An Intelligent Machine-Learning-Driven Metalloporphyrin Covalent Organic Framework Sensor Array for Pesticide...

Area of Science:

• Analytical Chemistry
• Materials Science
• Environmental Science

Background:

• Pesticide residue detection is crucial for environmental protection and human health.
• Current methods for rapid and accurate pesticide identification face significant challenges.

Purpose of the Study:

• To develop a novel colorimetric sensor array for the rapid and accurate discrimination of multiple pesticide residues.
• To utilize metalloporphyrin covalent organic frameworks (MCOFs) as catalytic sites for enhanced detection.

Main Methods:

• Fabrication of a colorimetric sensor array using three distinct MCOF nanozymes.
• Application of Linear Discriminant Analysis (LDA) for pesticide differentiation.
• Integration of Random Forest (RF) algorithm for analysis in complex matrices.

Main Results:

• The MCOF nanozyme array showed 2.4-4.5 fold enhanced discrimination activity compared to metal-free COFs.
• Successfully differentiated five pesticides in the 10-100 nM range with limits of detection as low as 2.19 nM.
• Achieved 94.1% accuracy in river water and over 95% accuracy in tomato samples for complex pesticide residue identification.

Conclusions:

• The MCOF-based sensor array offers a simple, convenient, and promising approach for pesticide residue analysis.
• This technology enables hierarchical screening and prediction of multiple pesticide residues.
• The developed platform is suitable for environmental and food monitoring applications.