Advancing global aerosol forecasting with artificial intelligence

作     者：Gui, Ke Zhang, Xutao Che, Huizheng Li, Lei Zheng, Yu An, Linchang Miao, Yucong Zhao, Hujia Dubovik, Oleg Holben, Brent Wang, Jun Gupta, Pawan Lind, Elena S. Toledano, Carlos Wang, Hong Wang, Zhili Wang, Yaqiang Huang, Xiaomeng Dai, Kan Xia, Xiangao Xu, Xiaofeng Zhang, Xiaoye 

作者机构：State Key Laboratory of Severe Weather Key Laboratory of Atmospheric Chemistry of CMA Chinese Academy of Meteorological Sciences Beijing China National Meteorological Center CMA Beijing China Institute of Atmospheric Environment China Meteorological Administration Shenyang China Université de Lille CNRS UMR 8518–Laboratoire d’Optique Atmosphérique Lille France NASA Goddard Space Flight Center GreenbeltMD United States Department of Chemical and Biochemical Engineering The University of Iowa Iowa CityIA United States  HuntsvilleAL United States NASA Marshall Space Flight Center HuntsvilleAL United States Department of Electrical and Computer Engineering Virginia Tech BlacksburgVA United States Grupo de Optica Atmosférica Universidad de Valladolid Paseo Prado de la Magdalena Valladolid Spain Institute of Artificial Intelligence for Meteorological Chinese Academy of Meteorological Sciences Beijing China Department of Earth System Science Tsinghua University Beijing China Key Laboratory of Middle Atmosphere and Global Environment Observation Institute of Atmospheric Physics Chinese Academy of Sciences Beijing China China Meteorological Administration Beijing China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2024年

核心收录：

主　　题：Risk assessment 

摘      要：Aerosol forecasting is essential for air quality warnings, health risk assessment, and climate change mitigation. However, it is more complex than weather forecasting due to the intricate interactions between aerosol physicochemical processes and atmospheric dynamics, resulting in significant uncertainty and high computational costs. Here, we develop an artificial intelligence-driven global aerosol-meteorology forecasting system (AI-GAMFS), which provides reliable 5-day, 3-hourly forecasts of aerosol optical components and surface concentrations at a 0.5° × 0.625° resolution. AI-GAMFS combines Vision Transformer and U-Net in a backbone network, robustly capturing the complex aerosol-meteorology interactions via global attention and spatiotemporal encoding. Trained on 42 years of advanced aerosol reanalysis data and initialized with GEOS Forward Processing (GEOS-FP) analyses, AI-GAMFS delivers operational 5-day forecasts in one minute. It outperforms the Copernicus Atmosphere Monitoring Service (CAMS) global forecasting system, GEOS-FP forecasts, and several regional dust forecasting systems in forecasting most aerosol variables including aerosol optical depth and dust components. Our results mark a significant step forward in leveraging AI to refine physics-based aerosol forecasting, facilitating more accurate global warnings for aerosol pollution events, such as dust storms and wildfires. Copyright © 2024, The Authors. All rights reserved.