Metraipolis › archive › dc_c79e006e575c

Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscaling — arXiv:2609.28749

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.28749
License (as archived)
CC0-1.0
Archived
2026-10-08T05:25:45.565Z
SHA-256 of the archived text
ed1a09d45a930c06ea10d4e0cb3a1bccdc58fb65764b19a52264884753a75117
Stable URL of this page
https://metraipolis.com/documento/dc_c79e006e575c

How to cite

Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscaling — arXiv:2609.28749 — arXiv (en), https://arxiv.org/abs/2609.28749 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c79e006e575c (Metraipolis archive dc_c79e006e575c, sha256 ed1a09d45a930c06ea10d4e0cb3a1bccdc58fb65764b19a52264884753a75117)
BibTeX
@misc{dcc79e006e575c,
  title = {Evaluating Cross-region Generalization for Wavelet-Diffusion Precipitation Downscaling — arXiv:2609.28749},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.28749},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c79e006e575c; sha256 ed1a09d45a930c06ea10d4e0cb3a1bccdc58fb65764b19a52264884753a75117},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.28749. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Diffusion models have shown strong potential for kilometer-scale precipitation downscaling, but their performance in geographically unseen regions and event regimes remains insufficiently understood. Building on the wavelet diffusion model (WDM) framework, this study evaluates cross-region and cross-event generalization. Six 3 x 3 deg U.S. regions represent convective, winter, tropical, and atmospheric-river precipitation regimes. Low-resolution inputs are generated by block averaging NOAA Multi-Radar/Multi-Sensor (MRMS) composite reflectivity fields. A WDM trained only on Oklahoma (OK) samples and a WDM trained on all six regions are compared with nearest-neighbor and Bicubic interpolation. Model performance is evaluated using three metric families that measure image-domain reconstruction, spectral and distributional fidelity, and bin-wise precipitation detection. The OK-trained WDM remains competitive outside OK. Although the all-region WDM delivers the best and most consistent overall image-domain and detection performance, its gains are uneven across precipitation intensities. Bin-wise critical success index (CSI) over 5-dBZ reflectivity bins shows that WDM improvements concentrate in localized higher-reflectivity structures, which image-domain metrics partly obscure. In addition, the performance differences among samples are strongly associated with the spatial organization of the precipitation field, quantified by Moran's I as the spatial autocorrelation of each reflectivity bin. The sample-level Moran's I-CSI correlation stratified by sample intensity reaches 0.901 in all six regions, including regions unseen during training. Overall, these findings support future efforts to transfer downscaling models to regions with limited local training data and to generate globally consistent, high-resolution precipitation products.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-25 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG) ; Atmospheric and Oceanic Physics (physics.ao-ph).
Pagina del lavoro: https://arxiv.org/abs/2609.28749 — 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 2026-10-08T04:50:39.237Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).