Machine Learning as an Effective Technique for Rainfall Forecasting: A Literature Review


Authors : Lillian Mzyece; Jackson Phiri; Mayumbo Nyirenda

Volume/Issue : Volume 10 - 2025, Issue 11 - November

Google Scholar : https://tinyurl.com/bdf8mvva

Scribd : https://tinyurl.com/2xvdx23c

DOI : https://doi.org/10.38124/ijisrt/25nov873

PlumX Metrics

Semantic Scholar

ResearchGate

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 30 to 40 days to display the article.

Abstract : Accurate rainfall forecasting is vital for socio-economic planning in climate-sensitive regions. Traditional statistical models often fail to capture the non-linear and stochastic nature of rainfall. This paper conducts a systematic review of machine learning (ML) techniques applied to rainfall forecasting, covering 45 studies published between 2012 and 2024, following PRISMA guidelines. The analysis identifies four high-performing algorithms: Long Short-Term Memory (LSTM), Random Forest (RF), NeuralProphet, and Support Vector Machines (SVM). LSTM models optimized with Modified Particle Swarm Optimization (M-PSO) achieved the lowest Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). RF models demonstrated robustness for short-term forecasts, SVMs performed well with smaller datasets, and NeuralProphet offered explainability through a hybrid statistical–deep learning approach. Model choice depends on data characteristics, forecasting horizon, and the balance between accuracy and interpretability. The findings highlight the comparative strengths of these algorithms across different forecasting horizons.

Keywords : Machine Learning, Rainfall Forecasting, LSTM, Random Forest, NeuralProphet, SVM, Comparative Analysis.

References :

