Feature Engineering for Tropical Rainfall Forecasting Using Random Forest and Support Vector Regression

Cepy Slamet, Rizka M Imron, Agung Wahana, Dian Sa'adillah Maylawati, Wildan Budiawan Zulfikar, Muhammad Ali Ramdhani
Pages 715-728
Abstract Views 866
PDF Downloads 585
Crossref Citations -
DOI https://doi.org/10.47738/jads.v7i1.1111

Abstract


The complex dynamics of weather variability in Indonesia, influenced by multiple climatic drivers, make rainfall forecasting in tropical regions a significant scientific challenge. This study proposes an automated feature engineering pipeline to enhance the performance of Random Forest Regression (RFR) and Support Vector Regression (SVR) models for tropical rainfall prediction. Monthly rainfall data spanning 388 months (1993–2025) from a BMKG station were used as the basis for model development. The pipeline systematically generates temporal, seasonal, statistical, and anomaly-based features to provide domain-informed representations for non-sequential learning algorithms. Model performance was evaluated under four temporal data partitioning scenarios using R², RMSE, and probabilistic confidence intervals derived from bootstrap residual simulations. Results indicate that RFR achieved the highest predictive accuracy (R² = 0.93; RMSE = 31.01 mm) and demonstrated superior temporal–seasonal stability (Rolling CV: R² = 0.81 ± 0.07; RMSE = 55.44 ± 16.18), with comparable performance between wet and dry seasons. Conversely, SVR showed greater sensitivity to seasonal variability, with R² dropping to 0.55 during the wet season, indicating higher uncertainty under extreme rainfall conditions. Robustness and drift analyses further revealed that RFR adapts better to temporal and seasonal shifts, while SVR remains relevant as an adaptive model for extreme risk analysis. Overall, this study contributes to the development of automated feature engineering, reproducible climatological forecasting pipelines, and probabilistic modeling frameworks for rainfall prediction under uncertainty in tropical regions.

Keywords


Feature Engineering; Probabilistic Modeling; Rainfall Forecasting; Random Forest Regression; Support Vector Regression; Tropical Climate

Full Text:

PDF

References


F. Simanjuntak, I. Jamaluddin, T.-H. Lin, H. A. W. Siahaan, and Y.-N. Chen, “Rainfall Forecast Using Machine Learning with High Spatiotemporal Satellite Imagery Every 10 Minutes,” Remote Sens (Basel), vol. 14, no. 23, p. 5950, Nov. 2022, doi: 10.3390/rs14235950.

A. J. Hill and R. S. Schumacher, “Forecasting Excessive Rainfall with Random Forests and a Deterministic Convection-Allowing Model,” Weather Forecast, vol. 36, no. 5, pp. 1693–1711, Oct. 2021, doi: 10.1175/WAF-D-21-0026.1.

X. Zhao et al., “A Comprehensive Review of Methods for Hydrological Forecasting Based on Deep Learning,” May 01, 2024, Multidisciplinary Digital Publishing Institute (MDPI). doi: 10.3390/w16101407.

E. Yanfatriani et al., “Extreme Rainfall Trends and Hydrometeorological Disasters in Tropical Regions: Implications for Climate Resilience,” Emerging Science Journal, vol. 8, no. 5, pp. 1860–1874, 2024, doi: 10.28991/ESJ-2024-08-05-012.

R. Ramadhan et al., “Trends in rainfall and hydrometeorological disasters in new capital city of Indonesia from long-term satellite-based precipitation products,” Remote Sens Appl, vol. 28, p. 100827, Nov. 2022, doi: 10.1016/j.rsase.2022.100827.

E. Hermawan et al., “Large-Scale Meteorological Drivers of the Extreme Precipitation Event and Devastating Floods of Early-February 2021 in Semarang, Central Java, Indonesia,” Atmosphere (Basel), vol. 13, no. 7, p. 1092, Jul. 2022, doi: 10.3390/atmos13071092.

H. Shen, B. A. Tolson, and J. Mai, “Time to Update the Split-Sample Approach in Hydrological Model Calibration,” Water Resour Res, vol. 58, no. 3, Mar. 2022, doi: 10.1029/2021WR031523.

P. O. Bojang, T. C. Yang, Q. B. Pham, and P. S. Yu, “Linking singular spectrum analysis and machine learning for monthly rainfall forecasting,” Applied Sciences (Switzerland), vol. 10, no. 9, May 2020, doi: 10.3390/app10093224.

O. Ejike, D. Ndzi, and M. Z. Shakir, “Comparative Study of Machine Learning-Based Rainfall Prediction in Tropical and Temperate Climates,” Climate, vol. 13, no. 8, Aug. 2025, doi: 10.3390/cli13080167.

L. T. Pham, L. Luo, and A. Finley, “Evaluation of random forests for short-term daily streamflow forecasting in rainfall- And snowmelt-driven watersheds,” Hydrol Earth Syst Sci, vol. 25, no. 6, pp. 2997–3015, Jun. 2021, doi: 10.5194/hess-25-2997-2021.

