An Enhanced Hybrid LSTM–Linear Regression Framework for 90-Day Rainfall Forecasting in Rainfed Agricultural Regions
Corresponding author: Jakkrit Kaewyotha
Abstract
This study develops a 90-day rainfall forecasting model for rain-fed agricultural systems in areas lacking ground-based weather sensors. To address this limitation, open data from the NASA POWER satellite (2014–2024) covering Nadi Subdistrict, Mueang District, Surin Province, Thailand, is utilized. The proposed hybrid framework combines Long Short-Term Memory (LSTM) networks with Linear Regression (LR) to join the ability to learn nonlinear temporal dynamics with the potential to model long-term trends, complemented by lag and rolling windows techniques. The results indicate that the lag–rolling–augmented LSTM–LR model achieved the lowest Root Mean Squared Error (RMSE) of 0.0413 and Mean Absolute Error (MAE) of 0.0230 among all 10 models. The Friedman test confirmed the significant difference (x² = 364.33, p < 0.001), and the Nemenyi test showed that the proposed model significantly outperformed the traditional BiLSTM, Convolutional Neural Network (CNN), CNN (with lag and rolling features), and LSTM+LR (p < 0.0001). Furthermore, the model maintained high accuracy during both heavy and drought conditions. The novelty of this study lies in the integration of temporal hybrid models with open satellite data to create a low-cost and statistically validated tool for climate risk management and decision support approaches for smallholder agriculture.
Keywords:
hybrid model, LSTM, linear regression, feature engineering, rainfall forecastingDownloads
References
R. Mungkung et al., "Measuring Sustainability Performance of Rice Cultivation in Thailand using Sustainable Rice Platform Indicators," International Journal of Agricultural Sustainability, vol. 20, no. 7, pp. 1278–1293, Dec. 2022. DOI: https://doi.org/10.1080/14735903.2022.2105008
M. A. Alwadi, "Fuel Sales Price Forecasting using Time Series, Machine Learning, and Deep Learning Models," Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 22360–22366, Jun. 2025. DOI: https://doi.org/10.48084/etasr.10348
S. Zairi and M. Freihat, "Electric Load Forecasting using Machine Learning for Peak Demand Management in Smart Grids," Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 23335–23346, Jun. 2025. DOI: https://doi.org/10.48084/etasr.10687
M. Bousla et al., "Modeling Wind Energy Production Forecasting using Machine Learning: An In-depth Analysis of Wind Farms in Morocco," Engineering, Technology & Applied Science Research, vol. 15, no. 3, pp. 23268–23276, Jun. 2025. DOI: https://doi.org/10.48084/etasr.10296
G. Thottungal Harilal, A. Dixit, and G. Quattrone, "Establishing Hybrid Deep Learning Models for Regional Daily Rainfall Time Series Forecasting in the United Kingdom," Engineering Applications of Artificial Intelligence, vol. 133, July 2024, Art. no. 108581. DOI: https://doi.org/10.1016/j.engappai.2024.108581
Q. Guo, Z. He, and Z. Wang, "Monthly Climate Prediction using Deep Convolutional Neural Network and Long Short-Term Memory," Scientific Reports, vol. 14, no. 1, July 2024, Art. no. 17748. DOI: https://doi.org/10.1038/s41598-024-68906-6
X. Cui, Z. Wang, and R. Pei, "A VMD-MSMA-LSTM-ARIMA Model for Precipitation Prediction," Hydrological Sciences Journal, vol. 68, no. 6, pp. 810–839, Apr. 2023. DOI: https://doi.org/10.1080/02626667.2023.2190896
Y. Lyu and B. Yong, "A Novel Double Machine Learning Strategy for Producing High‐Precision Multi‐Source Merging Precipitation Estimates Over the Tibetan Plateau," Water Resources Research, vol. 60, no. 4, Apr. 2024, Art. no. e2023WR035643. DOI: https://doi.org/10.1029/2023WR035643
C. Chen et al., "Forecast of Rainfall Distribution Based on Fixed Sliding Window Long Short-Term Memory," Engineering Applications of Computational Fluid Mechanics, vol. 16, no. 1, pp. 248–261, Dec. 2022. DOI: https://doi.org/10.1080/19942060.2021.2009374
B. Chueasa, U. W. Humphries, and M. Waqas, "Influence of El Niño Southern Oscillation on Precipitation Variability in Northeast Thailand," MethodsX, vol. 13, Dec. 2024, Art. no. 102954. DOI: https://doi.org/10.1016/j.mex.2024.102954
H. Du, M. L. Tan, K. P. Chun, and F. Zhang, "Evaluation of Four Gridded Climate Products for Streamflow and Drought Simulations in the Kelantan River Basin, Malaysia," Geocarto International, vol. 40, no. 1, Dec. 2025, Art. no. 2453615. DOI: https://doi.org/10.1080/10106049.2025.2453615
