Agropredml: Crop Yield Prediction In Smart Agriculture Using Machine Learning
DOI:
https://doi.org/10.29284/zqtvr998Keywords:
Crop Yield Prediction, Smart Agriculture, Machine Learning, Deep Feature Selection, Genetic Algorithm, Quantum Differential Evolution, Support Vector Regression.Abstract
With the accelerating global demand for food, variability in climate, and the need for efficient resource use, the agricultural sector is increasingly using data-driven strategies. Crop yield prediction is a challenging task as agricultural data is spatially and temporally nonlinear and heterogeneous. To tackle these issues, the paper presents a hybrid DFS–GA + QDE–SVR framework for rice yield prediction. The methodology combines Deep Feature Scoring (DFS) with a Genetic Algorithm (GA) to select informative and non-redundant features, which is subsequently followed by Quantum Differential Evolution (QDE) for fine-tuning Support Vector Regression (SVR) hyperparameters. The study examined the practical utility of the proposed model on a real agricultural dataset and compared it with the existing FMIG–RFE + ICOA–SVR baseline. The experimental results indicate that the proposed framework for predicting streamflow leads to a large enhancement in prediction performance, as RMSE and MAE drop by 28.45% and 47.01% and R² is 0.4881. The chosen features are very agronomically relevant, improving interpretability. The proposed solution is suitable for offline crop yield prediction and agricultural advisory systems because, despite its high computational cost, it improves accuracy and generalization.
References
1. Alzubi, A. A., &Galyna, K. (2023). Artificial Intelligence and Internet of Things for Sustainable Farming and Smart Agriculture. IEEE Access.
2. Katarya, R., Raturi, A., Mehndiratta, A., &Thapper, A. (2020). Impact of Machine Learning Techniques in Precision Agriculture. ICETCE-2020.
3. Muniasamy, A. (2020). Machine Learning for Smart Farming: A Focus on Desert Agriculture. ICCIT-1441, University of Tabuk.
4. Liu, F., & Yan, X. (2022). The application of Machine Learning and IOT in Smart Agriculture. GCRAIT.
5. Izna, A., Sharma, A., & Pandey, R. P. (2022). Application of IoT and ML Towards Smart Agriculture in India. 11th International Conference on System Modeling.
6. Senthil, S. S., Kumar, R. R., &Jabakumar, A. K. (2022). Smart Agriculture Management Using NB-IOT. ICSTCEE.
7. Zancanaro, A., Cisotto, G., Tegegn, D. D., & Manzoni, S. L. (2022). Variational Autoencoder for Early Stress Detection. MetroAgriFor.
8. Alfred, R., Obit, J. H., & Chin, C. P. Y. (2021). Paddy Rice Smart Farming with Big Data and ML. IEEE Access.
9. Ünal, Z. (2017). Smart Farming and Deep Learning – A Bibliographical Analysis. IEEE Access.
10. Basnet, B., & Bang, J. (2018). Knowledge-Intensive Agriculture: A Review. Journal of Sensors.
11. Sahu, P. K., Malla, S., Khuntia, M., Rath, S., & Nayak, M. (2024). Smart Crop Prediction Using ML Through IoT. Journal of Theoretical and Applied Information Technology.
12. Bhati, R., Gaur, S., & Kamil, A. (2024). Integrated Prediction Model for Crop Yield using ML and IoT. ICDT 2024.
13. Kumar, S., Shinde, V. D., Goradiya, U. B., Patil, A. A., &Verman, S. P. (2024). Improved Crop Yields via Ensemble Learning. AUTOCOM 2024.
14. Goel, M., & Pandey, M. (2024). Crop Yield Prediction using AI – A Review. ICDT 2024.
15. Haque, F. F., Abdelgawad, A., Yanambaka, V. P., &Yelamarthi, K. (2020). Crop Yield Prediction Using Deep Neural Network. IEEE 11th IC on SMART Trends.
16. Sharma, A. K., &Rajawat, A. S. (2022). Crop Yield Prediction using Hybrid Deep Learning. ICAIS-2022.
17. Islam, A., Arefin, R., Saim, M. A. H., Mahin, J. A., Nizamee, F., &Delowar, K. E. (2023). Crop Yield Prediction Using IoT and ML Fusion. ICCIT 2023.
18. Kallenberg, M. G. J., Maestrini, B., &Athanasiadis, I. N. (2023). Hybrid Meta-Modeling in Agriculture. arXiv:2307.13466.
19. Abdel-salam, M., Kumar, N., & Mahajan, S. (2024). Hybrid Feature Selection with Optimized SVR. Neural Computing and Applications. https://doi.org/10.1007/s00521-024-10226-x
20. Manjunath, M. C., &Palayyan, B. P. (2023). Efficient Crop Yield Prediction Framework. Revue d'IntelligenceArtificielle, 37(4), 1057–1067.
21. Li, Y., Guan, L., Jin, J., Wang, Y., & Guo, Y. (2023). A Data-Driven Crop Model for Maize Yield. Communications Biology, 6(1), 48. https://doi.org/10.1038/s42003-023-04833-y
22. Cunha, R. L. de F., Silva, B., &Avegliano, P. B. (2023). AI-based Crop Yield Forecasting. arXiv:2306.10121.
23. Morales, A., & Villalobos, F. J. (2023). Machine Learning for Historical and Future Crop Yield Prediction. Frontiers in Plant Science, 14. https://doi.org/10.3389/fpls.2023.1128388
Downloads
Published
Issue
Section
License
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