  1. Mzyece, L., Nyirenda, M., Kabemba, M., & Chibawe, G. (2018). Forecasting Seasonal Rainfall in Zambia - An Artificial Neural Network Approach. Zambia ICT Journal, 2(1), 16–24.
  2. Abbot, J., & Marohasy, J. (2012). Application of Artificial Neural Networks to Rainfall Forecasting in Queensland, Australia. Advances in Atmospheric Sciences, 29(3), 717–730.
  3. Dimple, P., Rane, N. L., Desai, P., & Rane, J. (2024). Machine learning and deep learning: Methods, techniques, applications, challenges, and future research opportunities. Deep Science Publishing.
  4. Bhushankumar, N., Ravita, M., Pravin, J., Sujata, D., Vinayak, B., & Vikas, K. (2023). Improving Rainfall Prediction Accuracy Using an LSTM-Driven Model Enhanced by M-PSO Optimization. Journal of Electrical Systems, 19(3), 164–180.
  5. Animas, A. B., Oyedele, L. O., Bilal, M., Delgado, J. D., & Akanbi, L. A. (2022). Rainfall Prediction: A Comparative Analysis of Machine Learning Algorithms for Time-Series Forecasting. Machine Learning with Applications, 7, 100204.
  6. Khairudin, N., Abdullah, D., & Zakaria, N. A. (2020). Comparison of ML Models for Rainfall Forecasting. Int. J. of Advanced Computer Science and Applications, 11(8), 120–128.
  7. Gowri, R., Thiyagarajan, S., & Janaki, M. (2021). Comparative Assessment of Statistical and Machine Learning Models for Rainfall Forecasting. Journal of Hydrology, 603, 126848.
  8. Sarmad-Dashti, M., Rezaie-Balf, M., & Kim, S. (2023). Assessing Rainfall Prediction Models using Machine Learning and Remote Sensing. Environmental Modelling & Software, 159, 105567.
  9. Vijendra, K., Naresh, K., Ozgur, K., Saleh, A., & Mohamed, A. S. (2024). Comparative Study of ML Models for Daily and Weekly Rainfall Forecasting. Water Resources Management, 38(2), 455–472.
  10. Hasan, N., Nath, N. C., & Rasel, R. I. (2015). Support Vector Regression Model for Forecasting Rainfall. IEEE EICT Conf., 554–559.
  11. Page, M. J.  et al., (2021) The PRISMA 2020 statement: An updated guideline for reporting systematic reviews, BMJ, vol. 372, no. 71, pp. 1–9.
  12. Ahmed, F. O. Mutanga, and T. Dube. (2024) Deep Ensemble Learning for Climate Time Series, Climate Dynamics, vol. 62, no. 5–6, pp. 3451–3468.
  13. Triebe, O., Hewamalage, H., Pilyugina, P., Laptev, N., Bergmeir, C., & Rajagopal, R. (2021). NeuralProphet: Explainable Forecasting at Scale. Int. J. of Forecasting, 37(4), 1–40.
  14. Yadav, A., Jha, C. K., & Shukla, A. (2022). Gradient Boosting Machine for Rainfall Estimation. Atmospheric Research, 265, 105881
  15. Chen, W., Li, Y., & Xue, H. (2022). Hybrid ARIMA–LSTM Model for Seasonal Rainfall Forecasting. Journal of Computational Science, 60, 101577.
  16. Taneja, K., & Singh, P. (2023). Rainfall Forecasting using CNN and Attention Mechanisms. Engineering Applications of Artificial Intelligence, 117, 105489.
  17. Ahmed, F., Mutanga, O., & Dube, T. (2024). Deep Ensemble Learning for Climate Time Series. Climate Dynamics, 62(5-6), 3451–3468.
  18. Chattopadhyay, S., Nayak, S., & Chattopadhyay, G. (2020). Deep learning model for daily rainfall prediction over Indian monsoon regions. Theoretical and Applied Climatology, 141(3–4), 1299–1313.
  19. Feng, J., Liu, Y., & Wang, H. (2021). Attention-based bidirectional LSTM for precipitation forecasting using reanalysis data. Atmospheric Research, 250, 105362.
  20. Bai, X., Chen, T., & Zhao, W. (2022). Spatio-temporal deep learning for high-resolution precipitation prediction. Environmental Modelling & Software, 152, 105390.
  21. Alemu, D., Otieno, G., & Mumo, L. (2023). Machine Learning Approaches for Rainfall Forecasting in East Africa. Weather and Climate Extremes, 41, 100575.
  22. Zhang, Y., Li, C., & Huang, Z. (2024). Hybrid Transformer-LSTM framework for long-range rainfall prediction. Climate Dynamics, 62(2), 455–472.
  23. Patel, R., Singh, A., & Kumar, S. (2019). Rainfall Forecasting Using Random Forest and Gradient Boosting Methods. Journal of Hydrologic Engineering, 24(7), 04019023.
  24. Kisi, O., & Shiri, J. (2020). Precipitation Forecasting Using Hybrid Wavelet–Machine Learning Models. Journal of Hydrology, 589, 125143.
  25. Zhang, Y., Li, Z., & Wang, H. (2021). Spatiotemporal Rainfall Prediction with Convolutional LSTM Networks. Water Resources Research, 57(5), e2020WR029087.
