Machine Learning-Assisted Eu(III)-Functionalized HOF-on-HOF\nComposite-Based Sensor Platform for Precise and Visual Identification\nof Multiple Pesticides

Precise and rapid identification\nof pesticides is crucial to ensure\na green environment, food safety, and human health. However, complex\nsample environments often hinder precise identification, especially\nfor simultaneous differentiation of multiple pesticides. Herein, we\nfirst synthesize a Eu(III)-functionalized HOF-on-HOF composite (Eu@PFC-1@MA-TPA)\nand then utilize principal component analysis (PCA) and a machine\nlearning (ML) algorithm to achieve simultaneous identification of\nthe pesticides 2,6-dichloro-4-nitroaniline (DCN) and thiabendazole\n(TBZ) and their mixtures. Eu@PFC-1@MA-TPA displays high quantitative\nidentification ability, which can distinguish single DCN and TBZ as\nlow as 1 μM and their mixtures at 5 μM through PCA. In\naddition, the hydrogel film Eu@PFC-1@MA-TPA/AG is fabricated to monitor\nDCN and TBZ in drinking water, tap water, river water, and apple juice\nwith high sensitivity. Furthermore, based on the obvious fluorescence\ncolor variance of pesticides, Eu@PFC-1@MA-TPA/AG achieves visual and\nin situ imaging detection of single DCN and TBZ and their mixtures.\nMore importantly, we construct an intelligent artificial vision platform\nintegrating Eu@PFC-1@MA-TPA/AG with a DenseNet algorithm, which can\nidentify the concentrations and types of DCN and TBZ and their mixtures\nwithin 1 s with over 98% accuracy. This work develops a precise and\nrapid analysis method for simultaneous identification of multiple\npesticides through combining a visualized fluorescence sensor and\nan ML algorithm.