FERTILIZER RECOMMENDATION AND SOIL HEALTH ANALYSIS USING EXPLAINABLE AI

Author

Dr. Jai Ruby, M. Saranya


Abstract

 Agriculture plays an important role in ensuring food security and supporting economic development. Maintaining soil fertility and selecting suitable fertilizers are essential for sustainable crop production. However, fertilizer requirements vary depending on soil properties, nutrient availability, crop type, growth stage, environmental conditions, and agricultural practices. Improper fertilizer application can cause nutrient imbalances, reduce crop productivity, increase cultivation costs, and affect soil quality. Therefore, an intelligent and interpretable approach is needed to support appropriate fertilizer selection and soil health assessment.

This paper presents an Explainable Artificial Intelligence (XAI)-based approach for fertilizer recommendation and soil health analysis using deep learning techniques. The study uses an agricultural dataset containing 10,000 records, 19 input features, and seven fertilizer categories: Urea, DAP, MOP, NPK, SSP, Compost, and Zinc Sulphate. Artificial Neural Network (ANN), Deep Neural Network (DNN), and TabNet algorithms are considered for fertilizer classification and performance comparison. The approach analyses soil characteristics, nutrient levels, crop information, environmental conditions, and agricultural practices to identify suitable fertilizer categories. In addition, Explainable AI techniques, including SHapley Additive exPlanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME), are used to interpret model predictions and identify the important features influencing fertilizer recommendations. Soil health assessment is also included to provide information about soil conditions and nutrient status. By combining deep learning-based classification with explainable techniques, this research aims to improve prediction transparency, support informed fertilizer selection, and contribute to sustainable agricultural practices.


Keywords

Fertilizer Recommendation, Deep Learning, Soil Health Analysis, Explainable Artificial Intelligence, Deep Neural Network, SHAP, LIME, Precision Agriculture.



Full Text:

Download Paper PDF


References


  1. Lundberg, S. M., and Lee, S. I. (2017). “A Unified Approach to Interpreting Model Predictions.” Advances in Neural Information Processing Systems, 30.
  2. Ribeiro, M. T., Singh, S., and Guestrin, C. (2016). “‘Why Should I Trust You?’ Explaining the Predictions of Any Classifier.” Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 1135–1144.
  3. Arik, S. Ö., and Pfister, T. (2021). “TabNet: Attentive Interpretable Tabular Learning.” Proceedings of the AAAI Conference on Artificial Intelligence, 35(8), pp. 6679–6687.
  4. LeCun, Y., Bengio, Y., and Hinton, G. (2015). “Deep Learning.” Nature, 521, pp. 436–444.
  5. Venkateswara, S. M., and Padmanaban, J. (2025). “Interpretable Deep Learning Models for Independent Fertilizer and Crop Recommendation.” Scientific Reports, 15, Article 41721. https://doi.org/10.1038/s41598-025-26910-4
  6. Pedregosa, F., et al. (2011). “Scikit-learn: Machine Learning in Python.” Journal of Machine Learning Research, 12, pp. 2825–2830.
  7. Abekoon, T., Sajindra, H., Rathnayake, N., Ekanayake, I. U., Jayakody, A., and Rathnayake, U. (2025). “A Novel Application with Explainable Machine Learning (SHAP and LIME) to Predict Soil N, P, and K Nutrient Content in Cabbage Cultivation.” Smart Agricultural Technology, 11, Article 100879. https://doi.org/10.1016/j.atech.2025.100879
  8. Yaganteeswarudu, A., Biswas, S. K., Aruna, V., and Tripathi, D. (2025). “Enhancing Transparency in Smart Farming: Local Explanations for Crop Recommendations Using LIME.” Procedia Computer Science, 258, pp. 1993–2005. https://doi.org/10.1016/j.procs.2025.04.450
  9. Dey, B., Ferdous, J., and Ahmed, R. (2024). “Machine Learning Based Recommendation of Agricultural and Horticultural Crop Farming in India Under the Regime of NPK, Soil pH and Three Climatic Variables.” Heliyon, 10(3), Article e25112. https://doi.org/10.1016/j.heliyon.2024.e25112
  10. Xu, X., Liu, Q., Liu, Y., Li, Y., Chen, Y., Lei, T., Kuzyakov, Y., Zhang, W., Chen, J., and Ge, T. (2025). “Novel Soil Health Assessment Framework for Legume-Based Rotation Farmland by Interpretable Machine Learning with Causal Inference.” Computers and Electronics in Agriculture, 239, Part B, Article 111011. https://doi.org/10.1016/j.compag.2025.111011

Share your valuable work from Social Media Buttons