Development of a Hybrid Model for Rainfall Forecasting in Northeastern Thailand: Integration of Seasonal Autoregressive Integrated Moving Average, Support Vector Regression, and Variational Mode Decomposition
Article Sidebar
Main Article Content
Abstract
This study presents a hybrid model integrating Seasonal Autoregressive Integrated Moving Average (SARIMA), Ensemble Variational Mode Decomposition (EVMD), and Support Vector Regression (SVR) to improve monthly rainfall forecasting in Northeastern Thailand. The approach addresses the challenges posed by the non-stationary and nonlinear nature of rainfall data. SARIMA is first applied to extract linear components, while EVMD is used to decompose residuals into Intrinsic Mode Functions (IMFs). Each IMF and the remaining residuals are forecasted using SVR. A dataset comprising 496 months of rainfall records (January 1983 to April 2024) from 12 meteorological stations under the Thai Meteorological Department was used. Model performance was evaluated using five statistical metrics: RMSE, PRMSE, RPD, MAE, and R². The hybrid SARIMA-EVMD-SVR model consistently outperformed SARIMA and SVR standalone models, achieving R² values above 0.84 and RPD values greater than 2.5 in most stations. The hybrid model improved forecasting accuracy by up to 39.26% over SVR and 36.11% over SARIMA. The results highlight the model’s ability to effectively capture complex rainfall dynamics. Its adaptability offers potential for application in other time series forecasting tasks, contributing to enhanced decision-making in water resource planning and climate-related policy development.
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
Copyright Transfer Statement
The copyright of this article is transferred to Current Applied Science and Technology journal with effect if and when the article is accepted for publication. The copyright transfer covers the exclusive right to reproduce and distribute the article, including reprints, translations, photographic reproductions, electronic form (offline, online) or any other reproductions of similar nature.
The author warrants that this contribution is original and that he/she has full power to make this grant. The author signs for and accepts responsibility for releasing this material on behalf of any and all co-authors.
Here is the link for download: Copyright transfer form.pdf
References
Abebe, W. T., & Endalie, D. (2023). Artificial intelligence models for prediction of monthly rainfall without climatic data for meteorological stations in Ethiopia. Journal of Big Data, 10(1), Article 2. https://doi.org/10.1186/s40537-022-00683-3
Akhtar, M., Shatat, A. S. A., Ahamad, S. A. H., Dilshad, S., & Samdani, F. (2023). Optimized cascaded CNN for intelligent rainfall prediction model: A research towards statistic-based machine learning. Theoretical Issues in Ergonomics Science, 24(5), 564-592. https://doi.org/10.1080/1463922X.2022.2135786
Ali, M., Prasad, R., Xiang, Y., & Yaseen, Z. M. (2020). Complete ensemble empirical mode decomposition hybridized with random forest and kernel ridge regression model for monthly rainfall forecasts. Journal of Hydrology, 584, Article 124647. https://doi.org/10.1016/j.jhydrol.2020.124647
Alqahtani, F., Abotaleb, M., Subhi, A. A., El-Kenawy, E.-S. M., Abdelhamid, A. A., Alakkari, K., Badr, A., Al-Mahdawi, H. K., Ibrahim, A., & Kadi, A. (2023). A hybrid deep learning model for rainfall in the wetlands of southern Iraq. Modeling Earth Systems and Environment, 9(4), 4295-4312. https://doi.org/10.1007/s40808-023-01754-x
Ayiah-Mensah, F., Bosson-Amedenu, S., Baah, E. M., & Addor, J. A. (2025). Advancements in seasonal rainfall forecasting: A seasonal auto-regressive integrated moving average model with outlier adjustments for Ghana’s Western Region. Scientific African, 28, Article e02632. https://doi.org/10.1016/j.sciaf.2025.e02632
Chen, W., Xu, H., Chen, Z., & Jiang, M. (2021). A novel method for time series prediction based on error decomposition and nonlinear combination of forecasters. Neurocomputing, 426, 85-103. https://doi.org/10.1016/j.neucom.2020.10.048
Dotse, S.-Q., Larbi, I., Limantol, A. M., & De Silva, L. C. (2024). A review of the application of hybrid machine learning models to improve rainfall prediction. Modeling Earth Systems and Environment, 10(1), 19-44. https://doi.org/10.1007/s40808-023-01835-x
Dragomiretskiy, K., & Zosso, D. (2014). Variational mode decomposition. IEEE Transactions on Signal Processing, 62(3), 531-544. https://doi.org/10.1109/TSP.2013.2288675
