Rapid detection and quantitative analysis of thiram in fruits using a shape-adaptable flexible SERS substrate combined with deep learning

Abstract

Ensuring food safety necessitates rapid identification of pesticide residues on fruits. Herein, we developed a shape-adaptable flexible surface-enhanced Raman scattering (SERS) substrate, combined with a deep learning algorithm, to quickly detect and quantitatively analyze thiram on fruit surfaces. This SERS substrate was fabricated by depositing silver nanoparticles (Ag NPs) onto a thin, corrugated polydimethylsiloxane (PDMS) film. This innovative design improves physical flexibility, ensuring conformal contact with curved surfaces while achieving high sensitivity, reproducibility, and mechanical robustness. The corrugated Ag NPs@PDMS thin film was able to directly detect thiram at concentrations as low as 10⁻⁷ M on tomato and blueberry peels, exhibiting consistent SERS activity with small interference from the fruit's shape. Furthermore, we developed a one-dimensional convolutional neural network (1D CNN) model, trained using a dataset of SERS signals from thiram, for quantitative analysis. The developed model achieved high prediction accuracy, with a coefficient of determination (R²) of 0.9905 and a root mean square error (RMSE) of 0.1364. The integration of our flexible SERS substrate, which adapts well to irregular surfaces, with the 1D CNN algorithm for quantitative analysis, holds great potential for rapid thiram detection in fruits.