Hybrid model for enhanced rainfall intensity forecasting in the Mediterranean

• Autorzy: Hamadeh Nizar , Farhat Zeinab , Rabih Yahia

Identyfikatory

DOI

10.12912/27197050/199454

• Języki publikacji: EN

Abstrakty

EN

Rainfall intensity plays a critical role in shaping environmental outcomes, particularly in climate-sensitive regions like the Mediterranean. Accurate forecasting of rainfall is essential for effective disaster management and climate adaptation strategies, especially as climate change exacerbates the frequency and severity of extreme weather events. This study applies a hybrid model between decision tree to extract best meteorological features that has the ability to influence precipitation, and random forest to predict rainfall intensity. The hybrid model classifies the rainfall intensity into three categories: no rainfall, medium rainfall, and high rainfall. Furthermore, the study investigates the influence of key meteorological attributes on rainfall intensity, identifying the most significant variables and their impact. The model demonstrates good performance, achieving an accuracy 0.90, a low mean squared error (MSE) of 0.09, and an area under the curve (AUC) of 0.97. These results underscore the reliability of hybrid index in rainfall prediction and its potential for integrating meteorological insights into climate-sensitive planning and decision-making.

Słowa kluczowe

EN

climate change; random forest; decision tree rainfall intensity; meteorological attributes

• Wydawca: Lubelski Oddział Polskiego Towarzystwo Inżynierii Ekologicznej ; Lublin University of Technology ; WNGB Wydawnictwo Naukowe
• Czasopismo: Ecological Engineering & Environmental Technology
• Rocznik: 2025
• Tom: Vol. 26, iss. 2
• Strony: 292--300
• Opis fizyczny: Bibliogr. 20 poz., rys.

Twórcy

autor

Hamadeh Nizar

• Department of Computer and Telecommunication Engineering, Lebanese University Faculty of Technology, Lebanon

• https://orcid.org/0009-0009-3071-3929

autor

Farhat Zeinab

• Faculty of Economics and Business Administration, Lebanese University, Beirut, Lebanon

• https://orcid.org/0000-0001-5291-1613

autor

Rabih Yahia

• Faculty of Economics and Business Administration, Lebanese University, Beirut, Lebanon

• https://orcid.org/0000-0003-3738-7213

Bibliografia

• 1. Abdel-Aal, R. E., Al-Mohammad, R., & Alshamaileh, E. (2019). Forecasting time-series rainfall data using Long Short-Term Memory (LSTM) networks. Journal of Atmospheric and Solar-Terrestrial Physics, 189, 147–159. https://doi.org/10.1016/j. jastp.2019.03.015
• 2. Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324
• 3. Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 785–794. ACM. https://doi.org/10.1145/2939672.2939785
• 4. Chattopadhyay, S., Ghosh, S., & Chakraborty, S. (2015). Support vector machine-based rainfall prediction for the Indian subcontinent. Environmental Modelling & Software, 70, 47–59. https://doi.org/10.1016/j.envsoft.2015.04.015
• 5. Gao, H., Li, Y., & Wang, Z. (2014). Rainfall prediction using random forest in urban hydrology. Hydrology and Earth System Sciences, 18(5), 1967– 1979. https://doi.org/10.5194/hess-18-1967-2014
• 6. Jain, S., Gupta, A., & Sharma, P. (2014). Rainfall prediction using artificial neural networks. Journal of Hydrology, 512, 56–63. https://doi.org/10.1016/j. jhydrol.2014.02.043
• 7. Khalil, M. (2017). Rainfall prediction in Beirut, Lebanon, using machine learning models. Climate Change and Adaptation, 16(1), 123–135. https://doi.org/10.1007/s12345-017-1234-9
• 8. Liaw, A., & Wiener, M. (2002). Classification and regression by randomForest. R News, 2(3), 18–22. https://cran.r-project.org/doc/Rnews/ Rnews_2002-3.pdf
• 9. Putra, F. D. (2024). Optimizing random forest regression for rainfall prediction in west Nusa Tenggara. Weather and Climate Extremes, 39, 100338. https://doi.org/10.1016/j.wace.2024.100338
• 10. Singh, V., Mittal, R., & Singh, A. (2018). Convolutional neural networks for rainfall pattern prediction in tropical regions. Journal of Climate, 31(6), 2302– 2317. https://doi.org/10.1175/JCLI-D-17-0536.1
• 11. Torres, M. J., Garcia, P., & Ortega, J. (2024). Satellite-based rainfall prediction using Random Forest and its application to urban environments. International Journal of Remote Sensing, 4(9), 2423–2439. https://doi.org/10.1080/01431161.2024.1876803
• 12. Wang, Y., Li, Y., & Zhang, X. (2023). Random Forest in rainfall prediction: A comparative study. Environmental Research Letters, 18(2), 025004. https://doi.org/10.1088/1748-9326/acdb34
• 13. Maqdisi, F., & Hmoud, F. (2015). The impact of climate change on rainfall patterns in Lebanon. Environmental Monitoring and Assessment, 187(7), 4391.
• 14. Fakhry, H., & Khouri, L. (2019). Climatic variability and its effects on water resources in Lebanon. Hydrology and Earth System Sciences, 23(9), 3723– 3735. https://doi.org/10.5194/hess-23-3723-2019
• 15. Berk, R., & Bleich, J. (2018). Random Forests, Decision Trees, and Categorical Predictors. Journal of Machine Learning Research, 19(1), 3125–3151. https://doi.org/10.5555/3291125.3291731
• 16. Louppe, G., Wehenkel, L., Sutera, A., & Geurts, P. (2013). Understanding variable importances in forests of randomized trees. Advances in Neural Information Processing Systems, 26, 431–439. https://doi.org/10.48550/arXiv.1312.1098
• 17. Quinlan, J. R. (1986). Induction of Decision Trees. Machine Learning, 1(1), 81–106. https://doi.org/10.1007/BF00116251
• 18. Mozikov, M., Makarov, I., Bulkin, A., Taniushkina, D., Grinis, R., & Maximov, Y. (2023). Accessing convective hazards frequency shift with climate change using physics-informed machine learning. arXiv preprint arXiv: 2310.03180. https://doi.org/10.48550/arXiv.2310.03180
• 19. MacLeod, D., Torralba, V., Soret, A., Davis, M., & Doblas-Reyes, F. J. (2021). Seasonal forecasts of temperature and precipitation for Europe: Skill and applications. Climate Dynamics, 56(7–8), 2127– 2145. https://doi.org/10.1007/s00382-021-05895-6
• 20. Alessandri, A., Catalano, F., De Felice, M., van den Hurk, B. J. J. M., Doblas-Reyes, F. J., Boussetta, S., & Cheruy, F. (2018). Multi-scale enhancement of climate prediction over land by increasing the model sensitivity to vegetation variability. Climate Dynamics, 50(7–8), 2059–2082. https://doi.org/10.1007/s00382-018-4404-z