Issue

Vol. 11, No. 3, August 2026 (Article in Progress)

Creative Commons License

This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

A Comparative Study of Hybrid GARCH–HOLT–BPNN Models for Rainfall Forecasting Using a MATLAB-Based Intelligent Computing System

https://doi.org/10.22219/kinetik.v11i3.2636
Supardi Supardi
Universitas Muhammadiyah Mataram
Syaharuddin Syaharuddin
Universitas Muhammadiyah Mataram
Vera Mandailina
Universitas Muhammadiyah Mataram
Saba Mehmood
University of Management and Technology

Corresponding Author(s) : Syaharuddin Syaharuddin

syaharuddin.ntb@gmail.com

Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, Vol. 11, No. 3, August 2026 (Article in Progress)

Abstract

Rainfall forecasting is a fundamental aspect of water resource management, hydrometeorological disaster mitigation, and agricultural planning, all of which are strongly influenced by climate variability. The complexity of rainfall data, characterized by non-linear, non-stationary, and highly fluctuating patterns, necessitates the use of adaptive and accurate predictive approaches. This study aims to conduct a comparative analysis of five forecasting models, namely the Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model, Holt’s Exponential Smoothing, Backpropagation Neural Network (BPNN), the hybrid GARCH–Holt model, and the advanced hybrid GARCH–Holt–BPNN model, in order to identify the most effective method for monthly rainfall forecasting. Rainfall data for the period 2015–2024 were used for model training and testing. Model performance was evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). In addition, this study incorporates the development of a MATLAB-based Graphical User Interface (GUI) to facilitate interactive model implementation and visualization of forecasting results. The results indicate that the GARCH model excels in capturing data volatility, Holt’s Exponential Smoothing effectively follows short-term trends with stability, and BPNN is capable of modeling non-linear relationships despite its sensitivity to data variability. The hybrid GARCH–Holt model demonstrates improved accuracy compared to single models. Furthermore, the hybrid GARCH–Holt–BPNN model achieves the most optimal performance, with an accuracy approaching 99% and the lowest MAPE value of 1.13%, reflecting excellent generalization capability. These findings confirm that the integration of linear and non-linear methods within a hybrid framework significantly enhances rainfall forecasting accuracy and contributes to data-driven decision-making in the field of hydrometeorology.

