Research map / Time series / Long-term forecasting
Earthformer: Exploring Space-Time Transformers for Earth System Forecasting
Zhihan Gao, Xingjian Shi, Hao Wang, Yi Zhu, Bernie Wang, Mu Li, Dit-Yan Yeung
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add global vectors to cuboid attention (ablation) | Earthformer (Axial) · MovingMNIST | MSE: 46.91 -> 41.79 | Improved |
| add global vectors (ablation) | Earthformer · SEVIR | CSI-M: 0.4356 -> 0.4419 | Improved |
| add global vectors (ablation) | Earthformer · SEVIR | CSI-16: 0.7637 -> 0.7513 | Hurt |
| add global vectors (ablation) | Earthformer · ICAR-ENSO | C-Nino3.4-M: 0.7239 -> 0.7329 | Improved |
| Axial cuboid pattern instead of DST (ablation) | Earthformer · MovingMNIST | MSE: 57.43 -> 46.91 | Improved |
| hierarchical encoder-decoder (Depth 4,4) instead of flat Depth 8 (ablation) | Earthformer · MovingMNIST | MSE: 48.04 -> 46.91 | Improved |
| Earthformer vs best baseline | spatiotemporal forecasting · SEVIR | CSI-219: 0.1312 -> 0.1791 | Improved |
| Earthformer vs best baseline | spatiotemporal forecasting · N-body MNIST | MSE: 21.76 -> 14.82 | Improved |
Later papers that compared with this method
1 later accepted paper reports EarthFormer as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.
- Extreme Weather Nowcasting via Local Precipitation Pattern Prediction (ICLR 2026 · better on 0 of 1 shared result)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Scaling transformer neural networks for skillful and reliable medium-range weather forecasting (NeurIPS 2024 · similarity 0.87)
- Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model (AAAI 2024 · similarity 0.87)
- Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth (NeurIPS 2024 · similarity 0.86)
- OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales (NeurIPS 2025 · similarity 0.86)
- On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting (NeurIPS 2025 · similarity 0.85)
- CirT: Global Subseasonal-to-Seasonal Forecasting with Geometry-inspired Transformer (ICLR 2025 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
