2024/08/20 by Vitus Benson, Ana Bastos, Benson, Vitus +9
Chemistry · Environmental Science · #Air Quality Monitoring and Forecasting #Atmospheric and Environmental Gas Dynamics #Atmospheric and Oceanic Physics (physics.ao-ph) #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #FOS: Physical sciences #Machine Learning (cs.LG) #Spectroscopy and Laser Applications
paper · pdf · doi:10.48550/arxiv.2408.11032
openalex publication_date 2024/08/20 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Accurately describing the distribution of CO2 in the atmosphere with atmospheric tracer transport models is essential for greenhouse gas monitoring and verification support systems to aid implementation of international climate agreements. Large deep neural networks are poised to revolutionize weather prediction, which requires 3D modeling of the atmosphere. While similar in this regard, atmospheric transport modeling is subject to new challenges. Both, stable predictions for longer time horizons and mass conservation throughout need to be achieved, while IO plays a larger role compared to computational costs. In this study we explore four different deep neural networks (UNet, GraphCast, Spherical Fourier Neural Operator and SwinTransformer) which have proven as state-of-the-art in weather prediction to assess their usefulness for atmospheric tracer transport modeling. For this, we assemble the CarbonBench dataset, a systematic benchmark tailored for machine learning emulators of Eulerian atmospheric transport. Through architectural adjustments, we decouple the performance of our emulators from the distribution shift caused by a steady rise in atmospheric CO2. More specifically, we center CO2 input fields to zero mean and then use an explicit flux scheme and a mass fixer to assure mass balance. This design enables stable and mass conserving transport for over 6 months with all four neural network architectures. In our study, the SwinTransformer displays particularly strong emulation skill (90-day R2 > 0.99), with physically plausible emulation even for forward runs of multiple years. This work paves the way forward towards high resolution forward and inverse modeling of inert trace gases with neural networks.