Machine Learning-Enhanced SERS Sensor Using Microgroove Structures for Enriching and Confining Nanoplastics in Localized 3D Hotspots

作者：Zilong Yan, Maofeng Zhang, Xue Chen, Cheng Ye, Zhuang Ding, Jiang Yang, Guangcheng Xi, Wei Zhang · 发表于：Analytical Chemistry · 年份：2026 · DOI：10.1021/acs.analchem.6c00573 · 被引用次数：1 · 研究领域：Gold and Silver Nanoparticles Synthesis and Applications、Advanced Sensor and Energy Harvesting Materials、Laser-Ablation Synthesis of Nanoparticles

M for 4-MBA, with excellent spatial uniformity (RSD = 7.55%). Furthermore, the sensor successfully detected NPs of different sizes and types, including polystyrene (PS), poly(methyl methacrylate), and polyethylene terephthalate, with an LOD of 20 ng/mL for 100 nm PS. In practical analysis, the sensor achieved LODs of 360 ng/mL in river water and 2.94 μg/g in the fish matrix for PS. Additionally, ML-assisted surface-enhanced Raman spectroscopy (SERS) analysis using K-nearest neighbor, gradient boosting decision trees, convolutional neural networks (CNN), and Transformer models enabled precise classification; despite being trained on only 800 SERS spectra from deionized water, the CNN achieves 100% accuracy in river water and 99% accuracy in the fish matrix. The strategic harmonization of microgroove-induced confinement enrichment, precise localization, and 3D hotspots within microcavities, combined with small-data set machine learning, provides a field-ready solution for the detection of trace pollutants in real-world scenarios.