Metraipolis › archive › dc_ebf3cc5fce8e
Physically Typed and Geometry-Aware Representations for Earth Foundation Models — arXiv:2609.13868
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.13868
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T00:15:08.884Z
- SHA-256 of the archived text
9ee5ce17522cf4fceeef636c3bbdd8a00c95d4c0759638c12616d2b21320607f- Stable URL of this page
https://metraipolis.com/documento/dc_ebf3cc5fce8e
How to cite
Physically Typed and Geometry-Aware Representations for Earth Foundation Models — arXiv:2609.13868 — arXiv (en), https://arxiv.org/abs/2609.13868 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ebf3cc5fce8e (Metraipolis archive dc_ebf3cc5fce8e, sha256 9ee5ce17522cf4fceeef636c3bbdd8a00c95d4c0759638c12616d2b21320607f)
BibTeX
@misc{dcebf3cc5fce8e,
title = {Physically Typed and Geometry-Aware Representations for Earth Foundation Models — arXiv:2609.13868},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.13868},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ebf3cc5fce8e; sha256 9ee5ce17522cf4fceeef636c3bbdd8a00c95d4c0759638c12616d2b21320607f},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13868. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Earth-observation (EO) foundation models have become exceptionally effective at learning se mantic, high-dimensional geospatial embeddings, while modern weather and climate models have demonstrated that Earth-specific geometry, spherical operators, meshes, and hybrid physical solvers can materially improve prediction. Yet these two advances are not equivalent. A conventional latent embedding has no inherent physical transformation law, whereas scalar fields, tangent polar-vector fields, axial/pseudovector quantities, covectors, and higher-order tensors transform differently under rotations, reflections, and changes of local coordinate frame. This proposal asks whether a general purpose Earth foundation model should preserve those distinctions explicitly, or whether standard embeddings plus augmentation already learn everything that matters. The central contribution is therefore not a more complicated architecture by assumption, but a staged falsification program. A compute-conscious ERA5 dry run first compares conventional, augmentation-matched, typed equivariant, and Hodge/Helmholtz variants under spatial, temporal, orientation, and low-data shifts. Only if explicit geometric typing yields reproducible improvements does the program advance toward a multimodal Earth foundation model in which semantic embeddings coexist with physically typed fields. The proposed gap is narrower and more defensible than claiming that current models ignore geometry entirely: several systems already respect spherical domain geometry, and emerging work explicitly learns scalar/vector fields on spheres. The unresolved question is whether foundation-scale, multimodal, parity-aware field typing produces practical gains beyond those existing approaches. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-15 in cs.LG). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.13868 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-15T23:54:14.862Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).