Hybrid SARIMA–Bi-LSTM model for monthly rainfall forecasting in the agroclimatic zones of Chhattisgarh
DOI:
https://doi.org/10.54386/jam.v27i3.3010Keywords:
Rainfall forecasting, Statistical techniques, Deep learning, Hybrid SARIMA–Bi-LSTM model, SARIMA, Agroclimatic zonesAbstract
This study proposes a hybrid Seasonal Autoregressive Integrated Moving Average (SARIMA)–Bidirectional Long Short-Term Memory (Bi-LSTM) model for monthly rainfall forecasting in the agroclimatic zones of Chhattisgarh, India. Accurate rainfall prediction is critical for agricultural planning and water resource management, especially under increasing climate variability. The analysis utilizes 120 years (1901–2020) of monthly rainfall data, preprocessed for time series modeling. SARIMA serves as a statistical baseline, effectively capturing linear and seasonal trends, while Bi-LSTM, a deep learning model, is adept at learning long-term and non-linear dependencies. The hybrid SARIMA–Bi-LSTM model leverages the strengths of both approaches to improve forecasting accuracy. Model performance was evaluated using standard metrics such as Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and the coefficient of determination (R²). Results show that Bi-LSTM outperforms SARIMA, and the hybrid model delivers the best generalization across agroclimatic zones. In the Chhattisgarh Plains, the hybrid model achieved the lowest validation RMSE (41.70 mm), MAE (25.93 mm), and the highest R² (0.906). The study highlights SARIMA’s limitations in capturing non-linearities and Bi-LSTM’s tendency to overfit, both addressed in the hybrid approach. This work demonstrates the effectiveness of hybrid models in enhancing rainfall forecasting and informs climate-resilient agricultural practices.
References
Ahmed, I. and Sreedevi, T. (2023). Comparative analysis of deep learning models for rainfall prediction. J. Climate Inform., 12(3): 45–58.
Box, G.E.P. and Jenkins, G.M. (1976). Time series analysis: Forecasting and control. Holden-Day.
Brown, R.G. (2004). Smoothing, forecasting and prediction of discrete time series. Dover Publications. (Original work published 1963)
Choi, J., Kim, H. and Lee, D. (2021). Application of machine learning techniques for seasonal rainfall prediction. Environ. Model. Softw., 145: 105205.
Chollet, F. (2017). Deep learning with Python. Manning Publications.
Dabral, P.P. and Murry, M. (2017). Rainfall forecasting using SARIMA models in Northeast India. Indian J. Hydrol., 34(2): 120–132.
Goodfellow, I., Bengio, Y. and Courville, A. (2016). Deep learning. MIT Press. ISBN: 978-0262035613. https://www.deeplearningbook.org
Greff, K., Srivastava, R.K., Koutník, J., Steunebrink, B.R. and Schmidhuber, J. (2017). LSTM: A search space odyssey. IEEE Trans. Neural Netw. Learn. Syst., 28(10): 2222–2232. https://doi.org/10.1109/TNNLS.2016.2582924
Gupta, R. and Sharma, A. (2021). Comparative performance of SARIMA and deep learning models in climate forecasting. Meteorol. Adv., 19(4): 78–92.
Han, J. and Park, S. (2020). Enhancing time-series forecasting accuracy with multivariate SARIMA models. J. Climate Res., 28(1): 35–50.
Hochreiter, S. and Schmidhuber, J. (1997). Long short-term memory. Neural Comput., 9(8): 1735–1780.
Hyndman, R.J. and Athanasopoulos, G. (2018). Forecasting: Principles and practice (2nd ed.). OTexts.
Kumar, V. and Singh, P. (2021). Deep learning for climate time series analysis: A review. Int. J. Data Sci., 17(2): 205–225.
Martinez, F. and Lee, J. (2019). Ensemble learning techniques for improved rainfall prediction. J. Artif. Intell. Climate Stud., 11(3): 67–79.
Pandey, S. (2018). Improving SARIMA forecasting accuracy using GARCH models. Indian J. Stat. Anal., 22(1): 45–59.
Pasini, A. (2020). Artificial intelligence for applied sciences. Springer.
Patro, B.S. and Bartakke, P.P. (2024). Daily rainfall prediction using long short-term memory (LSTM) algorithm. J. Agrometeorol., 26(4): 509–511. https://doi.org/10.54386/jam.v26i4.2745
Rajalakshmi, M. (2023). Evaluating the effectiveness of LSTM models for monsoon rainfall prediction. J. Hydrometeorol., 15(4): 98–115.
Ray, M., Singh, K.N., Pal, S., Saha, A., Sinha, K. and Kumar, R.R. (2023). Rainfall prediction using time-delay wavelet neural network (TDWNN) model for assessing agrometeorological risk. J. Agrometeorol., 25(1): 151–157. https://doi.org/10.54386/jam.v25i1.1895
Shumway, R.H. and Stoffer, D.S. (2017). Time series analysis and its applications (4th ed.). Springer. https://doi.org/10.1007/978-3-319-52452-8
Singh, R. and Patel, V. (2023). A meta-analysis of rainfall forecasting models: SARIMA vs. deep learning. J. Climate Anal., 21(2): 112–129.
Smith, B. and Taylor, J. (2023). Challenges of time series forecasting with traditional statistical models. Int. J. Forecast., 39(1): 23–37.
Wu, L. and Zhang, Y. (2022). A hybrid SARIMA-LSTM model for improved time-series forecasting. J. Comput. Meteorol., 25(3): 55–72.
Yadav, N. and Verma, K. (2022). Comparative study of SARIMA and deep learning models for rainfall prediction. Environ. Data Sci. Anal., 14(2): 88–101.
Zhang, G.P. (2003). Time series forecasting using a hybrid ARIMA and neural network model. Neurocomp., 50: 159–175. https://doi.org/10.1016/S0925-2312(01)00702-0
Zhou, Y., Wang, X. and Chen, L. (2023). Advances in deep learning for climate time series forecasting. Artif. Intell. Meteorol., 30(1): 67–85.
Downloads
Published
How to Cite
License
Copyright (c) 2025 DIWAKAR NAIDU, SURENDRA KUMAR CHANDNIHA
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
This is a human-readable summary of (and not a substitute for) the license. Disclaimer.
You are free to:
Share — copy and redistribute the material in any medium or format
Adapt — remix, transform, and build upon the material
The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
NonCommercial — You may not use the material for commercial purposes.
ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license as the original.
No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation.
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.
