MACHINE LEARNING-DRIVEN PADDY YIELD PREDICTION: COMPARATIVE EVALUATION OF BASELINE VS. ENSEMBLE MODELS IN UDHAM SINGH NAGAR, UTTARAKHAND

Rice is a cornerstone of food security in India, supporting millions of livelihoods and the national economy. However, erratic climate patterns are making paddy yields increasingly unpredictable. This study develops a machine learning framework for rice yield prediction in Udham Singh Nagar district, Uttarakhand, by integrating weather, soil, and crop data. Among baseline classifiers, CatBoost performed best with 80.85% accuracy and a ROC-AUC of 0.90. To further enhance performance, Optuna-tuned CatBoost, XGBoost, and LightGBM models were combined into hybrid ensembles. The Weighted Hard Voting classifier, giving higher weight to CatBoost ([3,1,1]), achieved the highest accuracy of 97.37%, followed by Stacking (95.6%) and Soft Voting ensembles (up to 96%). These results were supported by strong ROC-AUC scores. Overall, the study shows that carefully optimized ensemble models can significantly improve yield prediction accuracy, offering a practical tool for more precise and sustainable rice farming in climate-sensitive regions of India.

1. State Agriculture Statistics Data. Agriculture Department Uttarakhand. Available at: https://agriculture. uk.gov.in/document-category/state-agriculture-statistics-data/ (accessed 2025).

2. Sharma, M., Sharma, N., and Sachdeva, S. Ground Water Quality Assessment in Udham Singh Nagar, Uttarakhand, India. International Journal of Lakes and Rivers, 16 (2), 173–183 (2023). https://doi.org/10.37622/ijlr/16.2.2023.173-183

3. Tan, C., et al. Stacked and optimized machine learning for rice yield prediction in Asia. Agricultural Systems, 194, 103259 (2021). https://doi.org/10.1016/j.agsy.2021.103259

4. You, Y., Cao, J., and Zhou, W. A Survey of Change Detection Methods Based on Remote Sensing Images for Multi-Source and Multi-Objective Scenarios. Remote Sensing, 12 (15), 2460 (2020). https://doi.org/10.3390/rs12152460

5. Chandrakumar, T., Avanthica Sri, M.M., Mirdula, K., and K., M. Paddy Yield Forecasting using Regression Techniques. Proceedings of the IEEE Delhi Section Conference (DELCON), 1–6 (2023). https://doi.org/10.1109/DELCON57910.2023.10127256

6. Renju, R.S., Deepthi, P.S., and Chitra, M.T.AReview of CropYield Prediction Strategies basedon Machine Learning and Deep Learning. Proceedings of the International Conference on Computing, Communication, Security and Intelligent Systems (IC3SIS) (2022). https://doi.org/10.1109/IC3SIS54991.2022.9885325

7. Joshua, V., Priyadharson, S.M., and Kannadasan, R. Exploration of Machine Learning Approaches for Paddy Yield Prediction in Eastern Part of Tamilnadu. Agronomy, 11 (10), 2068 (2021). https://doi.org/10.3390/agronomy11102068

8. De Clercq, D., and Mahdi, A. Feasibility of machine learning-based rice yield prediction in India at the district level using climate reanalysis data. arXiv:2403.07967 (2024). Available at: https://arxiv.org/abs/2403.07967

9. Yewle, A.D., Mirzayeva, L., and Karakuş, O. Multi-modal Data Fusion and Deep Ensemble Learning for Accurate Crop Yield Prediction. arXiv:2502.06062 (2025). Available at: https://arxiv.org/abs/2502.06062

10. Kamilaris, A., and Prenafeta-Boldú, F.X. Deep learning in agriculture: A survey. Computers and Electronics in Agriculture, 147, 70–90 (2018). https://doi.org/10.1016/j.compag.2018.02.016

11. Manjunath, M.C., and Palayyan, B.P. An Efficient Crop Yield Prediction Framework Using Hybrid Machine Learning Model. Revue d’Intelligence Artificielle, 37 (4), 1157–1167 (2023). https://doi.org/10.18280/ria.370428

12. Chandraprabha, M., and Rajesh Kumar Dhanraj. Ensemble Deep Learning Algorithm for Forecasting of Rice Crop Yield based on Soil Nutrition Levels. ICST Transactions on Scalable Information Systems, 10 (3), e7–e7 (2023). https://doi.org/10.4108/eetsis.v10i3.2610

13. TNN. PAU-BITS Pilani tie up to marry agri with tech. The Times of India (May 27, 2025). Available at: https://timesofindia.indiatimes.com/city/ludhiana/pau-bits-pilani-tie-up-to-marry-agri-with-tech/articleshow/121446118.cms

14. Guruprasad, R.B., Saurav, K., and Randhawa, S. Machine Learning Methodologies for Paddy Yield Estimation in India: A Case Study. Proceedings of the IEEE International Geoscience and Remote Sensing Symposium (IGARSS), 5447–5450 (2019). https://doi.org/10.1109/IGARSS.2019.8900339

15. Photon Foundation. The Journal of Ethnobiology and Traditional Medicine. Available at: https://sites.google.com/site/photonfoundationorganization/home/the-journal-of-ethnobiology-and-traditional-medicine (accessed March 13, 2024).

16. Karthik Yasaswy, M.Y.S., Manimegalai, T., and Somasundaram, J. Crop Yield Prediction in Agriculture Using Gradient Boosting Algorithm Compared with Random Forest. Proceedings of the International Conference on Cyber Resilience (ICCR) (2022). https://doi.org/10.1109/ICCR56254.2022.9995829

17. Badshah, A., Alkazemi, B.Y., Din, F., Zamli, K.Z., and Haris, M. Crop Classification and Yield Prediction Using Robust Machine Learning Models for Agricultural Sustainability. IEEE Access, 12, 162799– 162813 (2024). https://doi.org/10.1109/ACCESS.2024.3486653

18. Chen, T., and Guestrin, C. XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794 (2016). https://doi.org/10.1145/2939672.2939785

19. Yandex. CatBoost: State-of-the-Art Open-Source Gradient Boosting Library with Categorical Features Support. Available at: https://catboost.ai/ (2019).

20. Rajesh Yamparla, Harisa Sultana Shaik, Naga, M.P., and Srilakshmi Nallamothu. Crop Yield Prediction using Random Forest Algorithm. Proceedings of the 7th International Conference on Communication and Electronics Systems (ICCES) (2022). https://doi.org/10.1109/ICCES54183.2022.9835756

21. Majnik, M., and Bosnić, Z. ROC Analysis of Classifiers in Machine Learning: A Survey. Intelligent Data Analysis, 17 (3), 531–558 (2013). https://doi.org/10.3233/IDA-130592

22. Ahmed, I. What is Hard and Soft Voting in Machine Learning? Medium (May 31, 2023). Available at: https://ilyasbinsalih.medium.com/what-is-hard-and-soft-voting-in-machine-learning-2652676b6a32

23. Lin, T.Y., Han, P.Y., Yin, O.S., How, K.W., and San, H.F. Stacking Ensemble Approach for Churn Prediction: Integrating CNN and Machine Learning Models with CatBoost Meta-Learner. Journal of Engineering Technology and Applied Physics, 5 (2), 99–107 (2023). https://doi.org/10.33093/JETAP.2023.5.2.12