B. Goehry, H. Yan, Y. Goude, P. Massart, and J. M. Poggi, “Random Forests for Time Series,” REVSTAT-Statistical Journal, vol. 21, no. 2, pp. 283–302, 2023, doi: 10.57805/revstat.v21i2.400.

P. Gajewski, B. Čule, and N. Rankovic, “Unveiling the Power of ARIMA, Support Vector and Random Forest Regressors for the Future of the Dutch Employment Market,” Journal of Theoretical and Applied Electronic Commerce Research, vol. 18, no. 3, pp. 1365–1403, 2023, doi: 10.3390/jtaer18030069.

S. Hia, H. Kuswanto, and D. D. Prasetyo, “Robustness of Support Vector Regression and Random Forest Models: A Simulation Study,” in Data Science and Emerging Technologies (DataSET 2022), Springer, Singapore, 2023, pp. 465–479. doi: https://doi.org/10.1007/978-981-99-0741-0_33.

S. Bhoopathi, K. Sumanth, L. Akanksha, and L. Pal, “Evaluating the Performance of ANN, SVR, RF, and XGBoost in the Prediction of Maximum Temperature and Heat Wave Days over Rajasthan, India,” J Hydrol Eng, vol. 29, no. 6, 2024, doi: https://doi.org/10.1061/JHYEFF.HEENG-6243.

M. Abbasi, A. Farokhnia, M. Bahreinimotlagh, and R. Roozbahani, “A hybrid of Random Forest and Deep Auto-Encoder with support vector regression methods for accuracy improvement and uncertainty reduction of long-term streamflow prediction,” J Hydrol (Amst), vol. 597, 2021, doi: https://doi.org/10.1016/j.jhydrol.2020.125717.

P. Cihan, “Comparative Performance Analysis of Deep Learning, Classical, and Hybrid Time Series Models in Ecological Footprint Forecasting,” Applied Sciences (Switzerland), vol. 14, no. 4, Feb. 2024, doi: 10.3390/app14041479.

M. A. Saleh, H. M. Rasel, and B. Ray, “A comprehensive review towards resilient rainfall forecasting models using artificial intelligence techniques,” Green Technologies and Sustainability, vol. 2, no. 3, Sep. 2024, doi: 10.1016/j.grets.2024.100104.

F. R. Aderyani, S. Jamshid Mousavi, and F. Jafari, “Short-term rainfall forecasting using machine learning-based approaches of PSO-SVR, LSTM and CNN,” J Hydrol (Amst), vol. 614, no. 128463, Nov. 2022, doi: 10.1016/j.jhydrol.2022.128463.

D. Li et al., “Prediction of Rainfall Time Series Using the Hybrid DWT-SVR-Prophet Model,” Water (Switzerland), vol. 15, no. 10, May 2023, doi: 10.3390/w15101935.

M. Čistý, M. Danko, S. Kohnová, B. Považanová, and A. Trizna, “Machine Learning Enhanced by Feature Engineering for Estimating Snow Water Equivalent,” Water (Switzerland), vol. 16, no. 16, Aug. 2024, doi: 10.3390/w16162285.

W. Fang et al., “An evaluation of random forest based input variable selection methods for one month ahead streamflow forecasting,” Sci Rep, vol. 14, no. 1, Dec. 2024, doi: 10.1038/s41598-024-81502-y.

J. H. Stagge, D. E. Rosenberg, A. M. Castronova, A. Ostfeld, and A. S. Jones, “Journal of Water Resources Planning and Management’s Reproducibility Review Program: Accomplishments, Lessons, and Next Steps,” J Water Resour Plan Manag, vol. 150, no. 8, Aug. 2024, doi: 10.1061/JWRMD5.WRENG-6559.

C. R. Corona and T. S. Hogue, “Machine learning in stream and river water temperature modeling: a review and metrics for evaluation,” Hydrol Earth Syst Sci, vol. 29, no. 12, pp. 2521–2549, Jun. 2025, doi: 10.5194/hess-29-2521-2025.

R. A. Collenteur et al., “Data-driven modelling of hydraulic-head time series: results and lessons learned from the 2022 Groundwater Time Series Modelling Challenge,” Hydrol Earth Syst Sci, vol. 28, no. 23, pp. 5193–5208, Dec. 2024, doi: 10.5194/hess-28-5193-2024.

Y. Cai et al., “Predicting Tropical Cyclone Extreme Rainfall in Guangxi, China: An Interpretable Machine Learning Framework Addressing Class Imbalance and Feature Optimization,” Meteorological Applications, vol. 32, no. 3, May 2025, doi: 10.1002/met.70052.

B. J. Kim, M. Kim, J. Yoo, and B. Kim, “Rapid simulation for real-time flood depth prediction using support vector machine,” Sci Rep, vol. 15, no. 1, Dec. 2025, doi: 10.1038/s41598-025-17090-2.

