Pesticide contamination in agricultural water systems threatens ecosystem health, water security, and sustainable agriculture. Conventional laboratory analyses are highly accurate but remain expensive, labor-intensive, and unsuitable for continuous field monitoring. This review summarizes recent advances in artificial intelligence (AI)-enabled sensing technologies for the real-time detection of pesticides in irrigation water, rivers, reservoirs, drainage canals, and groundwater. It covers electrochemical sensors, biosensors, hyperspectral imaging, fluorescence spectroscopy, optical sensing, and microfluidic platforms integrated with Internet of Things (IoT) networks, edge computing, and cloud analytics. Particular emphasis is placed on machine learning, deep learning, explainable AI, federated learning, graph neural networks, and multimodal data fusion for contaminant detection, prediction, and risk assessment. The distinctive contribution of this review is providing a pesticide-specific source-to-decision framework that links hydrological transport and chemical transformation to matrix-conditioned sensor responses, AI-assisted signal interpretation, validation maturity, and field deployment, thereby identifying where intelligent analytics can provide a meaningful advantage for pesticide surveillance in agricultural water systems.
* Title and MeSH Headings from MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine.