Comparison of Rainfall Prediction Results in South Bangka Regency Using Support Vector Regression and SARIMA
##plugins.themes.bootstrap3.article.sidebar##
##plugins.themes.bootstrap3.article.main##
Abstract
Rainfall is one of the key climate variables. It plays an important role in the hydrological cycle. In the field of agriculture, it is crucial as it determines the availability of water for crops, helping farmers manage water scarcity issues. South Bangka is one of the districts with the highest rice production levels compared to other districts in the Bangka Belitung Islands Province. This study aims to predict the rainfall in South Bangka for the next four years, from January 2024 to December 2027, using the Support Vector Regression (SVR) and SARIMA methods. The results of this study indicate that the SVR method is the best for prediction compared to the SARIMA method, with an average MAPE value of 0.03%. The kernel used is the Radial Basis Function (RBF), with parameter values including epsilon (ԑ) of 0.0001, Cost (C) of 1000, and gamma (γ) of 235. The MAPE value for the training data is 0.045%, and for the test data, it is 0.015%. The best SARIMA model is (3,1,3)(1,1,3)24 with a MAPE value of 15.51%.
##plugins.themes.bootstrap3.article.details##
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Authors who publish articles in CoreID Journal agree to the following terms:
- Authors retain copyright of the article and grant the journal right of first publication with the work simultaneously licensed under a CC-BY-SA or The Creative Commons Attribution–ShareAlike License.
- 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 acknowledgment 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).
References
Z. Guo and G. Bai, “Application of Least Squares Support Vector Machine for Regression to Reliability Analysis,” Chinese Journal of Aeronautics, vol. 22, no. 2, pp. 160–166, Apr. 2009, doi: 10.1016/S1000-9361(08)60082-5.
F. Zhang and L. J. O’Donnell, “Support vector regression,” in Machine Learning: Methods and Applications to Brain Disorders, Elsevier, 2019, pp. 123–140. doi: 10.1016/B978-0-12-815739-8.00007-9.
M. Sabzekar and S. M. H. Hasheminejad, “Robust regression using support vector regressions,” Chaos Solitons Fractals, vol. 144, Mar. 2021, doi: 10.1016/j.chaos.2021.110738.
M. Awad and R. Khanna, “Support vector regression,” in Efficient learning machines: Theories, concepts, and applications for engineers and system designers, Springer, 2015, pp. 67–80.
Y. Ding, L. Cheng, W. Pedrycz, and K. Hao, “Global nonlinear kernel prediction for large data set with a particle swarm-optimized interval support vector regression,” IEEE Trans Neural Netw Learn Syst, vol. 26, no. 10, pp. 2521–2534, 2015.
Z. Zhong and T. R. Carr, “Application of mixed kernels function (MKF) based support vector regression model (SVR) for CO2 – Reservoir oil minimum miscibility pressure prediction,” Fuel, vol. 184, pp. 590–603, Nov. 2016, doi: 10.1016/j.fuel.2016.07.030.
A. A. Akinpelu et al., “A support vector regression model for the prediction of total polyaromatic hydrocarbons in soil: an artificial intelligent system for mapping environmental pollution,” Neural Comput Appl, vol. 32, no. 18, pp. 14899–14908, Sep. 2020, doi: 10.1007/s00521-020-04845-3.
R. E. Caraka, S. A. Bakar, and M. Tahmid, “Rainfall forecasting multi kernel support vector regression seasonal autoregressive integrated moving average (MKSVR-SARIMA),” in AIP Conference Proceedings, American Institute of Physics Inc., Jun. 2019. doi: 10.1063/1.5111221.
P. Aghelpour, B. Mohammadi, and S. M. Biazar, “Long-term monthly average temperature forecasting in some climate types of Iran, using the models SARIMA, SVR, and SVR-FA,” Theor Appl Climatol, vol. 138, no. 3–4, pp. 1471–1480, Nov. 2019, doi: 10.1007/s00704-019-02905-w.
L. Parviz and M. Ghorbanpour, “Assimilation of PSO and SVR into an improved ARIMA model for monthly precipitation forecasting,” Sci Rep, vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-63046-3.
P. F. Pai, K. P. Lin, C. S. Lin, and P. T. Chang, “Time series forecasting by a seasonal support vector regression model,” Expert Syst Appl, vol. 37, no. 6, pp. 4261–4265, Jun. 2010, doi: 10.1016/j.eswa.2009.11.076.
A. Danandeh Mehr, V. Nourani, V. Karimi Khosrowshahi, and M. A. Ghorbani, “A hybrid support vector regression–firefly model for monthly rainfall forecasting,” International Journal of Environmental Science and Technology, vol. 16, no. 1, pp. 335–346, Jan. 2019, doi: 10.1007/s13762-018-1674-2.
A. Kumar Dubey, A. Kumar, V. García-Díaz, A. Kumar Sharma, and K. Kanhaiya, “Study and analysis of SARIMA and LSTM in forecasting time series data,” Sustainable Energy Technologies and Assessments, vol. 47, Oct. 2021, doi: 10.1016/j.seta.2021.101474.
BPS-Statistics of Bangka Selatan Regency. “Bangka Selatan Regency in Figure 2024. Volume 22, 2024.
H. Yang, Z. Wang, and K. Song, “A new hybrid grey wolf optimizer-feature weighted-multiple kernel-support vector regression technique to predict TBM performance,” Eng Comput, pp. 1–17, 2022.