Hybrid PSO-XGBoost Model for Accurate Flood Risk Assessment
DOI:
https://doi.org/10.30871/jaic.v9i6.11094Keywords:
XGBoost, Particle Swarm Optimization, Flood Prediction, Parameter Optimization, Machine LearningAbstract
Flood risk prediction is a crucial step in disaster mitigation. This study optimizes the Extreme Gradient Boosting (XGBoost) algorithm using the Particle Swarm Optimization (PSO) method to improve prediction accuracy. The process includes data cleaning, normalization, and classification of risk levels into low, medium, and high. The XGBoost model is trained both before and after parameter optimization of n_estimators, max_depth, and learning_rate. Before optimization, the model achieved 93% accuracy but struggled to identify minority classes. After optimization with PSO, accuracy increased to 97%, with the recall for the low-risk class improving from 21% to 57%. The optimized model also demonstrated more stable performance compared to Support Vector Machine (SVM) and Random Forest. These findings indicate that the combination of XGBoost and PSO can provide more accurate and efficient flood risk predictions.
Downloads
References
[1] H. Farhadi and M. Najafzadeh, “Flood Risk Mapping by Remote Sensing Data and Random Forest Technique,” Water, vol. 13, no. 21, p. 3115, Nov. 2021, doi: 10.3390/w13213115.
[2] H. Khodaei, F. Nasiri Saleh, A. Nobakht Dalir, and E. Zarei, “Future flood susceptibility mapping under climate and land use change,” Sci Rep, vol. 15, no. 1, Apr. 2025, doi: 10.1038/s41598-025-97008-0.
[3] M. Ma et al., “XGBoost-based method for flash flood risk assessment,” Journal of Hydrology, vol. 598, p. 126382, Jul. 2021, doi: 10.1016/j.jhydrol.2021.126382.
[4] M. M. A. Syeed, M. Farzana, I. Namir, I. Ishrar, M. H. Nushra, and T. Rahman, “Flood Prediction Using Machine Learning Models,” in 2022 International Congress on Human-Computer Interaction, Optimization and Robotic Applications (HORA), Ankara, Turkey: IEEE, Jun. 2022, pp. 1–6. doi: 10.1109/HORA55278.2022.9800023.
[5] G. Al-Rawas, M. R. Nikoo, M. Al-Wardy, and T. Etri, “A Critical Review of Emerging Technologies for Flash Flood Prediction: Examining Artificial Intelligence, Machine Learning, Internet of Things, Cloud Computing, and Robotics Techniques,” Water, vol. 16, no. 14, p. 2069, Jul. 2024, doi: 10.3390/w16142069.
[6] S.-E. Ryu, D.-H. Shin, and K. Chung, “Prediction Model of Dementia Risk Based on XGBoost Using Derived Variable Extraction and Hyper Parameter Optimization,” IEEE Access, vol. 8, pp. 177708–177720, 2020, doi: 10.1109/access.2020.3025553.
[7] A. Ogunleye and Q.-G. Wang, “XGBoost Model for Chronic Kidney Disease Diagnosis,” IEEE/ACM Trans. Comput. Biol. and Bioinf., vol. 17, no. 6, pp. 2131–2140, Nov. 2020, doi: 10.1109/TCBB.2019.2911071.
[8] N. Ghatasheh, I. Altaharwa, and K. Aldebei, “Modified Genetic Algorithm for Feature Selection and Hyper Parameter Optimization: Case of XGBoost in Spam Prediction,” IEEE Access, vol. 10, pp. 84365–84383, 2022, doi: 10.1109/access.2022.3196905.
[9] B. Liu, H. Lin, Y. Chen, and C. Yang, “Prediction of Rock Unloading Strength Based on PSO-XGBoost Hybrid Models,” Materials, vol. 17, no. 17, p. 4214, Aug. 2024, doi: 10.3390/ma17174214.
[10] D.-V. Hoang and Y.-A. Liou, “Elevating Flash Flood Prediction Accuracy: A Synergistic Approach with PSO and GA Optimization,” Dec. 12, 2024, Copernicus GmbH. doi: 10.5194/nhess-2024-215.
[11] J. Yu, W. Zheng, L. Xu, L. Zhangzhong, G. Zhang, and F. Shan, “A PSO-XGBoost Model for Estimating Daily Reference Evapotranspiration in the Solar Greenhouse,” Intelligent Automation & Soft Computing, vol. 26, no. 5, pp. 989–1003, 2020, doi: 10.32604/iasc.2020.010130.
[12] D. Kim, K. Lee, J. G. Hwang-Bo, H. S. Kim, and S. Kim, “Development of the Method for Flood Water Level Forecasting and Flood Damage Warning Using an AI-based Model,” J. Korean Soc. Hazard Mitig, vol. 22, no. 4, pp. 145–156, Aug. 2022, doi: 10.9798/kosham.2022.22.4.145.
[13] H. C. Kilinc, “Daily Streamflow Forecasting Based on the Hybrid Particle Swarm Optimization and Long Short-Term Memory Model in the Orontes Basin,” Water, vol. 14, no. 3, p. 490, Feb. 2022, doi: 10.3390/w14030490.
[14] W. Liang, S. Luo, G. Zhao, and H. Wu, “Predicting Hard Rock Pillar Stability Using GBDT, XGBoost, and LightGBM Algorithms,” Mathematics, vol. 8, no. 5, p. 765, May 2020, doi: 10.3390/math8050765.
[15] M. El Haou, M. Ourribane, M. Ismaili, S. Krimissa, and M. Namous, “Enhancing urban flood hazard assessment: a comparative analysis of frequency ratio and xgboost models for precision risk mapping,” Ecol. Eng. Environ. Technol., vol. 26, no. 3, pp. 286–300, Mar. 2025, doi: 10.12912/27197050/200141.
[16] S. Puttinaovarat and P. Horkaew, “Flood Forecasting System Based on Integrated Big and Crowdsource Data by Using Machine Learning Techniques,” IEEE Access, vol. 8, pp. 5885–5905, 2020, doi: 10.1109/access.2019.2963819.
[17] X. Dairu and Z. Shilong, “Machine Learning Model for Sales Forecasting by Using XGBoost,” in 2021 IEEE International Conference on Consumer Electronics and Computer Engineering (ICCECE), Guangzhou, China: IEEE, Jan. 2021, pp. 480–483. doi: 10.1109/iccece51280.2021.9342304.
[18] A. B. Parsa, “Toward safer highways, application of XGBoost and SHAP for real-time accident detection and feature analysis,” Accident Analysis and Prevention, 2020.
[19] H. Jiang, Z. He, G. Ye, and H. Zhang, “Network Intrusion Detection Based on PSO-Xgboost Model,” IEEE Access, vol. 8, pp. 58392–58401, 2020, doi: 10.1109/ACCESS.2020.2982418.
[20] E. Gul, “Urban flood hazard assessment using FLA-optimized boost algorithms in Ankara, Türkiye,” Appl Water Sci, vol. 15, no. 4, Apr. 2025, doi: 10.1007/s13201-025-02424-2.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 Lailatun Nabilah, Lukman Hakim
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License (Attribution-ShareAlike 4.0 International (CC BY-SA 4.0) ) that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