C. Kaprom, J. A. Williams, R. Mehrotra, C. Ophaphaibun, and N. Sriwongsitanon, "A Comprehensive Evaluation of the Accuracy of Satellite-Based Precipitation Estimates Over Thailand," Journal of Hydrology: Regional Studies, vol. 59, Jun. 2025, Art. no. 102380. DOI: https://doi.org/10.1016/j.ejrh.2025.102380
J. F. De Oliveira-Júnior et al., "Analysis of Drought and Extreme Precipitation Events in Thailand: Trends, Climate Modeling, and Implications for Climate Change Adaptation," Scientific Reports, vol. 15, no. 1, Feb. 2025, Art. no. 4501. DOI: https://doi.org/10.1038/s41598-025-86826-x
H. Xu, Z. Guo, Y. Cao, X. Cheng, Q. Zhang, and D. Chen, "Research on Short-Term Precipitation Forecasting Method Based on CEEMDAN-GRU Algorithm," Scientific Reports, vol. 14, no. 1, Dec. 2024, Art. no. 31885. DOI: https://doi.org/10.1038/s41598-024-83365-9
F. Kratzert, M. Gauch, D. Klotz, and G. Nearing, "HESS Opinions: Never Train a Long Short-Term Memory (LSTM) Network on a Single Basin," Hydrology and Earth System Sciences, vol. 28, no. 17, pp. 4187–4201, Sept. 2024. DOI: https://doi.org/10.5194/hess-28-4187-2024
N. Martin and J. White, "Water Resources’ AI–ML Data Uncertainty Risk and Mitigation using Data Assimilation," Water, vol. 16, no. 19, Sept. 2024, Art. no. 2758. DOI: https://doi.org/10.3390/w16192758
Z. Yang, D. Dong, Y. Chen, and R. Wang, "Water Inflow Forecasting Based on Visual MODFLOW and GS-SARIMA-LSTM Methods," Water, vol. 16, no. 19, Sept. 2024, Art. no. 2749. DOI: https://doi.org/10.3390/w16192749
J. Han, M. Kamber, and J. Pei, Data Mining: Concepts and Techniques, 3rd ed. Amsterdam, Netherlands: Elsevier/Morgan Kaufmann, 2012.
J. Snoek, H. Larochelle, and R. P. Adams, "Practical Bayesian Optimization of Machine Learning Algorithms." arXiv, 2012.
P. A. Shejule and S. Pekkat, "Hybrid Model for Multistep-Ahead Rainfall Forecast in Northeast India: A Comparative Study," Journal of Hydrometeorology, vol. 25, no. 8, pp. 1221–1236, Aug. 2024. DOI: https://doi.org/10.1175/JHM-D-23-0173.1
D. M. Moges et al., "Streamflow Prediction with Time-Lag-Informed Random Forest and Its Performance Compared to SWAT in Diverse Catchments," Water, vol. 16, no. 19, Oct. 2024, Art. no. 2805. DOI: https://doi.org/10.3390/w16192805
A. Khatun, M. N. Nisha, S. Chatterjee, and V. Sridhar, "A Novel Insight on Input Variable and Time Lag Selection in Daily Streamflow Forecasting using Deep Learning Models," Environmental Modelling & Software, vol. 179, Aug. 2024, Art. no. 106126. DOI: https://doi.org/10.1016/j.envsoft.2024.106126
J. Demsar, "Statistical Comparisons of Classifiers over Multiple Data Sets," Journal of Machine Learning Research, vol. 7, pp. 1–30, 2006.
J. Liu, J. Koch, S. Stisen, L. Troldborg, and R. J. M. Schneider, "A National-Scale Hybrid Model for Enhanced Streamflow Estimation – Consolidating A Physically Based Hydrological Model with Long Short-Term Memory (LSTM) Networks," Hydrology and Earth System Sciences, vol. 28, no. 13, pp. 2871–2893, July 2024. DOI: https://doi.org/10.5194/hess-28-2871-2024
R. Yuan, "Rainfall Prediction Based on CNN-LSTM Model Under Sliding Window," European Journal of Remote Sensing, vol. 58, no. 1, Dec. 2025, Art. no. 2540106. DOI: https://doi.org/10.1080/22797254.2025.2540106
I. Ebtehaj and H. Bonakdari, "CNN vs. LSTM: A Comparative Study of Hourly Precipitation Intensity Prediction as a Key Factor in Flood Forecasting Frameworks," Atmosphere, vol. 15, no. 9, Sept. 2024, Art. no. 1082. DOI: https://doi.org/10.3390/atmos15091082
T. Wang, W. Chen, and B. Tang, "Water Quality Prediction using ARIMA-SSA-LSTM Combination Model," Water Supply, vol. 24, no. 4, pp. 1282–1297, Apr. 2024. DOI: https://doi.org/10.2166/ws.2024.060
F. A. F. Sham, A. El-Shafie, W. Z. B. W. Jaafar, S. Adarsh, M. Sherif, and A. N. Ahmed, "Improving Rainfall Forecasting using Deep Learning Data Fusing Model Approach for Observed and Climate Change Data," Scientific Reports, vol. 15, no. 1, July 2025, Art. no. 27872. DOI: https://doi.org/10.1038/s41598-025-13567-2
D. Naidu and S. K. Chandniha, "Hybrid SARIMA–Bi-LSTM Model for Monthly Rainfall Forecasting in the Agroclimatic Zones of Chhattisgarh," Journal of Agrometeorology, vol. 27, no. 3, pp. 332–337, Sept. 2025. DOI: https://doi.org/10.54386/jam.v27i3.3010
Downloads
How to Cite
License
Copyright (c) 2025 Attapol Kunlerd, Atipat Ritthiron, Jakkrit Kaewyotha
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- 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 acknowledgement 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) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
