A Comprehensive Review of Deep Learning-Based Anomaly Detection Methods for Precision Agriculture

Anomaly detection is a challenging problem in various application domains of Artificial Intelligence, such as in video surveillance, the Internet of Things, and notably, precision agriculture. The effectiveness of anomaly detection in each field is intricately linked to the domain-specific data, adhering, at the same time, to the core objective of detecting outliers. In the precision agriculture domain, anomalies range from plant diseases in image data to fluctuating environmental conditions in time-series datasets. This review provides a detailed examination of deep learning-based anomaly detection methods within precision agriculture, adopting the PRISMA methodology for a structured and comprehensive analysis. We employ a novel taxonomy categorizing recent literature by agricultural application, anomaly relevance, data modality, deep learning architecture, supervision level, and dataset usage. Our findings highlight a predominant reliance on visual data and uncover a potential alignment between methods originally devised for classification or detection and the anomaly detection challenge. The review also signals a pressing need for large-scale datasets to address precision agriculture challenges effectively. By mapping the current landscape and suggesting directions for future research, our work aims to facilitate advancements in anomaly detection techniques, enabling enhanced decision-making and operational efficiency in precision agriculture.