article · IEEE Access
Artificial intelligence systems used in smart agricultural facilities frequently lack transparency, which prevents farmers from making full use of predictive technologies. A new framework integrates explainable artificial intelligence with predictive maintenance, providing actionable insights across data, model, outcome, and end-user levels. The system delivers global and local explanations alongside counterfactual scenarios to clarify automated decisions. In comparative evaluations, the approach outperforms earlier benchmarks. A Long Short-Term Memory classifier achieved a 5.81 per cent increase in accuracy, whilst an eXtreme Gradient Boosting model recorded a 10.66 per cent rise in accuracy, a 7.09 per cent gain in F1 score, and a 4.29 per cent lift in area under the curve. By balancing predictive performance with interpretable outputs, the architecture supports more reliable maintenance forecasting for agricultural infrastructure.
Modern agricultural operations increasingly rely on automated machinery and smart facilities, yet complex algorithms can be difficult for operators to trust. Providing clear, interpretable explanations alongside maintenance forecasts helps facility managers understand why equipment failures are predicted. This balance of transparency and heightened predictive accuracy can minimise unexpected downtime and assist operational decision-making in agricultural production.
The framework is intended for operators and managers of smart agricultural facilities seeking clearer oversight of machinery health. Although tested against baseline classifiers with quantifiable accuracy gains, the work remains at an applied research stage. Further development, such as multi-modal data integration and human-in-the-loop interfaces, is highlighted as necessary before commercial deployment in operational farm management software.
AI-generated from the published abstract. Always read the original work before citing.
Artificial Intelligence (AI) in Smart Agricultural Facilities (SAF) often lacks explainability, hindering farmers from taking full advantage of their capabilities. This study tackles this gap by introducing a model that combines eXplainable Artificial Intelligence (XAI), with Predictive Maintenance (PdM). The model aims to provide both predictive insights and explanations across four key dimensions, namely data, model, outcome, and end-user. This approach marks a shift in agricultural AI, 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 AI 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 AI 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 AI and addressing ethical concerns such as Fairness, Accountability, and Transparency (FAT) in agricultural AI applications.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1109/access.2024.3365586
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