Keywords

Rainfall Forecasting Hybrid Models Generalized Autoregressive Conditional Heteroskedasticity Holt’s Exponential Smoothing Backpropagation Neural Network MATLAB GUI
Supardi, S., Syaharuddin, S., Mandailina, V. ., & Mehmood, S. (2026). A Comparative Study of Hybrid GARCH–HOLT–BPNN Models for Rainfall Forecasting Using a MATLAB-Based Intelligent Computing System. Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control, 11(3). https://doi.org/10.22219/kinetik.v11i3.2636
Download Citation
Endnote/Zotero/Mendeley (RIS)
BibTeX
References
  1. A. Alvarez-Mena, J. Sanchez-Monedero, and D. Perez-Aranda, “Hydrological forecasting for agricultural water management: A review,” Water Resour. Manag., vol. 33, no. 7, pp. 2411–2435, 2019, doi: 10.1007/s11269-019-02243-8.
  2. A. Mishra and V. P. Singh, “Hydrological forecasting: A review of techniques and applications,” Water Resour. Manag., vol. 35, no. 1, pp. 1–28, 2021.
  3. O. Kisi and J. Shiri, “Predicting hydrological time series using machine learning,” J. Hydrol., vol. 523, pp. 446–457, 2015, doi: 10.1016/j.jhydrol.2015.01.061.
  4. E. G. Dada, H. J. Yakubu, and D. O. Oyewola, “Artificial Neural Network Models for Rainfall Prediction,” Eur. J. Electr. Eng. Comput. Sci., vol. 5, no. 2, pp. 30–35, 2021, doi: 10.24018/ejece.2021.5.2.313.
  5. S. Nugroho, “Hydrometeorological disaster risk analysis in Southeast Asia,” Nat. Hazards, vol. 117, pp. 1121–1139, 2023, doi: 10.1007/s11069-023-05851-7.
  6. S. S. Sammen, O. Kisi, and M. Ehteram, “Rainfall modeling using two different neural networks improved by metaheuristic algorithms,” Environ. Sci. Eur., vol. 35, no., p. Article 112--, 2023, doi: 10.1186/s12302-023-00818-0.
  7. I. Ahmad and A. Hossain, “Time series forecasting using GARCH and its applications in environmental science,” Springer Nat., 2020.
  8. C. Hamzacebi and H. A. Es, “Modeling meteorological volatility using GARCH-family models,” Theor. Appl. Climatol., vol. 159, pp. 1123–1137, 2024, doi: 10.1007/s00704-023-04568-8.
  9. N. Drop and A. Bohdan, “Application of the Holt–Winters Model in the Forecasting of Passenger Traffic at Szczecin–Goleniów Airport (Poland),” Sustainability, vol. 17, no. 14, p. 6407, 2025, doi: 10.3390/su17146407.
  10. E. Purwaningrum and S. Purwanto, “Performance of Holt–Winters model for monthly rainfall forecasting,” J. Meteorol. dan Geofis., vol. 25, no. 1, pp. 35–46, 2024, doi: 10.31172/jmg.v25i1.1203.
  11. H. Simatupang, “Short-term rainfall prediction using Holt’s method,” J. Sains Atmos., vol. 45, no. 2, pp. 110–121, 2023, doi: 10.31227/jsa.v45i2.9988.
  12. I. P. Leksono, M. A. Purnomo, and A. Ramadhani, “Komparasi metode BPNN dan ARIMA dalam peramalan curah hujan,” J. Inform. J. Pengemb. IT, vol. 6, no. 3, pp. 195–201, 2021.
  13. A. Nuryanto, “Rainfall forecasting in Central Java using ANN,” IOP Conf. Ser. Earth Environ. Sci., vol. 540, p. 12019, 2020, doi: 10.1088/1755-1315/540/1/012019.
  14. F. M. Woldemeskel, “Evaluation of rainfall prediction using multilayer perceptron,” J. Hydrol. Eng., vol. 22, no. 3, p. 4017001, 2017, doi: 10.1061/(ASCE)HE.1943-5584.0001493.
  15. M. Yuan, “Neural network approaches in atmospheric time series prediction,” Environ. Model. Softw., vol. 172, p. 105820, 2025, doi: 10.1016/j.envsoft.2025.105820.
  16. Y. He, “Applications of neural networks in rainfall prediction,” Environ. Model. Softw., vol. 170, p. 105754, 2025, doi: 10.1016/j.envsoft.2025.105754.
  17. S. Samantaray, “Machine learning performance in climate prediction,” Atmos. Res., vol. 290, p. 106985, 2025, doi: 10.1016/j.atmosres.2024.106985.
