Zhao Xiaoyu, Wang Yuxia, Liu Yuting, Chen Xinyi, Cheng Mingyu, Wang Yaxin, Wen Jiahong, Gao Renxian, Zhang Kun, Zhang Fengyi, Cui Rufei, Zhang Yongjun, Wang Zengyao, Ai Bin
College of Materials and Environmental Engineering, Hangzhou Dianzi University, Hangzhou, Zhejiang, 310018, P. R. China.
School of Microelectronics and Communication Engieerimng, Chongqing Key Laboratory of Bio-perception & Intelligent Information Processing, Chongqing University, Chongqing, 400044, P. R. China.
Adv Sci (Weinh). 2025 Jul;12(26):e2501793. doi: 10.1002/advs.202501793. Epub 2025 Apr 25.
Surface-Enhanced Raman Scattering (SERS) holds significant promise for trace-level molecular detection but faces challenges in achieving reliable quantitative analysis due to signal variability caused by non-uniform "hot spots" and external factors. To address these limitations, a novel SERS platform based on gradient nanostructures is developed using shadow sphere lithography, enabling the acquisition of diverse spectral features from a single analyte concentration under identical conditions. The gradient design minimizes fabrication variability and enhances spectral diversity, while the machine learning (ML) model trained on the multi-spectral dataset significantly outperformed traditional single-spectrum approaches, with the test Mean Squared Error (MSE) reduced by 84.8% and the coefficient of determination (R) improved by 61.2%. This strategy captures subtle spectral variations, improving the precision, robustness, and reproducibility of SERS-based quantification, paving the way for its reliable application in real-world scenarios.
表面增强拉曼散射（SERS）在痕量分子检测方面具有巨大潜力，但由于非均匀“热点”和外部因素导致的信号变异性，在实现可靠的定量分析方面面临挑战。为了解决这些限制，利用阴影球光刻技术开发了一种基于梯度纳米结构的新型SERS平台，能够在相同条件下从单一分析物浓度获取多样的光谱特征。梯度设计将制造变异性降至最低并增强了光谱多样性，而在多光谱数据集上训练的机器学习（ML）模型显著优于传统的单光谱方法，测试均方误差（MSE）降低了84.8%，决定系数（R）提高了61.2%。该策略捕捉到了细微的光谱变化，提高了基于SERS的定量分析的精度、稳健性和可重复性，为其在实际场景中的可靠应用铺平了道路。
