International Journal of Emerging Research in Science, Engineering, and Management
Vol. 2, Issue 3, pp. 194-201, March 2026.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Crop Prediction Based on Characteristics of Agricultural Environment
Masireddy Reddeppa Reddy
B Hima Bindu
R M Srilekha
Pathireddy Lihas Reddy
Basireddy Shalini
Vurandhuru Tharun
Department of CSE, Siddartha Institute of Science and Technology, Puttur, India.
Abstract: Agriculture encounters obstacles because of swift environmental shifts, rendering precise crop forecasting from soil and environmental variables essential. This study employs Machine Learning utilizing optimal feature selection alongside ensemble modeling to address the shortcomings of conventional approaches. Feature significance analysis identifies rainfall (28.5%), temperature (19.8%), and humidity (15.6%) as the predictors. The system employs three foundational models—Random Forest (500 trees), XGBoost (500 iterations), and Support Vector Machine—optimized using Grid Search Cross-Validation and combined using a Soft Voting Classifier. Testing on a dataset comprising 21,600 entries spanning 180 crop varieties shows the Random Forest leading model attains 99.91% accuracy, whereas the soft-voting ensemble reaches 99.49%. A five-fold stratified cross-validation verifies generalization (99.976% ± 0.013%) with per-class F₁-scores between 99.4% and 100.0%, definitively proving that this sophisticated ensemble approach delivers higher prediction accuracy than current single classification techniques, exceeding reported baselines (92–100% on 5–20 crops). The solution is embedded within AgriSmart, a production-grade platform providing real-time crop advice and a 47-millisecond inference delay, creating a foundation crucial for contemporary agricultural strategy.
Keywords: Soft Voting Classifier, Hyperparameter Optimization, Grid Search Cross-Validation, Crop Prediction, Agricultural Advisory.
References:
- G. Ramachandran, S. K. Saravanan, M. Bhanumathi, M. Sangeetha and F. M. H. Fernandez, “Computer Vision for Agricultural Automation – Algorithmic Solutions for Crop Yield Predictions,” 2024 International Conference on Recent Advances in Science and Engineering Technology (ICRASET), B G Nagara,Mandya, India, 2024, pp. 1-5, doi: 10.1109/ICRASET63057.2024.10895915.
- Kosaraju, C. Nama, Y. Deepthi, C. Ramanjamma and P. Chandrakala, “Mirchi Crop Yield Prediction based on Soil and Environmental Characteristics using modified RNN,” 2023 IEEE International Students’ Conference on Electrical, Electronics and Computer Science (SCEECS), Bhopal, India, 2023, pp. 1-5, doi: 10.1109/SCEECS57921.2023.10063004.
- R. Sudhakar, N. V. Pallavi, G. Pushpa, A. P. Sasank Reddy and M. Purushotham, “Crop Yield Prediction Based on the Characteristics of Agricultural Environment,” 2025 International Conference on Computational Robotics, Testing and Engineering Evaluation (ICCRTEE), Virudhunagar, India, 2025, pp. 1-6, doi: 10.1109/ICCRTEE64519.2025.11052989.
- Y. Zhang et al., “A Generative Time-series Data Augmentation Framework Based on Multi-Source Remote Sensing for Early Crop Classification,” in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, doi: 10.1109/JSTARS.2026.3662757.
- S. Vinothkumar, S. Varadhaganapathy, R. Shanthakumari, E. Dhivya, K. B. Jayaharitha and J. Livithasri, “Crop Prediction Based on Factors of the Agricultural Environment Using Machine Learning,” 2024 15th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kamand, India, 2024, pp. 1-6, doi: 10.1109/ICCCNT61001.2024.10725351.
- J. Vemunuri and G. Murthy, “Precision agriculture through biochemical urease-aware crop yield prediction using enhanced fuzzy logic and deep learning,” Smart Agricultural Technology, vol. 12, p. 101340, Aug. 2025, doi: 10.1016/j.atech.2025.101340.
- Md. S. B. Alam, V. Esichaikul, A. Lameesa, S. F. Ahmed, and A. H. Gandomi, “An approach for crop recommendation with uncertainty quantification based on machine learning for sustainable agricultural decision-making,” Results in Engineering, vol. 26, p. 105505, May 2025, doi: 10.1016/j.rineng.2025.105505.
- S. Behera, N. Padhy, R. Panigrahi, and S. K. Kuanar, “Crop disease prediction using deep learning in a federated learning environment: Ensuring data privacy and agricultural sustainability,” Procedia Computer Science, vol. 254, pp. 137–146, Jan. 2025, doi: 10.1016/j.procs.2025.02.072.
- F. Tschurr, A. Walter, and L. Roth, “DyMEP: R package for weather data-based phenology prediction for ten crops,” Computers and Electronics in Agriculture, vol. 237, p. 110536, Jun. 2025, doi: 10.1016/j.compag.2025.110536.
- Tripathi and S. K. Biswas, “Crop yield prediction using ensemble learning with effective data analytics,” Engineering Computations, vol. 43, no. 1, pp. 59–79, Oct. 2025, doi: 10.1108/ec-02-2025-0095.
- Z. Liu, G. Palacios-Navarro, and R. Lacuesta, “Agricultural big data for predicting crop water demand,” Smart Agricultural Technology, vol. 12, p. 101155, Jul. 2025, doi: 10.1016/j.atech.2025.101155.
- W. Xiang et al., “A crop model based on dual attention mechanism for large area adaptive yield prediction,” Smart Agricultural Technology, vol. 11, p. 100957, May 2025, doi: 10.1016/j.atech.2025.100957.
- L. Arslanova, S. Hese, M. Fölsch, F. Scheibler, and C. Schmullius, “Towards CNN-based classification of crop independent agricultural sub-classes,” Smart Agricultural Technology, vol. 12, p. 101284, Aug. 2025, doi: 10.1016/j.atech.2025.101284.
- J. Yan, H. Wu, Z. Diao, Y. Miao, B. Zhang, and C. Zhao, “Recent Developments and Applications of Crop Disease Detection, Prediction, and Early Warning: A review,” Engineering, Nov. 2025, doi: 10.1016/j.eng.2025.10.032.