Leveraging explainable AI for sustainable agriculture: a comprehensive review of recent advances

Abstract In recent years, Artificial Intelligence (AI) has emerged as a disruptive force, transforming industries worldwide through its ability to analyze vast amounts of data and generate informed decisions. The agricultural sector is undergoing a revolutionary transformation driven by the adoption of this technology to enhance productivity, efficiency, and sustainability. However, the lack of transparency in AI models has sparked doubts about their dependability, particularly when applied to critical industries like medicine and agriculture. To address these challenges, research into Explainable Artificial Intelligence (XAI) gained momentum in early 2017. Tools like Local Interpretable Model-agnostic Explanations (LIME), SHapley Additive Explanations (SHAP), and Gradient-weighted Class Activation Mapping (Grad-CAM) helped make progress. These methodologies have proven instrumental in elucidating the internal workings of complex AI models, making their decision-making processes more transparent and comprehensible. This review surveyed current agricultural developments, including using AI to identify plant diseases. We explored articles from Scopus, Web of Science, IEEE Xplore, PubMed, Google Scholar, Agricola, and the Association for Computing Machinery, published between 2017 and 2024. After extracting and filtering, we included publications that satisfied the selection criteria in the review. It has provided an overview of the uses of XAI methods and the difficulties researchers have encountered. In addition, we reviewed recent advancements in machine learning (ML) and deep learning (DL) to find the limitations that agriculturists face in agriculture. We also provide a modern explainable model for identifying plant diseases and show how XAI can be used in agricultural applications. The conclusion of this paper indicates how XAI is necessary for ML, DL models as well as real time monitoring in the agriculture field.