A Soil-Aware Hybrid AI Model for Precision Crop Recommendation and Yield Forecasting
Received: 31 January 2026 | Revised: 17 March 2026, 31 March 2026, and 12 April 2026 | Accepted: 17 April 2026 | Online: 21 May 2026
Corresponding author: Shilpa Mangesh Pande
Abstract
Matching crops to their specific soil type remains a major challenge for Indian farmers. This study proposes a model that uses crop yield, soil, and climatic data to guide optimal crop selection, improving productivity and lowering errors. Relevant environmental factors are identified through feature engineering to enhance yield prediction accuracy using the Sequential Forward Feature Selection Algorithm (SFFSA), Random Forest Variable Importance Algorithm (RFVIA), and Sequential Back Elimination Feature Selection Algorithm (SBEFSA). This study predicts the best crop to grow given a specific set of environmental conditions by employing a Machine Learning (ML) approach. A unified AI-enabled framework is created to help Indian farmers select the optimal crop to cultivate and project the Crop Yield (CY) using a hybrid system that combines Artificial Neural Network (ANN) and Multiple Linear Regression (MLR). This proposed approach employs a residual learning framework that separates linear agronomic effects from nonlinear interactions. ANN performs hyperparameter sensitivity analysis to assess the impact of learning rate and hidden neuron count to validate the performance. The results indicate that the Hybrid algorithm approach outperforms standard ML algorithms, with improvements up to 2.2-fold in RMSE and around 1.5-fold in MAE. The proposed work even predicts the best-suited fertilizer to grow the crops based on soil contents.
Keywords:
hybrid algorithm, crop yield, crop recommendation, Multiple Linear Regression (MLR), Artificial Neural Network (ANN), feature selection, Machine Learning (ML)References
S. Kiruthika and D. Karthika, "IoT-Based Professional Crop Recommendation System Using a Weight-Based Long-Term Memory Approach," Measurement: Sensors, vol. 27, Jun. 2023, Art. no. 100722.
S. P. Raja, B. Sawicka, Z. Stamenkovic, and G. Mariammal, "Crop Prediction Based on Characteristics of the Agricultural Environment Using Various Feature Selection Techniques and Classifiers," IEEE Access, vol. 10, pp. 23625–23641, 2022.
P. S. Maya Gopal and R. Bhargavi, "Selection of Important Features for Optimizing Crop Yield Prediction," International Journal of Agricultural and Environmental Information Systems, vol. 10, no. 3, pp. 54–71, Jul. 2019.
M. Abdel-Salam, N. Kumar, and S. Mahajan, "A Proposed Framework for Crop Yield Prediction Using Hybrid Feature Selection Approach and Optimized Machine Learning," Neural Computing and Applications, vol. 36, no. 33, pp. 20723–20750, Nov. 2024.
R. Kavitha, M. Kavitha, and R. Srinivasan, "Crop Recommendation in Precision Agriculture Using Supervised Learning Algorithms," in 2022 3rd International Conference for Emerging Technology (INCET), Belgaum, India, May 2022, pp. 1–4.
K. Bakthavatchalam et al., "IoT Framework for Measurement and Precision Agriculture: Predicting the Crop Using Machine Learning Algorithms," Technologies, vol. 10, no. 1, Jan. 2022, Art. no. 13.
M. Venkatanaresh and I. Kullayamma, "Deep Learning Based Concurrent Excited Gated Recurrent Unit for Crop Recommendation Based on Soil and Climatic Conditions," Multimedia Tools and Applications, vol. 83, no. 24, pp. 64109–64138, Jan. 2024.
P. S. S. Gopi and M. Karthikeyan, "Red Fox Optimization with Ensemble Recurrent Neural Network for Crop Recommendation and Yield Prediction Model," Multimedia Tools and Applications, vol. 83, no. 5, pp. 13159–13179, Jul. 2023.
C. Raju, D. V. Ashoka, and B.V. Ajay Prakash, "CropCast: Harvesting the Future with Interfused Machine Learning and Advanced Stacking Ensemble for Precise Crop Prediction," Kuwait Journal of Science, vol. 51, no. 1, Jan. 2024, Art. no. 100160.
M. Gallardo, M. T. Peña-Fleitas, C. Giménez, F. M. Padilla, and R. B. Thompson, "Adaptation of VegSyst-DSS for Macronutrient Recommendations of Fertigated, Soil-Grown, Greenhouse Vegetable Crops," Agricultural Water Management, vol. 278, Mar. 2023, Art. no. 107973.
