Metraipolis › archive › dc_a6790ed5a3e0
Steering Diffusion Priors with Sparse Observations for High-Resolution Temperature Downscaling — arXiv:2609.09247
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.09247
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T11:35:49.526Z
- SHA-256 of the archived text
2aeb8d1c87cb21de7288a6405b0e7051800a438ad860343303ccc7758c64a04c- Stable URL of this page
https://metraipolis.com/documento/dc_a6790ed5a3e0
How to cite
Steering Diffusion Priors with Sparse Observations for High-Resolution Temperature Downscaling — arXiv:2609.09247 — arXiv (en), https://arxiv.org/abs/2609.09247 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a6790ed5a3e0 (Metraipolis archive dc_a6790ed5a3e0, sha256 2aeb8d1c87cb21de7288a6405b0e7051800a438ad860343303ccc7758c64a04c)
BibTeX
@misc{dca6790ed5a3e0,
title = {Steering Diffusion Priors with Sparse Observations for High-Resolution Temperature Downscaling — arXiv:2609.09247},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.09247},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a6790ed5a3e0; sha256 2aeb8d1c87cb21de7288a6405b0e7051800a438ad860343303ccc7758c64a04c},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09247. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Local heatwave hazard depends on fine-scale air temperature, but ground stations are sparse and reanalysis products such as ERA5 cannot resolve the terrain and land-surface contrasts that shape real heat exposure. We present a conditional diffusion emulator for high-resolution 2-m temperature downscaling, conditioned on static geography, a training climatology, exact-time ERA5 temperature, and solar and temporal features, guided at inference by score-based data assimilation (SDA): a differentiable Gaussian observation likelihood steers the diffusion score toward sparse revealed temperature observations without any retraining. On a controlled 32-case synthetic-grid protocol over AORC, guidance improves hidden-cell reconstruction over both ERA5 and a strong observation-proximal nearest-neighbor baseline once observation density reaches 1\% (RMSE 0.318 vs.\ 0.431~K, winning all 32 cases), while sparser regimes still favor direct interpolation. We further map the full guidance-strength landscape across three observation densities, showing that the optimal strength shifts systematically with density and that over-guiding causes sharp, predictable degradation -- giving a concrete operating recipe rather than a single untuned setting. The resulting fields are intended as a temperature layer for downstream heatwave-hazard products such as threshold exceedance and cumulative heat-burden. The present evidence is a controlled synthetic-grid validation; station-network and held-out-year evaluations are the next steps toward deployment. Tema degli esploratori: terra, clima ed energia (retro-catalogo arXiv: annunci del 2026-09-10 in physics.ao-ph). Categorie arXiv: Atmospheric and Oceanic Physics (physics.ao-ph) ; Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.09247 — 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 2026-10-16T11:18:45.432Z dalla pagina https://arxiv.org/catchup/physics.ao-ph/2026-09-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).