Rapid detection of perfluorooctanoic acid by surface enhanced Raman spectroscopy and deep learning

• Published in: Talanta (Oxford) Vol. 280; p. 126693
• Main Authors: Huang, Chaoning, Zhang, Ying, Zhang, Qi, He, Dong, Dong, Shilian, Xiao, Xiangheng
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2024
• Subjects: Deep learning; Molecular dynamics simulation; PFOA detection; Surface enhanced Raman spectra; Deep learning; PFOA detection; Surface enhanced Raman spectra; Molecular dynamics simulation
• ISSN: 0039-9140; 1873-3573; 1873-3573
• DOI: 10.1016/j.talanta.2024.126693

Perfluorooctanoic acid (PFOA) has received increasing concerns in recent years due to its wide distribution and potential toxicity. Existing detection techniques of PFOA require complex pre-treatment, therefore often taking several hours. Here, we developed a rapid PFOA detection mode to detect approximate concentrations of PFOA (ranging from 10−15 to 10−3 mol/L) in deionized water, and detecting one sample takes only 20 min. The detection mode was achieved using a deep learning model trained by a large surface enhanced Raman spectra dataset, based on the agglomeration of PFOA with crystal violet. In addition, transfer learning approach was used to fine tune the model, the fine-tuned model was generalizable across water samples with different impurities and environments to determine whether meet the safety standards of PFOA, the accuracy was 96.25 % and 94.67 % for tap water and lake water samples, respectively. The mechanism and specificity of the detection mode were further confirmed by molecular dynamics simulation. Our work provides a promising solution for PFOA detection, especially in the context of the increasingly widespread application of PFOA. Utilizing a deep learning model trained on surface enhanced Raman spectra dataset, a rapid perfluorooctanoic acid detection mode (one sample takes only 20 min) with a wide detection range (from 10-15 to 10-3 mol/L) was developed, molecular dynamics simulations further confirmed the detection mechanism. [Display omitted] •SERS and deep learning were used to detect PFOA.•Detecting PFOA (from 10−15 to 10−3 mol/L) within 20 min.•Detection was based on the agglomeration of PFOA with crystal violet.•The mechanism was confirmed by molecular dynamics simulation.