Unraveling the Linkages between Molecular Abundance and Stable Carbon Isotope Ratio in Dissolved Organic Matter Using Machine Learning,Environmental Science & Technology

当前位置： X-MOL 学术 › Environ. Sci. Technol. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Unraveling the Linkages between Molecular Abundance and Stable Carbon Isotope Ratio in Dissolved Organic Matter Using Machine Learning
Environmental Science & Technology ( IF 10.8 ) Pub Date : 2023-04-20 , DOI: 10.1021/acs.est.3c00221
Yuanbi Yi ₁ , Tongcun Liu ₂ , Julian Merder ₃ , Chen He ₄ , Hongyan Bao ₅ , Penghui Li _{6,

7} , Siliang Li ₈ , Quan Shi ₄ , Ding He _{1,

9}

Affiliation

Dissolved organic matter (DOM) is a complex mixture of molecules that constitutes one of the largest reservoirs of organic matter on Earth. While stable carbon isotope values (δ¹³C) provide valuable insights into DOM transformations from land to ocean, it remains unclear how individual molecules respond to changes in DOM properties such as δ¹³C. To address this, we employed Fourier transform ion cyclotron resonance mass spectrometry (FT-ICR MS) to characterize the molecular composition of DOM in 510 samples from the China Coastal Environments, with 320 samples having δ¹³C measurements. Utilizing a machine learning model based on 5199 molecular formulas, we predicted δ¹³C values with a mean absolute error (MAE) of 0.30‰ on the training data set, surpassing traditional linear regression methods (MAE 0.85‰). Our findings suggest that degradation processes, microbial activities, and primary production regulate DOM from rivers to the ocean continuum. Additionally, the machine learning model accurately predicted δ¹³C values in samples without known δ¹³C values and in other published data sets, reflecting the δ¹³C trend along the land to ocean continuum. This study demonstrates the potential of machine learning to capture the complex relationships between DOM composition and bulk parameters, particularly with larger learning data sets and increasing molecular research in the future.

更新日期：2023-04-20

点击分享查看原文

点击收藏

阅读更多本刊新发论文本刊介绍/投稿指南