Performance Comparison of Random Forest, XGBoost, and SVM for Flood Risk Prediction Using BNPB GIS Data
DOI:
https://doi.org/10.63158/journalisi.v8i1.1461Keywords:
Flood Prediction, Machine Learning, Random Forest, XGBoost, SVM, Disaster Risk, Early Warning SystemAbstract
This study compares the performance of three machine learning algorithms—Random Forest, XGBoost, and Support Vector Machine (SVM)—for predicting flood risk using spatial and non-spatial data from BNPB GIS. The analysis focuses on disaster records from January 3 to 15, 2026, with district-city as the spatial unit of observation. Following data cleaning, exploratory analysis, and feature preparation, the models were evaluated using ROC-AUC, PR-AUC, F1-Score, Precision, Recall, and Accuracy. XGBoost demonstrated the highest ROC-AUC (0.675), indicating strong overall performance in distinguishing flood from non-flood events. Random Forest achieved the highest Recall (0.947), showing superior sensitivity in detecting flood events, while SVM exhibited fluctuating performance with a lower ROC-AUC (0.496). Visualizations of model behavior and spatial flood patterns were provided to support model interpretability. The study’s results suggest that ensemble models, particularly XGBoost and Random Forest, can significantly enhance flood risk prediction, improving the accuracy and sensitivity of early warning systems. These findings contribute to the development of more effective data-driven flood mitigation strategies in Indonesia, enabling better disaster preparedness and response.
Downloads
References
[1] Badan Nasional Penanggulangan Bencana, “Data dan Informasi Kebencanaan Bulanan Teraktual,” Info Bencana, vol. 5, no. 1, pp. 1–19, 2025.
[2] Badan Nasional Penanggulangan Bencana, “Indeks Risiko Bencana Indonesia Tahun 2024,” Indeks Risiko Bencana Indonesia Tahun 2024, vol. 03, pp. 1–184, 2024.
[3] Y. S. Ajaj, I. A. Ahmad, N. A. Mohammed, and N. Yahya, “Leveraging AI for Disaster Management: A Comprehensive Review of Applications and Challenges BT - Intelligent Systems, Blockchain, and Communication Technologies,” A. Abdelgawad, A. Jamil, and A. A. Hameed, Eds., Cham: Springer Nature Switzerland, 2025, pp. 177–184.
[4] L. Dong, Y. Bai, Q. Xu, and E. Mas, “Optimizing the Post-disaster Resource Allocation with Q-Learning: Demonstration of 2021 China Flood BT - Database and Expert Systems Applications,” C. Strauss, A. Cuzzocrea, G. Kotsis, A. M. Tjoa, and I. Khalil, Eds., Cham: Springer International Publishing, 2022, pp. 256–262.
[5] B. J. Weiner, “A theory of organizational readiness for change,” Implementation Science, vol. 4, no. 1, pp. 1–9, 2009, doi: 10.1186/1748-5908-4-67.
[6] Badan Nasional Penanggulangan Bencana, Indeks Risiko Bencana Indonesia Tahun 2023. 2023.
[7] A. Anindyaputri, J. E. Suseno, and C. E. Widodo, “An Integrated Information System for Selection of Areas Tourist Sites Using Clustering and Electre Methods,” vol. 165, no. Iccsr, pp. 71–75, 2018, doi: 10.2991/iccsr-18.2018.16.
[8] H. Xiang and T. Itagaki, “The Social Impact of IoT in Disasters,” 2nd International Conference on IT Innovations and Knowledge Discovery, ITIKD 2024, pp. 1–7, 2025, doi: 10.1109/ITIKD63574.2025.11005074.
[9] M. Janardhan, B. Likhitha, O. Purandeswari, P. Rani, and G. Harshini, “IoT and AI for Efficient Forest Fire Detection, Monitoring, and Risk Prediction with Real-Time Alerts,” Proceedings of 5th International Conference on Trends in Material Science and Inventive Materials, ICTMIM 2025, pp. 1324–1330, 2025, doi: 10.1109/ICTMIM65579.2025.10988101.
[10] X. Wu, H. Cheng, B. Wu, N. Jiang, and Y. Huang, “A regional XGBoost-based predictive model for the cumulative hours of wind speed levels,” Atmos. Res., vol. 327, no. June 2025, 2026, doi: 10.1016/j.atmosres.2025.108336.
[11] S. Lee et al., “Sistem Pendukung Keputusan Pemberian Bantuan Logistik Bencana Banjir di Jawa Tengah Berdasarkan Proses Hierarki Analitik,” J. Chem. Inf. Model., vol. 53, no. 9, pp. 1689–1699, 2012, [Online]. Available: 10.1016/j.tws.2012.02.007
[12] M. Harigane et al., “Indonesian Disaster Dataset Based on Type for Technology-Based Disaster Management and Mitigation,” International Journal of Disaster Risk Reduction, vol. 25, no. 1, pp. 123–132, 2025, doi: 10.17632/pyftdypmfs.1.
[13] A. Vereshchaka and W. Dong, “Dynamic Resource Allocation During Natural Disasters Using Multi-Agent Environment BT - Social, Cultural, and Behavioral Modeling,” R. Thomson, H. Bisgin, C. Dancy, and A. Hyder, Eds., Cham: Springer International Publishing, 2019, pp. 123–132.
[14] T. Agfianto, D. A. Wijaya, N. Wijayanto, N. Wulandari, C. Baker-Beall, and A. Chapman, “Preparedness of geotourism facilities in disaster mitigation based on the global South viewpoint: case study of East Java, Indonesia,” Worldwide Hospitality and Tourism Themes, vol. 17, no. 3, pp. 354–366, 2025, doi: 10.1108/WHATT-01-2025-0039.
[15] H. Dai et al., “Collaborative Scheduling Framework for Post-Disaster Restoration: Integrating Electric Vehicles and Traffic Dynamics in Waterlogging Scenarios,” Energies (Basel)., vol. 18, no. 7, pp. 1–20, 2025, doi: 10.3390/en18071708.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Information Systems and Informatics
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors Declaration
- The Authors certify that they have read, understood, and agreed to the Journal of Information Systems and Informatics (JournalISI) submission guidelines, policies, and submission declaration. The submission has been prepared using the provided template.
- The Authors certify that all authors have approved the publication of this manuscript and that there is no conflict of interest.
- The Authors confirm that the manuscript is their original work, has not received prior publication, is not under consideration for publication elsewhere, and has not been previously published.
- The Authors confirm that all authors listed on the title page have contributed significantly to the work, have read the manuscript, attest to the validity and legitimacy of the data and its interpretation, and agree to its submission.
- The Authors confirm that the manuscript is not copied from or plagiarized from any other published work.
- The Authors declare that the manuscript will not be submitted for publication in any other journal or magazine until a decision is made by the journal editors.
- If the manuscript is finally accepted for publication, the Authors confirm that they will either proceed with publication immediately or withdraw the manuscript in accordance with the journal’s withdrawal policies.
- The Authors agree that, upon publication of the manuscript in this journal, they transfer copyright or assign exclusive rights to the publisher, including commercial rights
