood resilience: A systematic review of urban flood risk mitigation model, research trends, and future directions. Land, 13(12), 2138. https://doi.org/10.3390/land13122138

Chen, Y., Zhang, X., Yang, K., Zeng, S., & Hong, A. (2023). Modeling rules of regional flash flood susceptibility prediction using different machine learning models. Frontiers in Earth Science, 11, 1117004. https://doi.org/10.3389/feart.2023.1117004

Costache, R., Bărbulescu, A., Fanti, R., & Segoni, S. (2025). Flood susceptibility assessment using multi-tier feature selection and ensemble boosting machine learning models. Water, 17(14), 2041. https://doi.org/10.3390/w17142041

Dawson, G., Butt, J., Jones, A., & Fraccaro, P. (2023). Flood susceptibility mapping at the country scale using machine learning approaches. Applied AI Letters, 4(4), e88. https://doi.org/10.1002/ail2.88

Dharmarathne, G., Waduge, A. O., Bogahawaththa, M., Rathnayake, U., & Meddage, D. (2024). Adapting cities to the surge: A comprehensive review of climate-induced urban flooding. Results in Engineering, 22, 102123. https://doi.org/10.1016/j.rineng.2024.102123

Gulshad, K., Yaseen, A., & Szydłowski, M. (2024). From data to decision: Interpretable machine learning for predicting flood susceptibility in Gdańsk, Poland. Remote Sensing, 16(20), 3902. https://doi.org/10.3390/rs16203902

Haghbin, S., & Mahjouri, N. (2023). Quantifying and improving flood resilience of urban drainage systems based on socio-ecological criteria. Journal of Environmental Management, 339, 117799. https://doi.org/10.1016/j.jenvman.2023.117799

Hussain, M., Tayyab, M., Ullah, K., Ullah, S., Rahman, Z. U., Zhang, J., & Al-Shaibah, B. (2023). Development of a new integrated flood resilience model using machine learning with GIS-based multi-criteria decision analysis. Urban Climate, 50, 101589. https://doi.org/10.1016/j.uclim.2023.101589

Islam, T., Zeleke, E. B., Afroz, M., & Melesse, A. M. (2025). A systematic review of urban flood susceptibility mapping: Remote sensing, machine learning, and other modeling approaches. Remote Sensing, 17(3), 524. https://doi.org/10.3390/rs17030524

Kaur, B., Binns, A., McBean, E., Sandink, D., Castro, K., & Gharabaghi, B. (2025). Urban flood susceptibility mapping for Toronto, Canada, using supervised regression and machine learning models. Journal of Flood Risk Management, 18(2), e70051. https://doi.org/10.1111/jfr3.70051

Kurugama, K. M., Kazama, S., Hiraga, Y., & Samarasuriya, C. (2024). A comparative spatial analysis of flood susceptibility mapping using boosting machine learning algorithms in Rathnapura, Sri Lanka. Journal of Flood Risk Management, 17(2), e12980. https://doi.org/10.1111/jfr3.12980

Li, J., & Burian, S. J. (2023). Evaluating real-time control of stormwater drainage network and green stormwater infrastructure for enhancing flooding resilience under future rainfall projections. Resources, Conservation and Recycling, 198, 107123. https://doi.org/10.1016/j.resconrec.2023.107123

Li, J., Strong, C., Wang, J., & Burian, S. (2023). An event-based resilience index to assess the impacts of land imperviousness and climate changes on flooding risks in urban drainage systems. Water, 15(14), 2663. https://doi.org/10.3390/w15142663

Li, Z., Liu, H., Fu, Z., & Fu, G. (2025). Assessment of rainfall-driven urban surface water flood hazards using convolutional neural networks. Journal of Flood Risk Management, 18(3), e70102. https://doi.org/10.1111/jfr3.70102

Liao, Z., He, X., Tian, W., Zhang, Z., Wang, H., & Xie, W. (2025). An integrated assessment of urban flooding risk and resilience based on spatial grids. Urban Water Journal, 22(2), 174–185. https://doi.org/10.1080/1573062X.2024.2443895

Lin, J. L., Sreng, C. S., Oare, E., & Batarseh, F. A. (2023). NeuralFlood: An AI-driven flood susceptibility index. Frontiers in Water, 5, 1291305. https://doi.org/10.3389/frwa.2023.1291305

Long, G., Tantanee, S., Nusit, K., & Sooraksa, P. (2025). A comprehensive review of flood-prone area zonation using ensemble and hybrid machine learning models with a framework proposal for modelling. Geocarto International, 40(1), 2492372. https://doi.org/10.1080/10106049.2025.2492372

Lyu, H.-M., Yin, Z., Shen, S.-L., Chen, X.-S., & Su, D. (2025). A novel framework incorporating machine learning into GIS for flood susceptibility prediction of urban metro systems. Science China Technological Sciences, 68(6), 1620701. https://doi.org/10.1007/s11431-024-2925-8

Manna, H., Das, M., Pramanik, M., Sarkar, S., Mahato, S., Talukdar, S., Alkhuraiji, W. S., & Zhran, M. (2025). Ensemble intelligence for urban resilience: Flood susceptibility modeling in Mumbai using advanced machine learning. Geomatics, Natural Hazards and Risk, 16(1), 2588718. https://doi.org/10.1080/19475705.2025.2588718

