A multi-geometry model, trained on 512 gridded Earth-system fields and 512 national indicators, couples physical and societal data in one latent space and supports uncertainty-aware reconstruction and downscaling.
Artificial intelligence to support cross-disciplinary climate change research
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
TerraNova: A Foundation Model for the Anthropocene
A multi-geometry model, trained on 512 gridded Earth-system fields and 512 national indicators, couples physical and societal data in one latent space and supports uncertainty-aware reconstruction and downscaling.