Unraveling the Linkages between Molecular Abundance and Stable Carbon Isotope Ratio in Dissolved Organic Matter Using Machine Learning
Yuanbi Yi, Tongcun Liu, Julian Merder, Chen He, Hongyan Bao, Penghui Li, Si‐Liang Li, Quan Shi, Ding He
Abstract
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 (δ 13 C) provide valuable insights into DOM transformations from land to ocean, it remains unclear how individual molecules respond to changes in DOM properties such as δ 13 C. 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 δ 13 C measurements. Utilizing a machine learning model based on 5199 molecular formulas, we predicted δ 13 C 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 δ 13 C values in samples without known δ 13 C values and in other published data sets, reflecting the δ 13 C 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.