paper
2020
Climate emulation
Global medium-range NWP New model or method
Transformer / ViTCNN / U-Net3–15 daysClimate projections / centennialLawrence Berkeley National Laboratory / NERSC Conference
2020-07-01
026
Jul 2020
A. Chattopadhyay, M. Mustafa, P. Hassanzadeh et al.
Proceedings of the 10th International Conference on Climate Informatics
Lawrence Berkeley National Laboratory / NERSC
Spatial-transformer encoder-decoder autoregressively predicts two-layer quasi-geostrophic flow up to 9 days and stays stable for years, aiming at data-driven climate surrogates.
Deep spatial transformers for autoregressive data-driven forecasting of geophysical turbulence
In one sentence. Spatial-transformer encoder-decoder autoregressively predicts two-layer quasi-geostrophic flow up to 9 days and stays stable for years, aiming at data-driven climate surrogates.
Labels
- Topic
- Climate emulation, Global medium-range NWP
- Type
- New model or method
- Method
- Transformer / ViT, CNN / U-Net
- Time scale
- 3–15 days, Climate projections / centennial
- Domain
- Regional
- Data
- Other
- Status
- Research
- Identifiers
- DOI:10.1145/3429309.3429325 OpenAlex:W3120863415
- Added
- 2026-10-22
Labels and summary are generated by Claude and reviewed weekly. Wrong? Edit this entry.