AI-Based Climate Pattern Analysis and Crop Recommendation for Maharashtra: A Comparative Study of Predictive Models
DOI:
https://doi.org/10.1956/jge.v22i3.934Keywords:
ARIMA, TFT, LSTM, IMD, crop recommendationAbstract
This study focuses on developing and evaluating AI enabled framework for district level climate pattern analysis and crop recommendation in Maharashtra, India. The research used data from 2015 – 2024 for 36 districts covering four crops – rice, soybean, cotton, sorghum). Predictors include monthly data of IMD 0.25◦ gridded rainfall and temperature, relative humidity, solar radiation, cropping patterns, irrigation share & soil texture proxies. Three models were compared: ARIMA, LSTM and TFT. Rolling origin evaluation, ablation tests and robustness checks assessed accuracy and interpretability. Results showed clear gains from deep learning over ARIMA, with TFT achieving best generalization. Use of relative humidity and solar radiation improved error by ≈0.02–0.03 t/ha beyond rainfall–temperature inputs across crops, confirming their incremental value. The recommendation engine produced an average yield gain of ≈0.11 t/ha with ≈70% decision support accuracy. Policy implications include expanding seasonal advisories to include humidity and radiation signals, adopting risk adjusted implementation thresholds, and aligning input logistics with district level recommendations. The framework demonstrates operational feasibility for climate smart planning and provides a replicable benchmark for all states facing growing weather volatility.
References
Bhat, R., Sreeganga, S. D., & Priyanka, P. (2022). Crop production prediction models in Indian agriculture: A review. Indian Ecological Society Review, 2(1), 1–13.
Chipade, A. M., & Salunkhe, S. (2024). Impact of climate variability on crop yield in Pune district. E3S Web of Conferences, 550, 01012.
Deforce, B. (2024). Harnessing the power of transformers and data fusion in smart agriculture. Applied Soft Computing, 153, 110084.
Deforce, B., Van Herck, J., Baert, A., & De Moor, B. (2022). Forecasting sensor-data in smart agriculture with Temporal Fusion Transformers. KU Leuven Working Paper.
IMD. (2024/2025). IMD new high spatial resolution (0.25° × 0.25°) long period (1901–2024) daily gridded rainfall data set over India (product page). India Meteorological Department.
Jabed, M. A., Paul, M., & Rahman, M. M. (2024). Crop yield prediction in agriculture: A systematic literature review. Heliyon, 10(11), e3168673.
Jena, P., Chattopadhyay, R., Kundu, P., Maiti, P., Rajeevan, M., & Pai, D. S. (2020). Performance analysis of IMD high-resolution gridded rainfall data over India. Journal of Hydrometeorology, 21(7), 1761–1775.
Junankar, V., et al. (2023). Wheat yield prediction using Temporal Fusion Transformers. Preprint/Conference record.
Kalmani, H. V., Dharwadkar, V. N., & Thapa, V. (2025). Crop yield prediction using deep learning algorithm based on CNN-LSTM with attention layer and skip connection. Indian Journal of Agricultural Research, 59(8), 1303–1311.
Kelkar, S. M., Tambe, S. S., & Kulkarni, P. (2020). Impact of climate variability and change on crop production in Maharashtra, India. Current Science, 118(8), 1235–1243.
Khedikar, S. Y., Panchabhai, S. N., & Mandal, T. K. (2023). Study on effect of rainfall variability on crop productivity of tur (arhar) and cotton crops for various districts of Maharashtra, India. International Journal of Environment and Climate Change, 13(9), 2347–2357.
Kumar, M., & Rana, S. K. (2025). A comparative statistical approach for forecasting maize yield in India using ARIMA models. Asian Journal of Probability and Statistics, 27(9), 1–9.
Lim, B., Arik, S. O., Loeff, N., & Pfister, T. (2019/2021). Temporal Fusion Transformers for interpretable multi-horizon time series forecasting. Nature Machine Intelligence .
Maldonado-Cruz, E., Ortega-Torres, J., Tavera-Mendoza, L., & Esquivel-Gómez, J. (2024). Multi-horizon well performance forecasting with Temporal Fusion Transformer. Energy Reports, 10, 100339.
Pai, D. S., Sridhar, L., Rajeevan, M., Sreejith, O. P., Satbhai, N. S., & Mukhopadhyay, B. (2014). Development of a new high spatial resolution (0.25° × 0.25°) daily gridded rainfall data set over India—Analysis of break and active spells of the southwest monsoon. MAUSAM, 65(1), 1–18.
Peringiyil, A., Raval, L., Mishra, V., & Jain, S. (2025). A station-based 0.1-degree daily gridded ensemble precipitation dataset for India. Scientific Data, 12, Article 123.
Prasad, G., Sinha, S., & Singh, G. (2018). Impact of temperature and solar radiation on wheat crop productivity. Vayu Mandal, 44(2), 7–17.
Saksena, R., Kanani, H., & Patidar, S. (2023). Optimizing LSTM and Bi-LSTM models for crop yield prediction. Applied Intelligence, 53(18), 22179–22196.
Shawon, S. M. A. K., Sumi, S. M. A., Naser, F., & Rahman, M. M. (2024). Crop yield prediction using machine learning: An extensive review. Computational Agriculture, 2, 100061.
Srivastava, A. K., Rajeevan, M., & Kshirsagar, S. R. (2009). Development of a high-resolution daily gridded temperature data set (1969–2005) for the Indian region. Met monograph/IMD .
Subramaniam, L. K., Chithambarathanu, T., & Periasamy, R. (2024). Crop yield prediction using effective deep learning and dimensionality reduction approaches for Indian regional crops. Agricultural Informatics, 5(3), 100191.
Times of India. (2025a, October 31). Scientists warn of 50% drop in grape yield across Maharashtra this season. The Times of India.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Journal of Global Economy
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
