Explainable Ensemble Learning for Urban Flood Risk Mapping in Jakarta Using Multi-Source Geospatial and Hydrometeorological Data

Arief Wibowo; Abdul Haris Achadi

doi:10.15408/jti.v19i1.49010

Authors

Arief Wibowo Department of Computer Science, Faculty of Information Technology, Universitas Budi Luhur
Abdul Haris Achadi Department of Disaster Management, Faculty of Economics and Bussiness, Universitas Budi Luhur

DOI:

https://doi.org/10.15408/jti.v19i1.49010

Keywords:

Ensemble Learning, Explainable Artificial Intelligence, Flood Risk, Multi-Source Data, Urban Flooding

Abstract

Urban flooding is a frequent hydrometeorological hazard in Indonesia, particularly in Jakarta, driven by rapid urbanization, limited drainage capacity, land cover change, and extreme rainfall. This study develops an explainable ensemble learning framework for urban flood risk mapping in Jakarta using multi-source geospatial and hydrometeorological data, including satellite-based rainfall, topography, land use/land cover, NDVI, and IoT-based river water level observations from 2023–2025. Flood occurrence labels were constructed by integrating municipal flood records with satellite-based inundation data. The framework integrates Random Forest, Gradient Boosting, and XGBoost models, with SHAP applied for interpretability and identification of dominant flood drivers. Model evaluation using ROC-AUC and RMSE indicates that XGBoost achieved the highest performance (AUC = 0.91, RMSE = 0.184), outperforming Random Forest (AUC = 0.87, RMSE = 0.221) and Gradient Boosting (AUC = 0.89, RMSE = 0.203). SHAP analysis identifies rainfall intensity, elevation, proximity to river channels, and built-up area percentage as the most influential factors. Despite uncertainties in flood labeling and the lack of high-resolution drainage data, the results demonstrate the potential of explainable ensemble learning for urban flood risk assessment and resilience planning.

References

[1] W. Huang, E. Park, J. Wang, and T. Sophal, “The changing rainfall patterns drive the growing flood occurrence in Phnom Penh, Cambodia,” Journal of Hydrology: Regional Studies, 2024, doi: 10.1016/j.ejrh.2024.101945.

[2] H. Kardhana, J. R. Valerian, F. Rohmat, and M. Kusuma, “Improving Jakarta’s Katulampa Barrage Extreme Water Level Prediction Using Satellite-Based Long Short-Term Memory (LSTM) Neural Networks,” Water, 2022, doi: 10.3390/w14091469.

[3] B. T. Hassan, M. Yassine, and D. Amin, “Comparison of Urbanization, Climate Change, and Drainage Design Impacts on Urban Flashfloods in an Arid Region: Case Study, New Cairo, Egypt,” Water, 2022, doi: 10.3390/w14152430.

[4] S. Huang et al., “Urbanization enhances channel and surface runoff: A quantitative analysis using both physical and empirical models over the Yangtze River basin,” Journal of Hydrology, 2024, doi: 10.1016/j.jhydrol.2024.131194.

[5] L. Zhou and L. Liu, “Enhancing dynamic flood risk assessment and zoning using a coupled hydrological-hydrodynamic model and spatiotemporal information weighting method.,” Journal of Environmental Management, vol. 366, pp. 121831, 2024, doi: 10.1016/j.jenvman.2024.121831.

[6] C. Hu, J. Xia, D. She, Z. Song, Y. Zhang, and S. Hong, “A new urban hydrological model considering various land covers for flood simulation,” Journal of Hydrology, vol. 603, pp. 126833, 2021, doi: 10.1016/j.jhydrol.2021.126833.

[7] G. Li, W. Shao, X. Su, Y. Li, Y. Zhang, and T. Song, “Urban Flood Hazard Assessment Based on Machine Learning Model,” Water Resources Management, 2025, doi: 10.1007/s11269-024-04013-5.

[8] I. Ahmad, R. Farooq, M. Ashraf, M. Waseem, and D. Shangguan, “Improving flood hazard susceptibility assessment by integrating hydrodynamic modeling with remote sensing and ensemble machine learning,” Natural Hazards, 2025, doi: 10.1007/s11069-025-07109-2.

[9] Y. Wang, P. Zhang, Y. Xie, L. Chen, and Y. Li, “Toward Explainable Flood Risk Prediction: Integrating A Novel Hybrid Machine Learning Model,” Sustainable Cities and Society, 2025, doi: 10.1016/j.scs.2025.106140.

[10] T. Canty et al., “System dynamics modeling in support of community-based decision-making to reduce opioid overdose fatalities,” Frontiers in Public Health, vol. 13, 2025, doi: 10.3389/fpubh.2025.1616032.

