Explainable machine learning model for predictive maintenance in smart agricultural facilities

Abstract

Machine Learning (ML) models in Smart Agricultural Facilities (SAF) often lack explainability, hindering farmers from taking full advantage of their capabilities. This study tackles this gap by introducing a model that combines a subset of eXplainable Artificial Intelligence (XAI), known as explainable Machine Learning, with Predictive Maintenance (PdM). The model aims to provide both predictive insights and explanations across four key dimensions: (1) data, (2) model, (3) outcome, and (4) end-user. This approach marks a shift in agricultural ML, reshaping how these technologies are understood and applied. The model outperforms related studies, showing quantifiable improvements. Specifically, the Long-Short-Term Memory (LSTM) classifier shows a 5.81% rise in accuracy. The eXtreme Gradient Boosting (XGBoost) classifier exhibits a 7.09% higher F1 score, 10.66% increased accuracy, and a 4.29% increase in Receiver Operating Characteristic-Area Under the Curve (ROC-AUC). These results could lead to more precise maintenance predictions in real-world settings. This study also provides insights into data purity, global and local explanations, and counterfactual scenarios for PdM in SAF. It advances ML by emphasising the importance of explainability beyond traditional accuracy metrics. The results confirm the superiority of the proposed model, marking a significant contribution to PdM in SAF. Moreover, this study promotes the understanding of ML in agriculture, emphasising explainability dimensions. Future research directions are advocated, including multi-modal data integration and implementing Human-in-the-Loop (HITL) systems aimed at improving the effectiveness of ML models and addressing ethical concerns such as Fairness, Accountability, and Transparency (FAT) in agricultural ML applications.