S. Fenz, T. Neubauer, J. Heurix, J. K. Friedel, and M.-L. Wohlmuth, "AI- and Data-driven Pre-Crop Values and Crop Rotation Matrices," European Journal of Agronomy, vol. 150, Oct. 2023, Art. no. 126949.
N. Subash et al., "Relevance of Climatological Information on Spatial and Temporal Variability of Indian Summer Monsoon Rainfall (ISMR) in Recent El Niño Years and Its Impact on Four Important Kharif Crops Over India," Climate Services, vol. 30, Apr. 2023, Art. no. 100370.
M. Y. Shams, S. A. Gamel, and F. M. Talaat, "Enhancing Crop Recommendation Systems with Explainable Artificial Intelligence: A Study on Agricultural Decision-Making," Neural Computing and Applications, vol. 36, no. 11, pp. 5695–5714, Apr. 2024.
Y. Akkem, S. K. Biswas, and A. Varanasi, "Streamlit-Based Enhancing Crop Recommendation Systems with Advanced Explainable Artificial Intelligence for Smart Farming," Neural Computing and Applications, vol. 36, no. 32, pp. 20011–20025, Nov. 2024.
A. M. Joshi and S. Patel, "A CNN-Bidirectional LSTM Approach for Price Forecasting of Agriculture Commodities in Gujarat," in 2022 International Conference on Applied Artificial Intelligence and Computing (ICAAIC), Salem, India, May 2022, pp. 266–272.
R. L. Manogna, V. Dharmaji, and S. Sarang, "A Novel Hybrid Neural Network-Based Volatility Forecasting of Agricultural Commodity Prices: Empirical Evidence from India," Journal of Big Data, vol. 12, no. 1, Apr. 2025, Art. no. 85.
V. Fassa, N. Pricca, G. Cabassi, L. Bechini, and M. Corti, "Site-Specific Nitrogen Recommendations’ Empirical Algorithm for Maize Crop Based on the Fusion of Soil and Vegetation Maps," Computers and Electronics in Agriculture, vol. 203, Dec. 2022, Art. no. 107479.
P. E. Rubini and P. Kavitha, "Prediction of the Right Crop for the Right Soil and Recommendation of Fertiliser Usage by Machine Learning Algorithm," International Journal of Computer Applications in Technology, vol. 69, no. 2, 2022, Art. no. 163.
P. Srinivas and A. Suresh, "CNN-LSTM Model for Cotton Yield Prediction Using Remote Sensing Data," in 2025 6th International Conference on Data Intelligence and Cognitive Informatics (ICDICI), Tirunelveli, India, Jul. 2025, pp. 515–520.
N. M. Basavaraju, U. B. Mahadevaswamy, and M. Srikantaswamy, "Optimized Crop Yield Forecasting Using the Naive Bayes Regression Algorithm in Smart Agriculture," Engineering, Technology & Applied Science Research, vol. 15, no. 6, pp. 28995–29001, Dec. 2025.
"District-Wise Season-Wise Crop Production Statistics from 1997." Ministry of Agriculture and Farmers Welfare, Government of India, 2013, [Online]. Available: https://www.data.gov.in/resource/district-wise-season-wise-crop-production-statistics-1997.
"Daily District-Wise Rainfall Data." India Meteorological Department, Ministry of Earth Sciences, Government of India, Sep. 2022, [Online]. Available: https://www.data.gov.in/resource/daily-district-wise-rainfall-data.
"State/UT-wise Number of Soil Health Cards Issued to the Farmers in the Country under Soil Health Card (SHC) Scheme from 2019-20 to 2023-24." Ministry of Agriculture and Farmers Welfare, Government of India, Oct. 2024, [Online]. Available: https://www.data.gov.in/resource/stateut-wise-number-soil-health-cards-issued-farmers-country-under-soil-health-card-shc.
S. P. Sudha and J. B. S. Loret, "A Review on Machine Learning-based Precision Agriculture Techniques for Crop Farming Monitoring with IoT," Discover Environment, vol. 4, no. 1, Jan. 2026, Art. no. 10.
M. Baishya and L. Dutta, "Tiny ML-Based Crop Recommendation System for Precision Agriculture 5.0," Smart Agricultural Technology, vol. 12, Dec. 2025, Art. no. 101247.
Downloads
How to Cite
License
Copyright (c) 2026 Shilpa Mangesh Pande, Prem Kumar Ramesh
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain the copyright and grant the journal the right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) after its publication in ETASR with an acknowledgement of its initial publication in this journal.
