Guokun Yang, Hengyu Xiao, Hao Gao, Baicheng Zhang, Wei Hu, Cheng Chen, Qinyu Qiao, Guozhen Zhang, Shuo Feng, Daobin Liu, Yang Wang, Jun Jiang, Yi Luo
{"title":"Repairing Noise-Contaminated Low-Frequency Vibrational Spectra with an Attention U-Net","authors":"Guokun Yang, Hengyu Xiao, Hao Gao, Baicheng Zhang, Wei Hu, Cheng Chen, Qinyu Qiao, Guozhen Zhang, Shuo Feng, Daobin Liu, Yang Wang, Jun Jiang, Yi Luo","doi":"10.1021/jacs.4c10893","DOIUrl":null,"url":null,"abstract":"Low-frequency vibrational modes in infrared (IR) and Raman spectra, often termed molecular fingerprints, are sensitive probes of subtle structural changes and chemical interactions. However, their inherent weakness and susceptibility to environmental interference make them challenging to detect and analyze. To tackle this issue, we developed a deep learning denoising protocol based on an attention-enhanced U-net architecture. This model leverages the inherent correlations between high- and low-frequency vibrational modes within a molecule, effectively reconstructing low-frequency spectral features from their high-frequency counterparts. We demonstrate the effectiveness of this method by recovering low-frequency signals of <i>trans</i>-1,2-bis(4-pyridyl)ethylene (BPE) adsorbed on an Ag surface, a representative system for surface enhancement Raman spectroscopy (SERS). Notably, the trained model exhibits promising transferability to SERS spectra acquired under different surface and external field conditions. Furthermore, we applied this method to experimental IR and Raman spectra of BPE, achieving high-quality, low-frequency spectral recovery.","PeriodicalId":49,"journal":{"name":"Journal of the American Chemical Society","volume":null,"pages":null},"PeriodicalIF":14.4000,"publicationDate":"2024-10-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the American Chemical Society","FirstCategoryId":"92","ListUrlMain":"https://doi.org/10.1021/jacs.4c10893","RegionNum":1,"RegionCategory":"化学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"CHEMISTRY, MULTIDISCIPLINARY","Score":null,"Total":0}
引用次数: 0
Abstract
Low-frequency vibrational modes in infrared (IR) and Raman spectra, often termed molecular fingerprints, are sensitive probes of subtle structural changes and chemical interactions. However, their inherent weakness and susceptibility to environmental interference make them challenging to detect and analyze. To tackle this issue, we developed a deep learning denoising protocol based on an attention-enhanced U-net architecture. This model leverages the inherent correlations between high- and low-frequency vibrational modes within a molecule, effectively reconstructing low-frequency spectral features from their high-frequency counterparts. We demonstrate the effectiveness of this method by recovering low-frequency signals of trans-1,2-bis(4-pyridyl)ethylene (BPE) adsorbed on an Ag surface, a representative system for surface enhancement Raman spectroscopy (SERS). Notably, the trained model exhibits promising transferability to SERS spectra acquired under different surface and external field conditions. Furthermore, we applied this method to experimental IR and Raman spectra of BPE, achieving high-quality, low-frequency spectral recovery.
期刊介绍:
The flagship journal of the American Chemical Society, known as the Journal of the American Chemical Society (JACS), has been a prestigious publication since its establishment in 1879. It holds a preeminent position in the field of chemistry and related interdisciplinary sciences. JACS is committed to disseminating cutting-edge research papers, covering a wide range of topics, and encompasses approximately 19,000 pages of Articles, Communications, and Perspectives annually. With a weekly publication frequency, JACS plays a vital role in advancing the field of chemistry by providing essential research.