Srivastava, SonaliWang, WeiZhou, WeiJin, MingVikesland, Peter J.2025-03-042025-03-042024-11-130013-936Xhttps://hdl.handle.net/10919/124774Surface-enhanced Raman spectroscopy (SERS) has gained significant attention for its ability to detect environmental contaminants with high sensitivity and specificity. The cost-effectiveness and potential portability of the technique further enhance its appeal for widespread application. However, challenges such as the management of voluminous quantities of high-dimensional data, its capacity to detect low-concentration targets in the presence of environmental interferents, and the navigation of the complex relationships arising from overlapping spectral peaks have emerged. In response, there is a growing trend toward the use of machine learning (ML) approaches that encompass multivariate tools for effective SERS data analysis. This comprehensive review delves into the detailed steps needed to be considered when applying ML techniques for SERS analysis. Additionally, we explored a range of environmental applications where different ML tools were integrated with SERS for the detection of pathogens and (in)organic pollutants in environmental samples. We sought to comprehend the intricate considerations and benefits associated with ML in these contexts. Additionally, the review explores the future potential of synergizing SERS with ML for real-world applications.Pages 20830-2084819 page(s)application/pdfenCreative Commons Attribution 4.0 InternationalSurface-Enhanced Raman SpectroscopyMachine LearningEnvironmental PollutantsEnvironmental PollutantsSpectrum Analysis, RamanMachine LearningArticle - Refereedhttps://doi.org/10.1021/acs.est.4c067375847Vikesland, Peter [0000-0003-2654-5132]Zhou, Wei [0000-0002-5257-3885]395373821520-5851