Guo, S., Sun, S., Zhang, X., Chen, H., & Li, H. (2023). Monthly precipitation prediction based on the EMD–VMD–LSTM coupled model. Water Supply, 23(11), 4742-4758. https://doi.org/10.2166/ws.2023.275
He, R., Zhang, L., & Chew, A. W. Z. (2022). Modeling and predicting rainfall time series using seasonal-trend decomposition and machine learning. Knowledge-Based Systems, 251, Article 109125. https://doi.org/10.1016/j.knosys.2022.109125
He, R., Zhang, L., & Chew, A. W. Z. (2024). Data-driven multi-step prediction and analysis of monthly rainfall using explainable deep learning. Expert Systems with Applications, 235, Article 121160. https://doi.org/10.1016/j.eswa.2023.121160
He, Z., & Huang, J. (2023). A novel non-ferrous metal price hybrid forecasting model based on data preprocessing and error correction. Resources Policy, 86, Article 104189. https://doi.org/10.1016/j.resourpol.2023.104189
Hou, S., Geng, Q., Huang, Y., & Bian, Z. (2024). Rainfall prediction model based on CEEMDAN-VMD-BiLSTM network. Water, Air, and Soil Pollution, 235(8), Article 482. https://doi.org/10.1007/s11270-024-07299-8
Jamei, M., Ali, M., Malik, A., Karbasi, M., Rai, P., & Yaseen, Z. M. (2023). Development of a TVF-EMD-based multi-decomposition technique integrated with Encoder-Decoder-Bidirectional-LSTM for monthly rainfall forecasting. Journal of Hydrology, 617, Article 129105. https://doi.org/10.1016/j.jhydrol.2023.129105
Jiang, X. (2023). A combined monthly precipitation prediction method based on CEEMD and improved LSTM. PLOS ONE, 18(7), Article e0288211. https://doi.org/10.1371/journal.pone.0288211
Johny, K., Pai, M. L., & S., A. (2022). A multivariate EMD-LSTM model aided with Time dependent intrinsic cross-correlation for monthly rainfall prediction. Applied Soft Computing, 123, Article 108941. https://doi.org/10.1016/j.asoc.2022.108941
Mehr, A. D., Shadkani, S., Abualigah, L., Safari, M. J. S., & Migdady, H. (2024). A novel stabilized artificial neural network model enhanced by variational mode decomposing. Heliyon, 10(13), Article e34142. https://doi.org/10.1016/j.heliyon.2024.e34142
Parsaie, A., Ghasemlounia, R., Gharehbaghi, A., Haghiabi, A., Chadee, A. A., & Nou, M. R. G. (2024). Novel hybrid intelligence predictive model based on successive variational mode decomposition algorithm for monthly runoff series. Journal of Hydrology, 634, Article 131041. https://doi.org/10.1016/j.jhydrol.2024.131041
Parviz, L., & Ghorbanpour, M. (2024). A hybrid EMD and MODWT models for monthly precipitation forecasting using an innovative error decomposition method. Stochastic Environmental Research and Risk Assessment, 38(10), 4107-4130. https://doi.org/10.1007/s00477-024-02797-x
Parviz, L., Rasouli, K., & Torabi Haghighi, A. (2023). Improving hybrid models for precipitation forecasting by combining nonlinear machine learning methods. Water Resources Management, 37(10), 3833-3855. https://doi.org/10.1007/s11269-023-03528-7
Pinheiro, E., & Ouarda, T. B. M. J. (2023). Short-lead seasonal precipitation forecast in northeastern Brazil using an ensemble of artificial neural networks. Scientific Reports, 13(1), Article 20429. https://doi.org/10.1038/s41598-023-47841-y
Pirone, D., Cimorelli, L., Del Giudice, G., & Pianese, D. (2023). Short-term rainfall forecasting using cumulative precipitation fields from station data: A probabilistic machine learning approach. Journal of Hydrology, 617, Article 128949. https://doi.org/10.1016/j.jhydrol.2022.128949
Rezaiy, R., & Shabri, A. (2024). Improving drought prediction accuracy: A hybrid EEMD and support vector machine approach with standardized precipitation index. Water Resources Management, 38(13), 5255-5277. https://doi.org/10.1007/s11269-024-03912-x
Shao, P., Feng, J., Zhang, P., & Lu, J. (2024). Interpretable spatial-temporal attention convolutional network for rainfall forecasting. Computers and Geosciences, 185, Article 105535. https://doi.org/10.1016/j.cageo.2024.105535
Skarlatos, K., Bekri, E. S., Georgakellos, D., Economou, P., & Bersimis, S. (2023). Projecting Annual Rainfall Timeseries Using Machine Learning Techniques. Energies, 16(3), Article 1459. https://doi.org/10.3390/en16031459
Someetheram, V., Marsani, M. F., Kasihmuddin, M. S. M., Jamaludin, S. Z. M., Mansor, Mohd. A., & Zamri, N. E. (2025). Hybrid double ensemble empirical mode decomposition and K-Nearest Neighbors model with improved particle swarm optimization for water level forecasting. Alexandria Engineering Journal, 115, 423-433. https://doi.org/10.1016/j.aej.2024.12.035
Sutthison, T. (2024). Forecasting Thai durian exports using a hybrid time series SARIMA-SVR approach. Suranaree Journal of Science and Technology, 31(5), 030229(1-13).