[11] B. Pradhan, S. Lee, A. Dikshit, and H. Kim, “Spatial flood susceptibility mapping using an explainable artificial intelligence (XAI) model,” Geoscience Frontiers, 2023, doi: 10.1016/j.gsf.2023.101625.

[12] A. Ponce-Bobadilla, V. Schmitt, C. Maier, S. Mensing, and S. Stodtmann, “Practical guide to SHAP analysis: Explaining supervised machine learning model predictions in drug development,” Clinical and Translational Science, vol. 17, 2024, doi: 10.1111/cts.70056.

[13] A. Cartolano, A. Cuzzocrea, and G. Pilato, “Analyzing and assessing explainable AI models for smart agriculture environments,” Multimedia Tools and Applications, vol. 83, pp. 37225–37246, 2024, doi: 10.1007/s11042-023-17978-z.

[14] K. Nam, Y. Lee, S. Lee, S. Kim, and S. Zhang, “Explainable Artificial Intelligence (XAI) for Flood Susceptibility Assessment in Seoul: Leveraging Evolutionary and Bayesian AutoML Optimization,” Remote Sensing, 2025, doi: 10.3390/rs17132244.

[15] A. Khoshkonesh, R. Nazari, M. Nikoo, and M. Karimi, “Enhancing flood risk assessment in urban areas by integrating hydrodynamic models and machine learning techniques.,” Science of the Total Environment, pp. 175859, 2024, doi: 10.1016/j.scitotenv.2024.175859.

[16] C. Singha, V. Rana, Q. B. Pham, D. Nguyen, and E. Łupikasza, “Integrating machine learning and geospatial data analysis for comprehensive flood hazard assessment,” Environmental Science and Pollution Research., vol. 31, pp. 48497–48522, 2024, doi: 10.1007/s11356-024-34286-7.

[17] S. Wongchuig et al., “Multi‐Satellite Data Assimilation for Large‐Scale Hydrological‐Hydrodynamic Prediction: Proof of Concept in the Amazon Basin,” Water Resources Research, vol. 60, 2024, doi: 10.1029/2024wr037155.

[18] W. Qing, H. Zhang, Y. Chen, X. Yifan, H. Yin, and X. Zuxin, “City scale urban flooding risk assessment using multi-source data and machine learning approach,” Journal of Hydrology, 2024, doi: 10.1016/j.jhydrol.2024.132626.

[19] M. Zhang, X. Fu, S. Liu, and C. Zhang, “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, 2025, doi: 10.3390/rs17071189.

[20] M. Khan, S. Arslanturk, and S. Draghici, “A comprehensive review of spatial transcriptomics data alignment and integration,” Nucleic Acids Research, vol. 53, 2025, doi: 10.1093/nar/gkaf536.

[21] K.-L. Du, R. Zhang, B. Jiang, J. Zeng, and J. Lu, “Foundations and Innovations in Data Fusion and Ensemble Learning for Effective Consensus,” Mathematics, 2025, doi: 10.3390/math13040587.

[22] D. Kulaklıoğlu, “Explainable AI: Enhancing Interpretability of Machine Learning Models,” Human–Computer Interaction, 2024, doi: 10.62802/z3pde490.

[23] V. Coletta et al., “Socio-hydrological modelling using participatory System Dynamics modelling for enhancing urban flood resilience through Blue-Green Infrastructure,” Journal of Hydrology, vol. 636, pp. 131248, 2024, doi: 10.1016/j.jhydrol.2024.131248.

[24] T. Tong dan Z. Li, “Predicting learning achievement using ensemble learning with result explanation,” PLoS One, vol. 20, 2025, doi: 10.1371/journal.pone.0312124.

[25] H. Liu, H. Yan, and M. Guan, “Evaluating the effects of topography and land use change on hydrological signatures: a comparative study of two adjacent watersheds,” Hydrology and Earth System Sciences, 2025, doi: 10.5194/hess-29-2109-2025.

[26] X. Zhu, H. Guo, and J. J. Huang, “Urban flood susceptibility mapping using remote sensing, social sensing and an ensemble machine learning model,” Sustainable Cities and Society, 2024, doi: 10.1016/j.scs.2024.105508.

[27] B. Du, M. Wang, J. Zhang, Y. Chen, and T. Wang, “Urban flood prediction based on PCSWMM and stacking integrated learning model,” Natural Hazards, 2024, doi: 10.1007/s11069-024-06893-7.

[28] W. Dai, Y. Tang, N. Liao, S. Zou, and Z. Cai, “Urban flood prediction using ensemble artificial neural network: an investigation on improving model uncertainty,” Applied Water Science, vol. 14, pp. 1–10, 2024, doi: 10.1007/s13201-024-02201-7.