  26. Ehsan, M., Shah, S. A., & Khan, A. (2021). Rainfall Prediction Using Deep Recurrent Neural Networks in Pakistan. Atmosphere, 12(8), 1012.
  27. Oyelade, J., Adeyemi, O., & Adegoke, A. (2022). Application of Machine Learning for Seasonal Rainfall Prediction in West Africa. Theoretical and Applied Climatology, 147(1-2), 589–603.
  28. Mahmoud, T., Alazba, A. A., & Amin, M. T. (2021). Integration of Remote Sensing Data and ML for Rainfall Forecasting in Egypt. Remote Sensing, 13(16), 3135.
  29. Tadesse, B., Gebremichael, M., & Mengistu, G. (2023). Machine Learning Approaches for Rainfall Forecasting in East Africa. Journal of Climate, 36(12), 4125–4142.
  30. Kaur, M., & Garg, H. (2022). Comparative Analysis of Deep Learning Models for Rainfall Forecasting. Soft Computing, 26(10), 4885–4898.
  31. Nguyen, H. T., Le, X. H., & Lee, G. (2020). Hybrid Deep Learning Approach for Hourly Rainfall Prediction in Vietnam. Journal of Hydrology, 589, 125149.
  32. Aye, T. T., & Phyo, P. P. (2021). Predicting Daily Rainfall Using Extreme Gradient Boosting (XGBoost). International Journal of Data Science and Analytics, 12(3), 235–248.
  33. Adeyemi, A., Botai, J., & Sivakumar, V. (2022). Rainfall Forecasting in Southern Africa Using Machine Learning Techniques. Water SA, 48(2), 198–211.
  34. Pan, B., Hsu, K., AghaKouchak, A., & Sorooshian, S. (2023). Physics-Informed Neural Networks for Rainfall and Runoff Forecasting. Hydrology and Earth System Sciences, 27(2), 585–604.
  35. Huang, X., Zhao, W., & Liu, Y. (2024). Attention-Based Encoder–Decoder Model for Rainfall Forecasting. Neurocomputing, 565, 127012.
  36. Mutale, L., Phiri, J., & Nyirenda, M. (2025). Data Fusion and ML-Based Rainfall Forecasting Framework for Southern Africa. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18, 1–15.
  37. Abdullah, Al Mukaddim, Rashed, Mohaimin, Mohammad, A. Hider, Mitu, Karmakar, Nasiruddin, S. Alam, Farhana, R. Anonna (2024). Improving Rainfall Prediction Accuracy in the USA Using Advanced Machine Learning Techniques. Journal of Environmental and Agricultural Studies, 23-24.
  38. Huijun, Zhang, Yaxin, Liu, Chongyu, Zhang & Ningyun, Li. (2025). Machine Learning Methods for Weather Forecasting: A Survey. Atmosphere, (16) 82, 1-34.
  39. B. Cramer, J. Mensah, and K. Adu-Gyamfi, “Rainfall Prediction Using Machine Learning Algorithms for Ecological Zones of Ghana,” International Journal of Environmental Data Science, vol. 7, no. 2, pp. 115–128, 2021.
  40. Australian Bureau of Meteorology, “Machine Learning-Based Rainfall Prediction for Improved Preparedness,” Journal of Climate Informatics and Modelling, vol. 5, no. 1, pp. 45–62, 2023.
  41. Li, Y., Wang, X., & Zhang, Z. (2023). Cascade Learning Framework for 15-Day Rainfall Forecasting. Atmospheric Research, 285, 106645.
  42. Singh, P., Dhiman, G., & Sharma, R. (2021). Hybrid CNN-LSTM Model for Short-Term Rainfall Prediction. Journal of Hydrology, 601, 126586.

Accurate rainfall forecasting is vital for socio-economic planning in climate-sensitive regions. Traditional statistical models often fail to capture the non-linear and stochastic nature of rainfall. This paper conducts a systematic review of machine learning (ML) techniques applied to rainfall forecasting, covering 45 studies published between 2012 and 2024, following PRISMA guidelines. The analysis identifies four high-performing algorithms: Long Short-Term Memory (LSTM), Random Forest (RF), NeuralProphet, and Support Vector Machines (SVM). LSTM models optimized with Modified Particle Swarm Optimization (M-PSO) achieved the lowest Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE). RF models demonstrated robustness for short-term forecasts, SVMs performed well with smaller datasets, and NeuralProphet offered explainability through a hybrid statistical–deep learning approach. Model choice depends on data characteristics, forecasting horizon, and the balance between accuracy and interpretability. The findings highlight the comparative strengths of these algorithms across different forecasting horizons.

Keywords : Machine Learning, Rainfall Forecasting, LSTM, Random Forest, NeuralProphet, SVM, Comparative Analysis.

CALL FOR PAPERS


Paper Submission Last Date
30 - November - 2025

Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe