An Explainable AI-Driven Decision Support Framework for Precision Agriculture, Environmental Monitoring, Crop Prediction, and Sustainable Resource Management
Computer and Decision Making An International Journal · 08.11.2026
DOI: 10.1922/comdem.v3i8s.19177 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computer and Decision Making An International Journal, online erschienen am 08.11.2026. Verfasst von M Vijay Sekhar Babu und 5 weiteren Autor:innen.
Abstract (Originalsprache)
Agricultural decision-making increasingly requires predictive systems that combine crop suitability with transparent interpretation of soil, environmental, and resource conditions. This study developed an explainable artificial intelligence-driven decision-support framework for precision agriculture using a cleaned dataset of 2,200 observations representing 22 crop classes and 23 agricultural variables. Soil nutrients, climatic conditions, environmental indicators, and resource-management attributes were characterized before predictive modelling. Random Forest, XGBoost, Gradient Boosting, and Support Vector Machine classifiers were evaluated using a stratified 80:20 train-test split. Model performance was assessed through accuracy, macro precision, macro recall, macro F1-score, and weighted F1-score. Random Forest achieved the strongest held-out performance, with accuracy and macro F1 of 1.000, followed by Gradient Boosting, XGBoost, and Support Vector Machine. Explainability analysis using SHAP identified humidity, nitrogen, potassium, rainfall, and phosphorus as the dominant contributors to crop predictions. Correlation analysis showed that most predictor relationships were weak to moderate, supporting complementary information across feature domains. The findings demonstrate that interpretable machine learning can connect crop prediction with environmental assessment and resource-aware agricultural decision support. The framework provides a reproducible basis for precision crop selection while retaining transparent evidence about the variables underlying model recommendations in practical farming contexts and planning applications.
Zitieren
APA
Babu, M. V. S., Rao, P. J., Singh, G., Biradar, D. S. S., Parmar, B. M., & Selvarasu, M. A. (2026). An Explainable AI-Driven Decision Support Framework for Precision Agriculture, Environmental Monitoring, Crop Prediction, and Sustainable Resource Management. Computer and Decision Making An International Journal. https://doi.org/10.1922/comdem.v3i8s.19177
Vancouver
Babu MVS, Rao PJ, Singh G, Biradar DSS, Parmar BM, Selvarasu MA. An Explainable AI-Driven Decision Support Framework for Precision Agriculture, Environmental Monitoring, Crop Prediction, and Sustainable Resource Management. Computer and Decision Making An International Journal. 2026. doi:10.1922/comdem.v3i8s.19177
BibTeX
@article{Babu2026,
author = {Babu, M Vijay Sekhar and Rao, P Jagadeeswara and Singh, Gurpreet and Biradar, Dr. Sharanagoud S and Parmar, Bhupendra M. and Selvarasu, Mr. A.},
title = {An Explainable AI-Driven Decision Support Framework for Precision Agriculture, Environmental Monitoring, Crop Prediction, and Sustainable Resource Management},
journal = {Computer and Decision Making An International Journal},
year = {2026},
doi = {10.1922/comdem.v3i8s.19177}
}
EUVIMED