GAIA: A Foundation Model for Operational Atmospheric Dynamics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917358669398016 |
|---|---|
| author | Asanjan, Ata Akbari Alexander, Olivia Berg, Tom Peng, Stephen Makki, Jad Zhang, Clara Yang, Matt Shidham, Disha Chakraborty, Srija Bender, William Crawford, Cara Ravindran, Arun Raiman, Olivier Potere, David Bell, David |
| author_facet | Asanjan, Ata Akbari Alexander, Olivia Berg, Tom Peng, Stephen Makki, Jad Zhang, Clara Yang, Matt Shidham, Disha Chakraborty, Srija Bender, William Crawford, Cara Ravindran, Arun Raiman, Olivier Potere, David Bell, David |
| contents | We introduce GAIA (Geospatial Artificial Intelligence for Atmospheres), a hybrid self-supervised geospatial foundation model that fuses Masked Autoencoders (MAE) with self-distillation with no labels (DINO) to generate semantically rich representations from global geostationary satellite imagery. Pre-trained on 15 years of globally-merged infrared observations (2001-2015), GAIA learns disentangled representations that capture atmospheric dynamics rather than trivial diurnal patterns, as evidenced by distributed principal component structure and temporal coherence analysis. We demonstrate robust reconstruction capabilities across varying data availability (30-95% masking), achieving superior gap-filling performance on real missing data patterns. When transferred to downstream tasks, GAIA consistently outperforms an MAE-only baseline: improving atmospheric river segmentation (F1: 0.58 vs 0.52), enhancing tropical cyclone detection (storm-level recall: 81% vs 75%, early detection: 29% vs 17%), and maintaining competitive precipitation estimation performance. Analysis reveals that GAIA's hybrid objectives encourage learning of spatially coherent, object-centric features distributed across multiple principal components rather than concentrated representations focused on reconstruction. This work demonstrates that combining complementary self-supervised objectives yields more transferable representations for diverse atmospheric modeling tasks. Model weights and code are available at: https://huggingface.co/bcg-usra-nasa-gaia/GAIA-v1. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_18179 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GAIA: A Foundation Model for Operational Atmospheric Dynamics Asanjan, Ata Akbari Alexander, Olivia Berg, Tom Peng, Stephen Makki, Jad Zhang, Clara Yang, Matt Shidham, Disha Chakraborty, Srija Bender, William Crawford, Cara Ravindran, Arun Raiman, Olivier Potere, David Bell, David Machine Learning Artificial Intelligence We introduce GAIA (Geospatial Artificial Intelligence for Atmospheres), a hybrid self-supervised geospatial foundation model that fuses Masked Autoencoders (MAE) with self-distillation with no labels (DINO) to generate semantically rich representations from global geostationary satellite imagery. Pre-trained on 15 years of globally-merged infrared observations (2001-2015), GAIA learns disentangled representations that capture atmospheric dynamics rather than trivial diurnal patterns, as evidenced by distributed principal component structure and temporal coherence analysis. We demonstrate robust reconstruction capabilities across varying data availability (30-95% masking), achieving superior gap-filling performance on real missing data patterns. When transferred to downstream tasks, GAIA consistently outperforms an MAE-only baseline: improving atmospheric river segmentation (F1: 0.58 vs 0.52), enhancing tropical cyclone detection (storm-level recall: 81% vs 75%, early detection: 29% vs 17%), and maintaining competitive precipitation estimation performance. Analysis reveals that GAIA's hybrid objectives encourage learning of spatially coherent, object-centric features distributed across multiple principal components rather than concentrated representations focused on reconstruction. This work demonstrates that combining complementary self-supervised objectives yields more transferable representations for diverse atmospheric modeling tasks. Model weights and code are available at: https://huggingface.co/bcg-usra-nasa-gaia/GAIA-v1. |
| title | GAIA: A Foundation Model for Operational Atmospheric Dynamics |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2505.18179 |