用AI模型实现全球气溶胶与活性气体的高效中程预报
AIFS-COMPO: A Global Data-Driven Atmospheric Composition Forecasting System
- 基于Transformer架构联合建模气象与大气成分变量
- 预报精度接近或优于现有系统，计算开销大幅降低
- 适合需要快速高精度全球空气质量预测的研究者
我们提出AIFS-COMPO，一种基于数据驱动的全球中程大气成分预报系统，用于气溶胶和活性气体。该系统建立在欧洲中期天气预报中心的人工智能预报系统（AIFS）基础上，采用Transformer编码-处理-解码架构，联合建模气象与大气成分变量。模型基于哥白尼大气监测服务（CAMS）再分析、分析及预报数据训练，学习天气、排放、传输与大气化学的耦合动态。评估显示，AIFS-COMPO在多个关键物种上的预报技能与现行操作级CAMS全球预报系统IFS-COMPO相当或更优，且仅需极少计算资源。该方法的高效性使预测可拓展至当前运行时限之外，展现了基于AI的系统在快速准确全球大气成分预测中的潜力。
原文摘要 · Abstract (English)
We introduce AIFS-COMPO, a skilful medium-range data-driven global forecasting system for aerosols and reactive gases. Building on the ECMWF Artificial Intelligence Forecast System (AIFS), AIFS-COMPO employs a transformer-based encoder-processor-decoder architecture to jointly model meteorological and atmospheric composition variables. The model is trained on Copernicus Atmosphere Monitoring Service (CAMS) reanalysis, analysis, and forecast data to learn the coupled dynamics of weather, emissions, transport, and atmospheric chemistry. We evaluate AIFS-COMPO against a range of atmospheric composition observations and compare its performance with the operational CAMS global forecasting system IFS-COMPO. The results show that AIFS-COMPO achieves comparable or improved forecast skill for several key species while requiring only a fraction of the computational resources. Furthermore, the efficiency of the approach enables forecasts beyond the current operational horizon, demonstrating the potential of AI-based systems for fast and accurate global atmospheric composition prediction.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。