Revelation and Prediction of Atmospheric Pollutant Photolysis on Particulate Matter with Deterministic Learning Based on Infrared Spectra
- 31 October 2025
- journal article
- Published by American Chemical Society (ACS) in Environmental Science & Technology
- Vol. 59 (44) , 23895-23904
Abstract
Revealing nitrate photolysis on atmospheric particulate matter (PM), which generates secondary NOx and contributes to haze, acid rain, and daytime HONO formation, offers crucial insights into regulating regional air quality. While in situ spectroscopic techniques are useful to reveal photolysis mechanisms on single-component PM surfaces, it remains challenging to infer the photolysis behavior of mixed PM in real environments and quantify the influencing factors. To mitigate this challenge, we herein utilized artificial intelligence (AI) to capture time-dependent spectral variations, enabling the prediction and analysis of nitrate photolysis in complex atmospheric systems. Specifically, the deterministic learning approach, a novel machine learning (ML) algorithm specialized in modeling and analyzing the nonlinear systems, was innovatively applied to extract critical dynamic characteristic curves from time-series infrared spectra. Taking NH4NO3 photolysis on mineral dust as an example, we developed a spectroscopy-based ML approach that relies on single-component PM data sets and demonstrates its broad applicability by enabling direct prediction of nitrate photolysis trends across diverse mixed-source PMs without experimental measurements. In addition to the predominant contribution of photoactive TiO2 and Fe3O4 to nitrate photolysis by dynamic characteristic curve analysis, we also uncovered and experimentally validated a significant but overlooked inhibitory mechanism exerted by carbonates on these components. This work advances the integration of AI with atmospheric research, offering new perspectives for predicting and analyzing multisystem interactions in atmospheric environments while reducing the reliance on extensive experiments.Keywords
Funding Information
- National Postdoctoral Program for Innovative Talents (BX20230058)
- China Postdoctoral Science Foundation (2024M750359)
- Science and Technology Department of Sichuan Province (2024YFHZ0222, 2025NSFTD0003)
- National Natural Science Foundation of China (22225606, 22361142703, 2240060281)
This publication has 51 references indexed in Scilit:
- Quantifying multi-year ozone precursor contributions over the Pearl River Delta Region of China using a deep learning-based response surface modelFrontiers of Environmental Science & Engineering, 2025
- Multi-phase ECG dynamic features for detecting myocardial ischemia and identifying its etiology using deterministic learningBiomedical Signal Processing and Control, 2023
- Chemical composition, sources and evolution of PM2.5 during wintertime in the city cluster of southern Sichuan, ChinaAtmospheric Pollution Research, 2022
- Insight into the Overlooked Photochemical Decomposition of Atmospheric Surface Nitrates Triggered by Visible LightAngewandte Chemie International Edition, 2022
- Dynamic Evolution of Active Sites in Electrocatalytic CO2 Reduction Reaction: Fundamental Understanding and Recent ProgressAdvanced Functional Materials, 2022
- Mapping the daily nitrous acid (HONO) concentrations across China during 2006–2017 through ensemble machine-learning algorithmScience of The Total Environment, 2021
- Effects of kaolin-limestone blended additive on the formation and emission of particulate matter: Field study on a 1000 MW coal-firing power stationJournal of Hazardous Materials, 2020
- Photochemical reaction of CO2 on atmospheric mineral dustsAtmospheric Environment, 2020
- Investigation of formation mechanism of particulate matter in a laboratory-scale simulated cement kiln co-processing municipal sewage sludgeJournal of Cleaner Production, 2019
- Deterministic learning from sampling dataNeurocomputing, 2019