Zeeman: A Deep Learning Framework for Regional Atmospheric Chemistry Forecasting

Geophysical Research Letters, vol. 53

Abstract

Abstract Atmospheric chemistry encapsulates the emission of various pollutants, the complex chemistry reactions, and the meteorology dominant transport, which form a dynamic system that governs air quality. While deep learning (DL) models have shown promise in capturing intricate patterns for forecasting individual atmospheric components—such as and ozone—the critical interactions among multiple pollutants and the combined influence of emissions and meteorology are often overlook. This study introduces a DL‐based framework–Zeeman for atmospheric chemistry forecasting. Our model effectively captures the nuanced relationships among these constituents and while achieving a 68.5‐fold increase in computational speed compared to traditional numerical model. Evaluations demonstrate that our approach rivals numerical model, offering an efficient solution for atmospheric chemistry forecasting. In the future, this model could be further integrated with data assimilation techniques to facilitate efficient and accurate atmospheric emission estimation and concentration forecast.

Authors 7

1. Mijie Pang

   Delft University of Technology

   Affiliation as printed

   Delft Institute of Applied Mathematics Delft University of Technology Delft The Netherlands

2. Jianbing Jin corresponding

   Nanjing University of Information Science and Technology

   Affiliation as printed

   State Key Laboratory of Climate System Prediction and Risk Management Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology School of Environmental Science and Engineering Nanjing University of Information Science and Technology Nanjing China

3. Arjo J. Segers

   Netherlands Organisation for Applied Scientific Research

   Affiliation as printed

   TNO Department of Climate Air and Sustainability Utrecht The Netherlands

4. Hai Xiang Lin Aachen Institute of Environment Sciences Leiden University Leiden The Netherlands

   Leiden University · Delft University of Technology

   Affiliation as printed

   Delft Institute of Applied Mathematics Delft University of Technology Delft The Netherlands

   Institute of Environment Sciences Leiden University Leiden The Netherlands

5. Guoqiang Wang

   Shanghai University of Engineering Science

   Affiliation as printed

   School of Mathematics Physics and Statistics Shanghai University of Engineering Science Shanghai China

6. Hong Liao

   Nanjing University of Information Science and Technology

   Affiliation as printed

   State Key Laboratory of Climate System Prediction and Risk Management Jiangsu Key Laboratory of Atmospheric Environment Monitoring and Pollution Control Jiangsu Collaborative Innovation Center of Atmospheric Environment and Equipment Technology School of Environmental Science and Engineering Nanjing University of Information Science and Technology Nanjing China

7. Wei Han corresponding

   China Meteorological Administration

   Affiliation as printed

   CMA Earth System Modeling and Prediction Centre Chinese Meteorological Administration Beijing China