Rainfall forecasting remains challenging in semi-arid regions due to high variability and intermittent rainfall patterns. Statistical forecasting methods such as Autoregressive Integrated Moving Average(ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) often struggle to capture the non-linear dynamics typical of such rainfall. Machine learning (ML) techniques such as Extreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) networks offer improved forecasting performance but have individual limitations. This study compares LSTM, XGBoost and a hybrid LSTM-XGBoost model for monthly rainfall forecasting, using SARIMA as a baseline. The study utilizes 44 years of CHIRPS (Climate Hazards Group InfraRed Precipitation with Station) data from Tana River County, Kenya, accessed through Google Earth Engine. Data preprocessing included log transformation, stationarity testing, normalization, and feature engineering. The data was chronologically split to form the train, validation and test sets. The performance of the models was evaluated using Root Mean Square Error, Mean Absolute Error, Coefficient of Determination and Nash Sutcliffe Efficiency. Shapley Additive Explanations were used for interpretability. The XGBoost, LSTM and Hybrid LSTM-XGBoost models outperformed the baseline, achieving a Coefficient of Determination of approximately 0.61 compared with 0.52. The hybrid model performed best overall, with an RMSE of 38.68 mm, MAE of 17.23 mm, and R2 of 0.609. Hybrid forecasting approaches combining deep learning and machine learning should be further explored for rainfall prediction in semi-arid regions due to their potential to capture complex temporal patterns.
| Published in | International Journal of Data Science and Analysis (Volume 12, Issue 5) |
| DOI | 10.11648/j.ijdsa.20261205.12 |
| Page(s) | 114-128 |
| Creative Commons |
This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited. |
| Copyright |
Copyright © The Author(s), 2026. Published by Science Publishing Group |
Rainfall Forecasting, LSTM, XGBoost, LSTM-XGBoost Hybrid Model, Machine Learning
| [1] | P. I. Palmer, C. M. Wainwright, B. Dong, R. I. Maidment, K. G. Wheeler, N. Gedney, and A. G. Turner. Drivers and impacts of Eastern African rainfall variability. Nature Reviews Earth & Environment, 4: 254-270, 2023. |
| [2] | P. K. Langat, L. Kumar, and R. Koech. Temporal variability and trends of rainfall and streamflow in Tana River Basin, Kenya. Sustainability, 9: 1963, 2017. |
| [3] | T. Dinku, C. Funk, P. Peterson, R. Maidment, T. Tadesse, H. Gadain, and P. Ceccato. Validation of the CHIRPS satellite rainfall estimates over eastern Africa. Quarterly Journal of the Royal Meteorological Society, 144(S1): 292-312, 2018. |
| [4] | V. I. Kontopoulou, A. D. Panagopoulos, I. Kakkos, and G. K. Matsopoulos. A review of ARIMA vs. machine learning approaches for time series forecasting in data driven networks. Future Internet, 15(8): 255, 2023. |
| [5] | T. Chen and C. Guestrin. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 785-794, 2016. |
| [6] | M. S. Islam, M. Shafiuzzaman, G. Mahmud, N. Nowshin, P. Reza, J. Hasan, F. M. Ahamed, M. Nahiduzzaman, M. A. Ayari, and A. Khandakar. Explainable deep learning for rainfall prediction: A CNN-XGBoost hybrid approach in the northern region of Bangladesh. Neural Computing and Applications, 37: 28125-28160, 2025. |
| [7] | A. Y. Barrera-Animas, L. O. Oyedele, M. Bilal, T. D. Akinosho, J. M. D. Delgado, and L. A. Akanbi. Rainfall prediction: A comparative analysis of modern machine learning algorithms for time-series forecasting. Machine Learning with Applications, 7: 100204, 2022. |
| [8] | C. M. Liyew and H. A. Melese. Machine learning techniques to predict daily rainfall amount. Journal of Big Data, 8: 153, 2021. |
| [9] | Z. Xiang, J. Yan, and I. Demir. A rainfall-runoff model with LSTM-based sequence-to-sequence learning. Water Resources Research, 56: e2019WR025326, 2020. |
| [10] | M. Waqas and U. W. Humphries. A critical review of RNN and LSTM variants in hydrological time series predictions. MethodsX, 13: 102946, 2024. |
| [11] | L. Semmelmann, S. Henni, and C. Weinhardt. Load forecasting for energy communities: A novel LSTM-XGBoost hybrid model based on smart meter data. Energy Informatics, 5(Suppl 1): 24, 2022. |
