气候变化领域集成服务门户(CCPortal): Predicting gas-particle partitioning coefficients of atmospheric molecules with machine learning

CCPortal

DOI	10.5194/acp-21-13227-2021
	Predicting gas-particle partitioning coefficients of atmospheric molecules with machine learning
	Lumiaro E.; Todorović M.; Kurten T.; Vehkamäki H.; Rinke P.
发表日期	2021
ISSN	1680-7316
起始页码	13227
结束页码	13246
卷号	21 期号:17
英文摘要	The formation, properties, and lifetime of secondary organic aerosols in the atmosphere are largely determined by gas-particle partitioning coefficients of the participating organic vapours. Since these coefficients are often difficult to measure and to compute, we developed a machine learning model to predict them given molecular structure as input. Our data-driven approach is based on the dataset by Wang et al. (2017), who computed the partitioning coefficients and saturation vapour pressures of 3414 atmospheric oxidation products from the Master Chemical Mechanism using the COSMOtherm programme. We trained a kernel ridge regression (KRR) machine learning model on the saturation vapour pressure (Psat) and on two equilibrium partitioning coefficients: between a water-insoluble organic matter phase and the gas phase (KWIOM/G) and between an infinitely dilute solution with pure water and the gas phase (KW/G). For the input representation of the atomic structure of each organic molecule to the machine, we tested different descriptors. We find that the many-body tensor representation (MBTR) works best for our application, but the topological fingerprint (TopFP) approach is almost as good and computationally cheaper to evaluate. Our best machine learning model (KRR with a Gaussian kernel + MBTR) predicts Psat and KWIOM/G to within 0.3 logarithmic units and KW/G to within 0.4 logarithmic units of the original COSMOtherm calculations. This is equal to or better than the typical accuracy of COSMOtherm predictions compared to experimental data (where available). We then applied our machine learning model to a dataset of 35ĝ€¯383 molecules that we generated based on a carbon-10 backbone functionalized with zero to six carboxyl, carbonyl, or hydroxyl groups to evaluate its performance for polyfunctional compounds with potentially low Psat. The resulting saturation vapour pressure and partitioning coefficient distributions were physico-chemically reasonable, for example, in terms of the average effects of the addition of single functional groups. The volatility predictions for the most highly oxidized compounds were in qualitative agreement with experimentally inferred volatilities of, for example, α-pinene oxidation products with as yet unknown structures but similar elemental compositions. © 2021 The Author(s).
语种	英语
scopus关键词	aerosol; concentration (composition); data set; hydroxyl radical; machine learning; partitioning; prediction
来源期刊	ATMOSPHERIC CHEMISTRY AND PHYSICS
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/246604
作者单位	Department of Applied Physics, Aalto University, P.O. Box 11100, Espoo, 00076, Finland; Department of Mechanical and Materials Engineering, University of Turku, Turku, 20014, Finland; Department of Chemistry, Faculty of Science, University of Helsinki, P.O. Box 55, Helsinki, 00014, Finland; Institute for Atmospheric and Earth System Research/Physics, Faculty of Science, University of Helsinki, P.O. Box 64, Helsinki, 00014, Finland
推荐引用方式 GB/T 7714	Lumiaro E.,Todorović M.,Kurten T.,et al. Predicting gas-particle partitioning coefficients of atmospheric molecules with machine learning[J],2021,21(17).
APA	Lumiaro E.,Todorović M.,Kurten T.,Vehkamäki H.,&Rinke P..(2021).Predicting gas-particle partitioning coefficients of atmospheric molecules with machine learning.ATMOSPHERIC CHEMISTRY AND PHYSICS,21(17).
MLA	Lumiaro E.,et al."Predicting gas-particle partitioning coefficients of atmospheric molecules with machine learning".ATMOSPHERIC CHEMISTRY AND PHYSICS 21.17(2021).