Cross-reactive molecularly imprinted electrochemical sensor arrays with adaptive deep learning for multiplexed PFAS quantification
Abstract
Per- and polyfluoroalkyl substances (PFAS) pose persistent challenges for water monitoring due to their high structural similarity, frequent co-occurrence, and increasingly stringent ultra-trace regulatory limits. Molecularly imprinted polymer (MIP)-based electrochemical sensors provide a promising platform by integrating molecular recognition with electrochemical sensitivity and field deployability. However, quantitative PFAS analysis using MIP-based sensors is often hindered by cross-reactivity, nonlinear signal coupling, and reliance on low-dimensional descriptors, particularly under ultra-trace mixed-PFAS conditions. Besides, machine learning-assisted electrochemical sensing remains insufficiently explored, especially regarding performance degradation at trace concentrations spanning wide logarithmic ranges. Herein, we report a deep learning-assisted molecularly imprinted electrochemical sensing strategy for robust and simultaneous quantification of multiple PFAS. A deliberately cross-reactive sensor array was constructed using three MIP electrodes templated with PFBA, PFHxA, and PFOA, employing o-phenylenediamine as a universal functional monomer. Full differential pulse voltammetry profiles were preserved to generate high-dimensional electrochemical fingerprints rather than relying on peak-based feature. To decode these complex signals, a self-adaptive convolutional-attention-multilayer perceptron (CAM) model was developed, enabling dynamic redistribution of feature…
Read the paper
Related studies
- Nano Biosensors: Properties, applications and electrochemical techniques
- Electrochemically Synthesized MIP Sensors: Applications in Healthcare Diagnostics
- Toward a Harmonization for Using in situ Nutrient Sensors in the Marine Environment
- Electrochemical determination of rutin by using NiFe2O4 nanoparticles-loaded reduced graphene oxide
- Application of Polyoxometalate-based composites for sensor systems: A review
- Sensitive Electrochemical and Thermal Detection of Human Noroviruses Using Molecularly Imprinted Polymer Nanoparticles Generated against a Viral Target
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.