| [12] | Tripti Dimri, Shamshad Ahmad, and Mohammad Sharif. Time series analysis of climate variables using seasonal arima approach. Journal of Earth System Science, 129: 149, 2020. |
| [13] | Mostafa Dastorani, Mohammad Mirzavand, Dastorani Mohammad Taghi, and Seyyed Javad Sadatinejad. Comparative study among different time series models applied to monthly rainfall forecasting in semi-arid climate condition. Natural Hazards, 81: 1811-1827, 2016. |
| [14] | O. A. Wani, S. S. Mahdi, M. Yeasin, S. S. Kumar, A. S. Gagnon, F. Danish, N. Al-Ansari, S. El-Hendawy, and M. A. Mattar. Predicting rainfall using machine learning, deep learning, and time series models across an altitudinal gradient in the North-Western Himalayas. Scientific Reports, 14, 2024. |
| [15] | S. Kundu, S. K. Biswas, D. Tripathi, R. Karmakar, S. Majumdar, and S. Mandal. A review on rainfall forecasting using ensemble learning techniques. e-Prime - Advances in Electrical Engineering, Electronics and Energy, 6: 100296, 2023. |
| [16] | M. Niazkar, A. Menapace, B. Brentan, R. Piraei, D. Jimenez, D. Pranav, and M. Righetti. Applications of XGBoost in water resources engineering: A systematic literature review. Journal of Hydroinformatics, 26(1), 2024. |
| [17] | Y. LeCun, Y. Bengio, and G. Hinton. Deep learning. Nature, 521(7553): 436-444, 2015. |
| [18] | Y. O. Ouma, R. Cheruyot, and A. N. Wachera. Rainfall and runoff time-series trend analysis using LSTM recurrent neural network and wavelet neural network with satellite-based meteorological data: case study of Nzoia River Basin, Lake Victoria, Kenya. Environmental Science and Pollution Research, 2021. |
| [19] | S. Siami-Namini, N. Tavakoli, and A. S. Namin. A comparison of ARIMA and LSTM in forecasting time series. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pages 1394-1401, 2018. |
| [20] | L. J. Slater, L. Arnal, M.-A. Boucher, A. Y.-Y. Chang, S. Moulds, C. Murphy, G. Nearing, G. Shalev, C. Shen, L. Speight, G. Villarini, R. L. Wilby, A. Wood, and M. Zappa. Hybrid forecasting: Blending climate predictions with machine learning. Hydrology and Earth System Sciences, 27(9): 1865-1889, 2023. |
| [21] | J. Saikia, K. Goswami, and S. C. Kakaty. Wavelet-sarima-transformer: A hybrid model for rainfall forecasting. arXiv, 2025. |
| [22] | M. El Hafyani, K. El Himdi, and S.-E. El Adlouni. Improving monthly precipitation prediction accuracy using machine learning models: A multi-view stacking learning technique. Frontiers in Water, 6: 1378598, 2024. |
| [23] | S. D. Latif, D. O. Mohammed, and A. Jaafar. Developing an innovative machine learning model for rainfall prediction in a semi-arid region. Journal of Hydroinformatics, 26(4): 904-914, 2024. |
| [24] | D. N. Moriasi, M. W. Gitau, N. Pai, and P. Daggupati. Hydrologic and water quality models: Performance measures and evaluation criteria. Transactions of the ASABE, 58(6): 1763-1785, 2015. |
APA Style
Muriithi, R. M., Gachoki, P. K., Kilai, M. (2026). Comparative Study of Lstm, Xgboost and Hybrid Lstm-xgboost Models for Rainfall Forecasting in Semi-arid Regions. International Journal of Data Science and Analysis, 12(5), 114-128. https://doi.org/10.11648/j.ijdsa.20261205.12
ACS Style
Muriithi, R. M.; Gachoki, P. K.; Kilai, M. Comparative Study of Lstm, Xgboost and Hybrid Lstm-xgboost Models for Rainfall Forecasting in Semi-arid Regions. Int. J. Data Sci. Anal. 2026, 12(5), 114-128. doi: 10.11648/j.ijdsa.20261205.12
AMA Style
Muriithi RM, Gachoki PK, Kilai M. Comparative Study of Lstm, Xgboost and Hybrid Lstm-xgboost Models for Rainfall Forecasting in Semi-arid Regions. Int J Data Sci Anal. 2026;12(5):114-128. doi: 10.11648/j.ijdsa.20261205.12
Share This Article
Twitter
Linked In
Facebook
Copy
Download@article{10.11648/j.ijdsa.20261205.12,
author = {Rony Mutugi Muriithi and Peter Kinyua Gachoki and Mutua Kilai},
title = {Comparative Study of Lstm, Xgboost and Hybrid Lstm-xgboost Models for Rainfall Forecasting in Semi-arid Regions},
journal = {International Journal of Data Science and Analysis},
volume = {12},
number = {5},
pages = {114-128},
doi = {10.11648/j.ijdsa.20261205.12},
url = {https://doi.org/10.11648/j.ijdsa.20261205.12},
eprint = {https://article.sciencepublishinggroup.com/pdf/10.11648.j.ijdsa.20261205.12},