Meng, C., & Jin, H. (2023). A comparison of machine learning models for predicting flood susceptibility based on the enhanced NHAND method. Sustainability, 15(20), 14928. https://doi.org/10.3390/su152014928

Qin, X., Wang, S., Meng, M., Long, H., Zhang, H., & Shi, H. (2025). Enhancing urban resilience through machine learning-supported flood risk assessment: Integrating flood susceptibility with building function vulnerability. npj Urban Sustainability, 5, 19. https://doi.org/10.1038/s42949-025-00208-w

Rezvani, S. M. H. S., Silva, M. J. F., & Almeida, N. (2024). Mapping geospatial AI flood risk in national road networks. ISPRS International Journal of Geo-Information, 13(9), 323. https://doi.org/10.3390/ijgi13090323

Rudra, R. R., & Sarkar, S. K. (2023). Artificial neural network for flood susceptibility mapping in Bangladesh. Heliyon, 9(6), e16459. https://doi.org/10.1016/j.heliyon.2023.e16459

Salvati, A., Nia, A. M., Salajegheh, A., Ghaderi, K., Asl, D. T., Al-Ansari, N., Solaimani, F., & Clague, J. J. (2023). Flood susceptibility mapping using support vector regression and hyper-parameter optimization. Journal of Flood Risk Management, 16(4), e12920. https://doi.org/10.1111/jfr3.12920

Sampurno, J., Putra, M. G. E., Faryuni, I. D., & Adriat, R. (2024). Flood impact assessment in remote areas using machine learning, SAR, and GIS: A case study of Ngabang District, Indonesia. Journal of Hydroinformatics, 26(11), 2928–2938. https://doi.org/10.2166/hydro.2024.324

Shirzadi, A., Salvati, A., Tahan, M. H., Shahabi, H., Nodoushan, E. J., Ramezani, M., Hashim, M., & Clague, J. J. (2025). Urban flood susceptibility mapping using deep and machine learning algorithms as a management tool: A case study of Sanandaj City, Iran. Ecological Indicators, 178, 113886. https://doi.org/10.1016/j.ecolind.2025.113886

Singha, C., Rana, V. K., Abu El-Magd, S. A., Nguyen, D. C., & Łupikasza, E. (2024). Integrating machine learning and geospatial data analysis for comprehensive flood hazard assessment. Environmental Science and Pollution Research, 31, 48497–48522. https://doi.org/10.1007/s11356-024-34286-7

Tayyab, M., Hussain, M., Zhang, J., Ullah, S., Tong, Z., Rahman, Z. U., Al-Aizari, A. R., & Al-Shaibah, B. (2024). Leveraging GIS-based AHP, remote sensing, and machine learning for susceptibility assessment of different flood types in Peshawar, Pakistan. Journal of Environmental Management, 371, 123094. https://doi.org/10.1016/j.jenvman.2024.123094

Uddameri, V., & Hernandez, E. A. (2025). Machine learning for flood resiliency: Current status and unexplored directions. Environments, 12(8), 259. https://doi.org/10.3390/environments12080259

Verdyansyah, A., Chang, Y.-L., Wang, F.-C., Tsai, F., & Lin, T.-H. (2025). Integrating CMIP6 and remote sensing datasets for current and future flood susceptibility projections using machine learning under climate change scenarios in Demak District for future sustainable planning. Sustainability, 17(18), 8188. https://doi.org/10.3390/su17188188

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. https://doi.org/10.1111/jfr3.13047

Wang, Z., Lyu, H., & Zhang, C. (2024). Urban pluvial flood susceptibility mapping based on a novel explainable machine learning model with synchronous enhancement of fitting capability and explainability. Journal of Hydrology, 642, 131903. https://doi.org/10.1016/j.jhydrol.2024.131903

Wang, J., Sanderson, J. E., Saify Iqbal, S. M., & Woo, W. L. (2025). Accelerated and interpretable flood susceptibility mapping through explainable deep learning with hydrological prior knowledge. Remote Sensing, 17(9), 1540. https://doi.org/10.3390/rs17091540

Widya, L. K., Rezaie, F., Lee, W., Lee, C.-W., Nurwatik, N., & Lee, S. (2024). Flood susceptibility mapping of Cheongju, South Korea based on the integration of environmental factors using various machine learning approaches. Journal of Environmental Management, 364, 121291. https://doi.org/10.1016/j.jenvman.2024.121291

Xing, Z., Lyu, G., Yao, Y., Liu, Z., & Zhang, X. (2025). Fine-grained analysis and mapping of urban flood susceptibility with interpretable machine learning: A case study of Hefei, China. Journal of Hydrology: Regional Studies, 60, 102501. https://doi.org/10.1016/j.ejrh.2025.102501

Zerouali, B., Almaliki, A. H., & Santos, C. A. G. (2025). Flood susceptibility mapping in arid urban areas using SHAP-enhanced stacked ensemble learning: A case study of Jeddah. Journal of Environmental Management, 393, 127128. https://doi.org/10.1016/j.jenvman.2025.127128

Zhou, S., Zhang, D., Wang, M., Liu, Z., Gan, W., Zhao, Z., Xue, S., Müller, B., & Ni, X. (2024). Risk-driven composition decoupling analysis for urban flooding prediction in high-density urban areas using Bayesian-optimized LightGBM. Journal of Cleaner Production, 457, 142286. https://doi.org/10.1016/j.jclepro.2024.142286