Knowledge Management System Of Guangzhou Institute of Geochemistry，CAS
Hong, Yihang1,2; Zhang, Yan-Lin1,3; Bao, Mengying4; Fan, Mei-Yi1,3,5; Lin, Yu-Chi1,3; Xu, Rongshuang1,3; Shu, Zhiyang6; Wu, Ji-Yan1,3; Cao, Fang1,3; Jiang, Hongxing7,8; Cheng, Zhineng7,8; Li, Jun7,8 ; Zhang, Gan7,8
| |
| Nitrogen-Containing Functional Groups Dominate the Molecular Absorption of Water-Soluble Humic-Like Substances in Air From Nanjing, China Revealed by the Machine Learning Combined FT-ICR-MS Technique | |
| Source Publication | JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES
 |
| ISSN | 2169-897X |
| 2023-12-27 | |
| Volume | 128Issue:24Pages:12 |
| DOI | 10.1029/2023JD039459 |
| Language | 英语 |
| WOS Research Area | Meteorology & Atmospheric Sciences |
| Abstract | The light absorption capacity of water-soluble humic-like substances (HULISWS) at the molecular level is crucial for reducing the uncertainties in modeling the radiative forcing. This study proposed a machine learning approach to allocate the light absorption coefficient at 365 nm (Abs(365)) of HULISWS into 8084 Fourier transform-ion cyclotron resonance mass spectrometry (FT-ICR-MS) detached molecular markers and their potential functional groups. The ML model showed an acceptable uncertainty (<5%) to the whole Abs(365) value based on the prediction errors. The results showed that five critical light-absorbing molecules (C4H6O4NS, C8H6O4NS, C11H15O3N2, C12H15O3N2, and C19H21O6) could explain 74% (+/- 3%) of the variation of Abs(365) in the winter, whereas no crucial light-absorbing molecules were found in the summer. Besides, the nitrogen-containing functional groups were found to dominate (61% +/- 8%) the molecular absorption near the 365 nm of the spectrum. This work illustrated how functional groups affect the absorption of HULISWS, providing critical information for future research of HULISWS on the molecular level. |
| Keyword | machine learning few-shot learning humic-like substances light absorption coefficient FT-ICR-MS functional groups |
| WOS ID | WOS:001124721800001 |
| Indexed By | SCI |
| Citation statistics | |
| Document Type | 期刊论文 |
| Identifier | http://ir.gig.ac.cn/handle/344008/75440 |
| Collection | 有机地球化学国家重点实验室 |
| Corresponding Author | Zhang, Yan-Lin |
| Affiliation | 1.Nanjing Univ Informat Sci & Technol, Minist Educ ILCEC, Atmospher Environm Ctr, Joint Lab Int Cooperat Climate & Environm Change, Nanjing, Peoples R China 2.Univ Reading, Sch Polit Econ & Int Relat, Reading, England 3.Nanjing Univ Informat Sci & Technol, Sch Ecol & Appl Meteorol, Nanjing, Peoples R China 4.Huzhou Meteorol Adm, Huzhou, Peoples R China 5.Hong Kong Polytech Univ, Dept Civil & Environm Engn, Air Qual Studies, Hong Kong, Peoples R China 6.Boston Coll, Morrissey Coll Arts & Sci, Boston, MA USA 7.Chinese Acad Sci, Guangzhou Inst Geochem, State Key Lab Organ Geochem, Guangdong Prov Key Lab Environm Protect & Resource, Guangzhou, Peoples R China 8.CAS Ctr Excellence Deep Earth Sci, Guangzhou, Peoples R China |
| Recommended Citation GB/T 7714 | Hong, Yihang,Zhang, Yan-Lin,Bao, Mengying,et al. Nitrogen-Containing Functional Groups Dominate the Molecular Absorption of Water-Soluble Humic-Like Substances in Air From Nanjing, China Revealed by the Machine Learning Combined FT-ICR-MS Technique[J]. JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES,2023,128(24):12. |
| APA | Hong, Yihang.,Zhang, Yan-Lin.,Bao, Mengying.,Fan, Mei-Yi.,Lin, Yu-Chi.,...&Zhang, Gan.(2023).Nitrogen-Containing Functional Groups Dominate the Molecular Absorption of Water-Soluble Humic-Like Substances in Air From Nanjing, China Revealed by the Machine Learning Combined FT-ICR-MS Technique.JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES,128(24),12. |
| MLA | Hong, Yihang,et al."Nitrogen-Containing Functional Groups Dominate the Molecular Absorption of Water-Soluble Humic-Like Substances in Air From Nanjing, China Revealed by the Machine Learning Combined FT-ICR-MS Technique".JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES 128.24(2023):12. |
| Files in This Item: | There are no files associated with this item. | |||||
Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.
Edit Comment