AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908543314034688 |
|---|---|
| author | Hatanpää, Väinö Ku, Eugene Stock, Jason Emani, Murali Foreman, Sam Jung, Chunyong Madireddy, Sandeep Nguyen, Tung Sastry, Varuni Sinurat, Ray A. O. Wheeler, Sam Zheng, Huihuo Arcomano, Troy Vishwanath, Venkatram Kotamarthi, Rao |
| author_facet | Hatanpää, Väinö Ku, Eugene Stock, Jason Emani, Murali Foreman, Sam Jung, Chunyong Madireddy, Sandeep Nguyen, Tung Sastry, Varuni Sinurat, Ray A. O. Wheeler, Sam Zheng, Huihuo Arcomano, Troy Vishwanath, Venkatram Kotamarthi, Rao |
| contents | Generative machine learning offers new opportunities to better understand complex Earth system dynamics. Recent diffusion-based methods address spectral biases and improve ensemble calibration in weather forecasting compared to deterministic methods, yet have so far proven difficult to scale stably at high resolutions. We introduce AERIS, a 1.3 to 80B parameter pixel-level Swin diffusion transformer to address this gap, and SWiPe, a generalizable technique that composes window parallelism with sequence and pipeline parallelism to shard window-based transformers without added communication cost or increased global batch size. On Aurora (10,080 nodes), AERIS sustains 10.21 ExaFLOPS (mixed precision) and a peak performance of 11.21 ExaFLOPS with $1 \times 1$ patch size on the 0.25° ERA5 dataset, achieving 95.5% weak scaling efficiency, and 81.6% strong scaling efficiency. AERIS outperforms the IFS ENS and remains stable on seasonal scales to 90 days, highlighting the potential of billion-parameter diffusion models for weather and climate prediction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_13523 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions Hatanpää, Väinö Ku, Eugene Stock, Jason Emani, Murali Foreman, Sam Jung, Chunyong Madireddy, Sandeep Nguyen, Tung Sastry, Varuni Sinurat, Ray A. O. Wheeler, Sam Zheng, Huihuo Arcomano, Troy Vishwanath, Venkatram Kotamarthi, Rao Machine Learning Distributed, Parallel, and Cluster Computing Generative machine learning offers new opportunities to better understand complex Earth system dynamics. Recent diffusion-based methods address spectral biases and improve ensemble calibration in weather forecasting compared to deterministic methods, yet have so far proven difficult to scale stably at high resolutions. We introduce AERIS, a 1.3 to 80B parameter pixel-level Swin diffusion transformer to address this gap, and SWiPe, a generalizable technique that composes window parallelism with sequence and pipeline parallelism to shard window-based transformers without added communication cost or increased global batch size. On Aurora (10,080 nodes), AERIS sustains 10.21 ExaFLOPS (mixed precision) and a peak performance of 11.21 ExaFLOPS with $1 \times 1$ patch size on the 0.25° ERA5 dataset, achieving 95.5% weak scaling efficiency, and 81.6% strong scaling efficiency. AERIS outperforms the IFS ENS and remains stable on seasonal scales to 90 days, highlighting the potential of billion-parameter diffusion models for weather and climate prediction. |
| title | AERIS: Argonne Earth Systems Model for Reliable and Skillful Predictions |
| topic | Machine Learning Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2509.13523 |