abstract = {Rainfall forecasting remains challenging in semi-arid regions due to high variability and intermittent rainfall patterns. Statistical forecasting methods such as Autoregressive Integrated Moving Average(ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) often struggle to capture the non-linear dynamics typical of such rainfall. Machine learning (ML) techniques such as Extreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) networks offer improved forecasting performance but have individual limitations. This study compares LSTM, XGBoost and a hybrid LSTM-XGBoost model for monthly rainfall forecasting, using SARIMA as a baseline. The study utilizes 44 years of CHIRPS (Climate Hazards Group InfraRed Precipitation with Station) data from Tana River County, Kenya, accessed through Google Earth Engine. Data preprocessing included log transformation, stationarity testing, normalization, and feature engineering. The data was chronologically split to form the train, validation and test sets. The performance of the models was evaluated using Root Mean Square Error, Mean Absolute Error, Coefficient of Determination and Nash Sutcliffe Efficiency. Shapley Additive Explanations were used for interpretability. The XGBoost, LSTM and Hybrid LSTM-XGBoost models outperformed the baseline, achieving a Coefficient of Determination of approximately 0.61 compared with 0.52. The hybrid model performed best overall, with an RMSE of 38.68 mm, MAE of 17.23 mm, and R2 of 0.609. Hybrid forecasting approaches combining deep learning and machine learning should be further explored for rainfall prediction in semi-arid regions due to their potential to capture complex temporal patterns.},
year = {2026}
}
TY - JOUR T1 - Comparative Study of Lstm, Xgboost and Hybrid Lstm-xgboost Models for Rainfall Forecasting in Semi-arid Regions AU - Rony Mutugi Muriithi AU - Peter Kinyua Gachoki AU - Mutua Kilai Y1 - 2026/09/08 PY - 2026 N1 - https://doi.org/10.11648/j.ijdsa.20261205.12 DO - 10.11648/j.ijdsa.20261205.12 T2 - International Journal of Data Science and Analysis JF - International Journal of Data Science and Analysis JO - International Journal of Data Science and Analysis SP - 114 EP - 128 PB - Science Publishing Group SN - 2575-1891 UR - https://doi.org/10.11648/j.ijdsa.20261205.12 AB - Rainfall forecasting remains challenging in semi-arid regions due to high variability and intermittent rainfall patterns. Statistical forecasting methods such as Autoregressive Integrated Moving Average(ARIMA) and Seasonal Autoregressive Integrated Moving Average (SARIMA) often struggle to capture the non-linear dynamics typical of such rainfall. Machine learning (ML) techniques such as Extreme Gradient Boosting (XGBoost) and Long Short-Term Memory (LSTM) networks offer improved forecasting performance but have individual limitations. This study compares LSTM, XGBoost and a hybrid LSTM-XGBoost model for monthly rainfall forecasting, using SARIMA as a baseline. The study utilizes 44 years of CHIRPS (Climate Hazards Group InfraRed Precipitation with Station) data from Tana River County, Kenya, accessed through Google Earth Engine. Data preprocessing included log transformation, stationarity testing, normalization, and feature engineering. The data was chronologically split to form the train, validation and test sets. The performance of the models was evaluated using Root Mean Square Error, Mean Absolute Error, Coefficient of Determination and Nash Sutcliffe Efficiency. Shapley Additive Explanations were used for interpretability. The XGBoost, LSTM and Hybrid LSTM-XGBoost models outperformed the baseline, achieving a Coefficient of Determination of approximately 0.61 compared with 0.52. The hybrid model performed best overall, with an RMSE of 38.68 mm, MAE of 17.23 mm, and R2 of 0.609. Hybrid forecasting approaches combining deep learning and machine learning should be further explored for rainfall prediction in semi-arid regions due to their potential to capture complex temporal patterns. VL - 12 IS - 5 ER -
School of Pure and Applied Sciences, Kirinyaga University, Kerugoya, Kenya
School of Pure and Applied Sciences, Kirinyaga University, Kerugoya, Kenya
School of Pure and Applied Sciences, Kirinyaga University, Kerugoya, Kenya
Information