Predicting intersystem crossing rate constants of alkoxy-radical pairs with structure-based descriptors and machine learning

Loading...
Thumbnail Image

Access rights

openAccess
CC BY
publishedVersion

URL

Journal Title

Journal ISSN

Volume Title

A1 Alkuperäisartikkeli tieteellisessä aikakauslehdessä

Major/Subject

Mcode

Degree programme

Language

en

Pages

11

Series

Physical Chemistry Chemical Physics, Volume 27, issue 28, pp. 14804-14814

Abstract

Peroxy radicals (RO2) are ubiquitous intermediates in many oxidation processes, especially in the atmospheric gas phase. The recombination reaction of two peroxy radicals (RO2 + R′O2) has been demonstrated to lead, via several steps, to a triplet complex of two alkoxy radicals: 3(RO˙⋯R′O˙). The different product channels of RO2 + R′O2 reactions thus correspond to different reactions of this triplet complex. Of particular interest to atmospheric chemistry is the intersystem crossing (ISC) to the singlet state, which enables the recombination of the two radicals to an ROOR′ peroxide with considerably lower volatility than the original precursors. These peroxides are believed to be key contributors to the formation of secondary organic aerosol (SOA) particles, which in turn contribute to both air pollution and radiative forcing uncertainties. Developing reliable computational models for, e.g., RO2 + R′O2 branching ratios requires accurate estimates of the ISC rate constants, which can currently be obtained only from computationally expensive quantum chemistry calculations. By contrast, machine learning (ML) methods offer a faster alternative for estimating ISC rate constants. In the present work, we create a dataset with 98 082 conformations of radical pairs and their corresponding rate constants. We apply three ML models—random forest (RF), CatBoost (CB), and a neural network (NN)—to predict ISC rate constants from triplet to singlet states. Specifically, the models predict kISC(T1 → Si) for i = 1-4 and the cumulative kISC(T1 → Sn), in alkoxy radical pairs, using only molecular geometry descriptors as inputs. All ML models achieved a mean absolute error (MAE) on our test set within one order of magnitude and a coefficient of determination R2 > 0.82 for all rate constants. Overall, the ML prediction matches the quantum chemical calculations within 1-2 orders of magnitude, providing a fast and scalable alternative for quantum chemical methods for ISC rate estimation.

Description

Publisher Copyright: © 2025 The Royal Society of Chemistry.

Keywords

Other note

Citation

Valiev, R R, Nasibullin, R T, Sandström, H, Rinke, P, Puolamäki, K & Kurten, T 2025, 'Predicting intersystem crossing rate constants of alkoxy-radical pairs with structure-based descriptors and machine learning', Physical Chemistry Chemical Physics, vol. 27, no. 28, pp. 14804-14814. https://doi.org/10.1039/d5cp01101a