GR-AI-N: HYBRID MLR-LSTM MACHINE LEARNING-DRIVEN RICE YIELD FORECASTING SYSTEM WITH GENERATIVE AI INTEGRATED PLATFORM FOR REAL-TIME OPTIMIZED PLANTING TIME PREDICTIONS AND RECOMMENDATIONS
Keywords:
Multiple Linear Regression (MLR), Machine Learning, Precision Agriculture, Decision-Support System, Rice-Yield ForecastingAbstract
Rice production in the Philippines is highly sensitive to climate variability, causing yield losses and inefficient resource use. This study presents GR-AI-N, a hybrid forecasting system combining Multiple Linear Regression (MLR), Long Short-Term Memory (LSTM) networks, and a Generative AI chatbot to predict rice yields and provide real-time recommendations. Historical geo-climatic data informed the hybrid MLR–LSTM model, which achieved high accuracy (R² = 0.99) and reliable planting forecasts through 2100. The chatbot demonstrated strong performance (F1 = 0.9766). User surveys on functionality, usability, adaptability, and acceptability showed excellent results. GR-AI-N thus delivers accurate, AI-driven decision support for sustainable rice production.
References
Ahmed, A., et al. (2019). Seasonal climate patterns and ideal planting times for rice in the Philippines. Philippine Journal of Crop Science, 12(4), 211–225.
Adisa, O. M., Botai, J. O., Adeola, A. M., Hassen, A., & Botai, C. M. (2022). Machine learning-based predictive modeling of maize yield using climate variables in South Africa. Agricultural and Forest Meteorology, 312, 108715. https://doi.org/10.1016/j.agrformet.2021.108715
Bian, L., Zhang, Y., & Chen, H. (2025). Effects of organic amendments on paddy field productivity. International Journal of Agronomy, 15(2), 45–60.
Callueng, A. E., Latip, A. Y. S., & Rejas, F. E. (2025). Multiple linear regression analysis of geo-climatic variables on rice yield in South Cotabato.
Casinillo, F., et al. (2023). Data-informed cultivation strategies and yield efficiency in Philippine rice farms. Philippine Journal of Agricultural Economics, 45(1), 55–67.
Chauhan, B. S., Jabran, K., & Mahajan, G. (Eds.). (2017). Rice production worldwide. Springer International Publishing. https://doi.org/10.1007/978-3-319-47516-5
Dubey, S., et al. (2018). Climate anomalies and rice yield disruptions in Southeast Asia. Climate Research, 76(3), 215–228.
Food and Agriculture Organization. (2013). Crop yield forecasting methods and early warning systems: A literature review. FAO. https://www.fao.org
Food and Agriculture Organization. (2024). FAOSTAT. https://www.fao.org/faostat/en
Foley, J. A., Ramankutty, N., Brauman, K. A., Cassidy, E. S., Gerber, J. S., Johnston, M., … Zaks, D. P. M. (2020). Solutions for a cultivated planet. Nature, 478(7369), 337–342. https://doi.org/10.1038/nature10452
Han, J., Kamber, M., & Pei, J. (2012). Data mining: Concepts and techniques (3rd ed.). Elsevier.
Hasan, M., et al. (2020). Mechanized rice farming: Improving yield and labor efficiency. Journal of Smart Agriculture, 11(2), 89–101.
Hatfield, J. L., & Beresford, N. A. (2016). Effects of heat stress on spikelet sterility in rice. Agricultural Meteorology, 218, 15–23.
Jin, Y., et al. (2025). Climate-induced salt stress on hybrid rice varieties. Plant Science Journal, 212(5), 88–103.
Khaki, S., & Wang, L. (2019). Crop yield prediction using deep neural networks. Frontiers in Plant Science, 10, 621. https://doi.org/10.3389/fpls.2019.00621
Kotsiantis, S. B., Kanellopoulos, D., & Pintelas, P. E. (2006). Data preprocessing for supervised learning. International Journal of Computer Science, 1(2), 111–117.
Kumar, S., et al. (2021). Climate adaptation strategies for rice farming. Journal of Environmental Management, 283, 111–123.
Lasalita-Zapico, R., et al. (2008). Traditional rice landraces and biodiversity conservation in Lake Sebu, Philippines. Philippine Journal of Crop Science, 33(1), 77–88.
Nagai, T., & Makino, A. (2019). Optimal temperature ranges for rice growth. Plant Physiology Journal, 12(3), 140–150.
Ocampo, O., Makahiya, H. A., Pamplona, M., Motilla, J. K., Meynard, P., Bueno, C., & Sta Cruz, P. (2023). Variability of cost and return of dry direct-seeded lowland rice in major rainfed growing areas in the Philippines. Philippine Agricultural Scientist, 106(2), 208–216. https://ovcre.uplb.edu.ph/journals-uplb/index.php/PAS/article/view/
Philippine News Agency. (2024). Rice farmers in South Cotabato.
Phuong, T. T., Pham, H. T., & Nguyen, T. N. (2022). Data preprocessing impact on LSTM-based crop yield forecasting using climatic time-series data. Computers and Electronics in Agriculture, 202, 107353. https://doi.org/10.1016/j.compag.2022.107353
Qu, X., Kojima, D., Wu, L., & Ando, M. (2021). Losses in the rice harvest process: A review. Sustainability, 13(17), 9627. https://doi.org/10.3390/su13179627
Remshard, M., & Queenborough, S. A. (2023). Design of tables for the presentation and communication of data in ecological and evolutionary biology. Ecology and Evolution, 13(7), e10062. https://doi.org/10.1002/ece3.10062
Sattar, R., et al. (2023). Relative humidity effects on rice transpiration and nutrient uptake. Agricultural Water Management, 285, 104118.
Stuecker, C., et al. (2018). ENSO-related rainfall disruptions and rice yield losses. Environmental Research Letters, 13(9), 095103. https://doi.org/10.1088/1748-9326/aadce6
Vicente, J., et al. (2019). Adoption of modern planting schedules among Filipino rice farmers. Philippine Journal of Agricultural Extension, 22(1), 33–45.
Wang, L., Feng, H., & Li, Z. (2018). Maize yield forecasting by linear regression and artificial neural networks in Jilin, China. The Journal of Agricultural Science, 156(9), 1125–1135. https://doi.org/10.1017/S0021859618000581
Wassmann, R., et al. (2009). Breeding heat-resistant rice varieties. Field Crops Research, 110(3), 85–98.
Weather and Climate. (2015). Historical climate data for South Cotabato. https://www.weather-and-climate.com
Yan, H., et al. (2025). Integrating time-series data and regression for crop yield forecasting. International Journal of Computational Agriculture, 11(1), 15–29.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Hayla D. Caitor, Il Nam O. Cho, Ayman Latip, Han Mark M. Lumayal, Ava Claire T. Ponteras
This work is licensed under a Creative Commons Attribution 4.0 International License.