A. Kumar et al., “World Meteorological Organization (WMO)-Accredited Infrastructure to Support Operational Climate Prediction,” Bull Am Meteorol Soc, vol. 105, no. 11, pp. E2126–E2143, Nov. 2024, doi: 10.1175/BAMS-D-23-0284.1.

V. Plotnikova, M. Dumas, and F. P. Milani, “Applying the CRISP-DM data mining process in the financial services industry: Elicitation of adaptation requirements,” Data Knowl Eng, vol. 139, p. 102013, May 2022, doi: 10.1016/j.datak.2022.102013.

J. A. Solano, D. J. Lancheros Cuesta, S. F. Umaña Ibáñez, and J. R. Coronado-Hernández, “Predictive models assessment based on CRISP-DM methodology for students performance in Colombia - Saber 11 Test,” Procedia Comput Sci, vol. 198, pp. 512–517, 2022, doi: 10.1016/j.procs.2021.12.278.

U. Kannengiesser and J. S. Gero, “Modelling The Design Of Models: An Example Using CRISP-DM,” in Proceedings of the Design Society, Cambridge University Press, Jul. 2023, pp. 2705–2714. doi: 10.1017/pds.2023.271.

E. Valla, S. Nõmm, K. Medijainen, P. Taba, and A. Toomela, “Tremor-related feature engineering for machine learning based Parkinson’s disease diagnostics,” Biomed Signal Process Control, vol. 75, p. 103551, May 2022, doi: 10.1016/j.bspc.2022.103551.

M. S. Ahammed et al., “Hypertuning Random Forest for Enhancing Cyber Security in Industrial Power Electronics,” in 2024 27th International Conference on Computer and Information Technology (ICCIT), IEEE, Dec. 2024, pp. 2529–2533. doi: 10.1109/ICCIT64611.2024.11022494.

M. Loki, A. Mindila, and W. Cheruiyot, “Hyper‐Parameter Optimization of Kernel Functions on Multi‐Class Text Categorization: A Comparative Evaluation,” WIREs Data Mining and Knowledge Discovery, vol. 15, no. 1, Mar. 2025, doi: 10.1002/widm.1572.

S. Peng, W. Wang, Y. Chen, X. Zhong, and Q. Hu, “Regression-Based Hyperparameter Learning for Support Vector Machines,” IEEE Trans Neural Netw Learn Syst, vol. 35, no. 12, pp. 18799–18813, Dec. 2024, doi: 10.1109/TNNLS.2023.3321685.

Y.-G. Wang, J. Wu, Z.-H. Hu, and G. J. McLachlan, “A new algorithm for support vector regression with automatic selection of hyperparameters,” Pattern Recognit, vol. 133, p. 108989, Jan. 2023, doi: 10.1016/j.patcog.2022.108989.

Y. Okadome and Y. Nakamura, “Feature extraction method using lag operation for sub-grouped multidimensional time series data,” IEEE Access, vol. 12, pp. 98945–98959, Jul. 2024, doi: 10.1109/ACCESS.2024.3429529.

B. Lim and S. Zohren, “Time-series forecasting with deep learning: A survey,” Philosophical Transactions of the Royal Society A, vol. 379, no. 2194, Apr. 2021, doi: 10.1098/rsta.2020.0209.

K. Yi et al., “A Survey on Deep Learning based Time Series Analysis with Frequency Transformation,” in KDD ’25: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2, ACM Digital Library, Aug. 2025, pp. 6206–6215. doi: https://doi.org/10.1145/3711896.3736571.

D. Dimoudis, T. Vafeiadis, A. Nizamis, D. Ioannidis, and D. Tzovaras, “Utilizing an adaptive window rolling median methodology for time series anomaly detection,” in Procedia Computer Science, Elsevier B.V., 2022, pp. 584–593. doi: 10.1016/j.procs.2022.12.254.

K. Zhou, Z. Liu, Y. Qiao, T. Xiang, and C. C. Loy, “Domain Generalization: A Survey,” IEEE Trans Pattern Anal Mach Intell, vol. 45, no. 4, pp. 4396–4415, Apr. 2023, doi: 10.1109/TPAMI.2022.3195549.

M. Akrout, A. Feriani, F. Bellili, A. Mezghani, and E. Hossain, “Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issues,” IEEE Communications Surveys and Tutorials, vol. 25, no. 4, pp. 3014–3037, 2023, doi: 10.1109/COMST.2023.3326399.

M. Gu, Y. Lin, V. C. Lee, and D. Y. Qiu, “Probabilistic forecast of nonlinear dynamical systems with uncertainty quantification,” Physica D, vol. 457, Jan. 2024, doi: 10.1016/j.physd.2023.133938.




DOI: https://doi.org/10.47738/jads.v7i1.1111

Refbacks

  • There are currently no refbacks.


Barcode

Journal of Applied Data Sciences

ISSN:2723-6471 (Online)
Publisher:Bright Publisher
Website:http://bright-journal.org/JADS
Email:taqwa@amikompurwokerto.ac.id (principal contact)
  support@bright-journal.org (technical issues)

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0