Atmospheric Transport Modeling of CO2 With Neural Networks
From Earthly Machine Learning by Amirpasha
April 27, 2026 · 21 min · Season 2 · Episode 7
About this episode
This episode discusses the use of neural networks for atmospheric transport modeling of CO2, highlighting a new benchmark dataset and the performance of various architectures.
Citation: Benson, V., Bastos, A., Reimers, C., Winkler, A. J., Yang, F., & Reichstein, M. (2025). Atmospheric transport modeling of CO2 with neural networks. Journal of Advances in Modeling Earth Systems , 17, e2024MS004655. https://doi.org/10.1029/2024MS004655 Main Takeaways: A New Benchmark for AI Carbon Tracking : The authors introduce CarbonBench, the first systematic benchmark dataset designed specifically for training and evaluating machine learning emulators of Eulerian atmospheric transport. Built from CarbonTracker CT2022 inversions and ObsPack station observations, it ships at three resolutions (the coarsest being 5.625° × 10 vertical levels × 6h) and is engineered to plug directly into modern deep learning pipelines — opening atmospheric carbon modeling to the broader ML community. SwinTransformer Wins, Decisively : Of the four architectures tested (UNet, GraphCast, SFNO, and SwinTransformer), the SwinTransformer reaches near-perfect emulation with a 90-day R² above 0.99 and stays stable in physically plausible forward runs for over three years — a regime where neural PDE solvers typically blow up. At measurement stations, it actually captures the seasonal cycle in…
People in this episode
Host: Amirpasha
Topics covered
- atmospheric transport modeling
- CO2
- neural networks
- machine learning
- carbon tracking
- benchmark datasets
Keywords
- CO2 modeling
- neural networks
- CarbonBench
- SwinTransformer
- machine learning
- atmospheric transport
Mentioned in this episode
Organizations: Journal of Advances in Modeling Earth Systems, CarbonTracker, ObsPack
Products: CarbonBench, SwinTransformer, UNet, GraphCast, SFNO
Books & works: TM5
More episodes of Earthly Machine Learning
- Aligning artificial intelligence with climate change mitigation · May 9, 2026 · 19 min
- Machine learning for the physics of climate · May 3, 2026 · 20 min
- On the foundations of Earth foundation models · April 20, 2026 · 18 min
- Whose weather is it? A fairness framework for data-driven weather forecasting · April 14, 2026 · 22 min
- Learning predictable and informative dynamical drivers of extreme precipitation using variational autoencoders · March 7, 2026 · 18 min
- Green and intelligent: the role of AI in the climate transition · February 28, 2026 · 18 min
Explore listener stats, chart rankings, contacts and more on the Earthly Machine Learning podcast page.