  18. K. B. Gokul Krishnan, R. Mehta, and Solanki, “Statistical Modelling and Projection of Future Rainfall using SARIMA and Hybrid SARIMA‑GARCH Models in Various Zones of Kerala,” J. Indian Soc. Agric. Stat., vol. 78, no. 2, pp. 151–160, 2024, doi: 10.56093/jisas.v78i2.9.
  19. L. Ni et al., “Streamflow and rainfall forecasting by two long short-term memory-based models,” J. Hydrol., vol. 583, p. 124296, 2020, doi: https://doi.org/10.1016/j.jhydrol.2019.124296.
  20. Q. Zhao, Y. Liu, X. Ma, W. Yao, Y. Yao, and X. Li, “An Improved Rainfall Forecasting Model Based on GNSS Observations,” IEEE Trans. Geosci. Remote Sens., vol. 58, no. 7, pp. 4891–4900, 2020, doi: 10.1109/TGRS.2020.2968124.
  21. D. T. Bui, “A novel hybrid intelligent model for rainfall forecasting,” J. Hydrol., vol. 575, pp. 838–849, 2019, doi: 10.1016/j.jhydrol.2019.05.035.
  22. S. E. Debele, “Performance of machine learning models for rainfall prediction in data-sparse regions,” Atmos. Res., vol. 244, p. 105040, 2020, doi: 10.1016/j.atmosres.2020.105040.
  23. F. Yusof, I. L. Kane, and Z. Yusop, “Hybrid of ARIMA‑GARCH Modeling in Rainfall Time Series,” J. Teknol. (Sciences Eng., vol. 63, no. 2, pp. 27–34, 2013, doi: 10.11113/jt.v63.1908.
  24. N. A. Zamrus, M. H. Mohd Rodzhan, and N. N. Mohamad, “Forecasting Model of Air Pollution Index using Generalized Autoregressive Conditional Heteroskedasticity Family (GARCH),” Malaysian J. Fundam. Appl. Sci., vol. 18, no. 2, 2022, doi: 10.11113/mjfas.v18n2.2279.
  25. A. Afifah Nur Aini, P. K. Intan, and N. Ulinnuha, “Prediksi Rata-Rata Curah Hujan Bulanan di Pasuruan Menggunakan Metode Holt‑Winters Exponential Smoothing,” JRST (Jurnal Ris. Sains dan Teknol., vol. 5, no. 2, pp. 117–122, 2022.
  26. R. Aprianto, A. Tawaqqal, and P. A. D. Puspitasari, “Prediksi Curah Hujan Menggunakan Metode Holt‑Winters di Kabupaten Sumbawa,” Titian Ilmu J. Ilm. Multi Sci., vol. 17, no. 1, pp. 42–52, 2025, doi: 10.30599/eybf7238.
  27. M. A. F. I. Aslim, Jasruddin, P. Palloan, Helmi, M. Arsyad, and H. Triwibowo, “Monthly Rainfall Prediction Using the Backpropagation Neural Network (BPNN) Algorithm in Maros Regency,” Sci. J. Informatics, vol. 10, no. 1, pp. 13–24, 2023, doi: 10.15294/sji.v10i1.37982.
  28. B. A. Rizaldi, A. A. B. Perwita, J. Widjayanto, and M. A. Madjid, “Deep learning of backpropagation neural network algorithm for long‑term predicting rainfall in the Kapuas Hulu, West Kalimantan province of Indonesia,” J. Appl. Nat. Sci., vol. 17, no. 1, pp. 389–397, 2025, doi: 10.31018/jans.v17i1.6183.
  29. D. Karthika and K. Karthikeyan, “Performance of combined forecasting model for monthly rainfall precipitation,” Adv. Appl. Stat., 2023, doi: 10.17654/0972361723066.
  30. T. Saba, A. Rehman, and J. S. AlGhamdi, “Weather forecasting based on hybrid neural model,” Appl. Water Sci., vol. 7, pp. 3869–3874, 2017, doi: 10.1007/s13201-017-0538-0.
  31. N. N. Aini, A. Iriany, W. H. Nugroho, and F. L. Wibowo, “Comparison of adaptive Holt-Winters exponential smoothing and recurrent neural network model for forecasting rainfall in Malang City,” ComTech Comput. Math. Eng. Appl., vol. 13, no. 2, pp. 87–96, 2022, doi: 10.21512/comtech.v13i2.7570.
  32. W. Thupeng, R. Sivasamy, and O. A. Daman, “Rainfall series forecasting models by ARIMA, NN, and HOMM methods,” Adv. Appl. Stat., 2024, doi: 10.17654/0972361724007.
Read More
Author biographies is not available.
Download this PDF file
Statistic
Read Counter : 0

Downloads

Download data is not yet available.