Wang, H., Chen, S., & Zhai, W. (2024a). Variational generalized nonlinear mode decomposition: Algorithm and applications. Mechanical Systems and Signal Processing, 206, Article 110913. https://doi.org/10.1016/j.ymssp.2023.110913
Wang, S., Cao, B., Bai, R., & Liu, G. (2024b). Optimization of waterproofing and drainage measures for open-pit mines based on seasonal rainfall time series prediction. Environmental Modelling and Software, 173, Article 105957. https://doi.org/10.1016/j.envsoft.2024.105957
Wang, Y., Yuan, Z., Liu, H., Xing, Z., Ji, Y., Li, H., Fu, Q., & Mo, C. (2022). A new scheme for probabilistic forecasting with an ensemble model based on CEEMDAN and AM-MCMC and its application in precipitation forecasting. Expert Systems with Applications, 187, Article 115872. https://doi.org/10.1016/j.eswa.2021.115872
Waqas, M., Humphries, U. W., Hlaing, P. T., Wangwongchai, A., & Dechpichai, P. (2024). Advancements in daily precipitation forecasting: A deep dive into daily precipitation forecasting hybrid methods in the tropical climate of Thailand. MethodsX, 12, Article 102757. https://doi.org/10.1016/j.mex.2024.102757
Wu, H., Du, P., & Heng, J. (2024a). Gated convolution with attention mechanism under variational mode decomposition for daily rainfall forecasting. Measurement, 237, Article 115222. https://doi.org/10.1016/j.measurement.2024.115222
Wu, S., Dong, Z., Guzmán, S. M., Conde, G., Wang, W., Zhu, S., Shao, Y., & Meng, J. (2024b). Two-step hybrid model for monthly runoff prediction utilizing integrated machine learning algorithms and dual signal decompositions. Ecological Informatics, 84, Article 102914. https://doi.org/10.1016/j.ecoinf.2024.102914
Xiang, Y., Gou, L., He, L., Xia, S., & Wang, W. (2018). A SVR–ANN combined model based on ensemble EMD for rainfall prediction. Applied Soft Computing, 73, 874-883. https://doi.org/10.1016/j.asoc.2018.09.018
Xu, B., Zhou, F., Li, H., Yan, B., & Liu, Y. (2019). Early fault feature extraction of bearings based on Teager energy operator and optimal VMD. ISA Transactions, 86, 249-265. https://doi.org/10.1016/j.isatra.2018.11.010
Yin, Y., He, J., Guo, J., Song, W., Zheng, H., & Dan, J. (2024). Enhancing precipitation estimation accuracy: An evaluation of traditional and machine learning approaches in rainfall predictions. Journal of Atmospheric and Solar-Terrestrial Physics, 255, Article 106175. https://doi.org/10.1016/j.jastp.2024.106175
Zhang, X., & Wu, X. (2023). Combined forecasting model of precipitation based on the CEEMD-ELM-FFOA coupling model. Water, 15(8), Article 1485. https://doi.org/10.3390/w15081485
Zheng, Z., Zhang, X., Yin, Q., Liu, F., Ren, H., & Zhao, R. (2024). A novel optimization rainfall coupling model based on stepwise decomposition technique. Scientific Reports, 14(1), Article 15617. https://doi.org/10.1038/s41598-024-66663-0
Zhou, Z., Ren, J., He, X., & Liu, S. (2021). A comparative study of extensive machine learning models for predicting long‐term monthly rainfall with an ensemble of climatic and meteorological predictors. Hydrological Processes, 35(11), Article e14424. https://doi.org/10.1002/hyp.14424
Zuo, G., Luo, J., Wang, N., Lian, Y., & He, X. (2020). Decomposition ensemble model based on variational mode decomposition and long short-term memory for streamflow forecasting. Journal of Hydrology, 585, Article 124776. https://doi.org/10.1016/j.jhydrol.2020.124776
