Preprint · 2026 · Open access

AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion

Somnath Luitel, Manmeet Singh, Joshua Durkee, Abdullah Al Fahad, Naveen Sudharsan, Prabhjot Singh, Cenlin He, Harsh Kamath, Zong-Liang Yang, Krishnagopal Halder, Sandeep Juneja, Parthasarathi Mukhopadhyay and 2 more

arXiv (Cornell University) · Published 20 May 2026 · DOI 10.48550/arxiv.2605.26130

Free PDFView at the publisherCite this paper

In brief

“AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion” is a 2026 preprint by Somnath Luitel and 13 co-authors, published in arXiv (Cornell University). OpenAlex counts 1 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at arXiv (Cornell University).

Citations
1
Most cited in
2026 (1)
References
3
Authors
14

Abstract

Operational weather prediction at kilometer scales remains computationally prohibitive for traditional numerical weather prediction (NWP) models, limiting forecast access for applications in energy, agriculture, and disaster management that require fine-grained spatiotemporal detail. Here we introduce AirCast-SR, a foundation model for atmospheric super-resolution that downscales global AI weather forecasts from 0.25 degree (~28 km) to 1 km horizontal resolution at hourly temporal resolution, producing 67-hour forecasts of eight coupled surface variables simultaneously. EarthMind-SR employs a three-dimensional U-Net conditioned within a Latent Consistency Model (LCM) diffusion framework, trained on patch-based samples over the contiguous United States (CONUS) using GraphCast forecasts as input and NOAA's Analysis of Record for Calibration (AORC) as the target. The model achieves near-zero bias across all variables and lead times, and its radial power spectral density analysis demonstrates preservation of fine-scale atmospheric structure at wavelengths of 10 km to 100 km where coarser models lose spectral power. We validate EarthMind-SR across three CONUS case studies spanning winter, summer, and spring seasons, and demonstrate zero-shot global transferability over India and Germany using independent surface station observations without any retraining or fine-tuning. As an open-weights foundation model, EarthMind-SR establishes a new paradigm for kilometer-scale AI weather prediction and provides a platform for regional fine-tuning, distillation, and downstream applications in climate services and hazard forecasting.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Luitel, S., Singh, M., Durkee, J., Al Fahad, A., Sudharsan, N., Singh, P., He, C., Kamath, H., Yang, Z.-L., Halder, K., Juneja, S., Mukhopadhyay, P., Dhanuka, S., & Srivastava, A. K. (2026). AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.26130

MLA 9

Luitel, Somnath, et al. “AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion.” arXiv (Cornell University), 2026. https://doi.org/10.48550/arxiv.2605.26130.

Chicago

Luitel, Somnath, Manmeet Singh, Joshua Durkee, Abdullah Al Fahad, Naveen Sudharsan, Prabhjot Singh, Cenlin He, et al. 2026. “AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion.” arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.26130.

Harvard

Luitel, S. et al. (2026) ‘AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion’, arXiv (Cornell University). doi:10.48550/arxiv.2605.26130.

IEEE

S. Luitel et al., “AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion,” arXiv (Cornell University), 2026, doi: 10.48550/arxiv.2605.26130.

BibTeX

@misc{luitel2026aircast,
  title     = {{AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion}},
  author    = {Luitel, Somnath and Singh, Manmeet and Durkee, Joshua and Al Fahad, Abdullah and Sudharsan, Naveen and Singh, Prabhjot and He, Cenlin and Kamath, Harsh and Yang, Zong-Liang and Halder, Krishnagopal and Juneja, Sandeep and Mukhopadhyay, Parthasarathi and Dhanuka, Saptarishi and Srivastava, Amit Kumar},
  howpublished = {arXiv (Cornell University)},
  year      = {2026},
  doi       = {10.48550/arxiv.2605.26130},
  url       = {https://doi.org/10.48550/arxiv.2605.26130}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations

  • GraphCast
  • U-Net
  • zero-shot transfer
  • climate services
  • hazard prediction

Work with this paper

Most-cited papers in Earth and Planetary Sciences

All highly cited Earth and Planetary Sciences papers

Questions about this paper

How do I cite this paper in APA style?

Luitel, S., Singh, M., Durkee, J., Al Fahad, A., Sudharsan, N., Singh, P., He, C., Kamath, H., Yang, Z.-L., Halder, K., Juneja, S., Mukhopadhyay, P., Dhanuka, S., & Srivastava, A. K. (2026). AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion. arXiv (Cornell University). https://doi.org/10.48550/arxiv.2605.26130

How many times has this paper been cited?

1 times, according to OpenAlex on 15 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access: read the free full text at arXiv (Cornell University).

Who wrote this paper?

Somnath Luitel, Manmeet Singh, Joshua Durkee, Abdullah Al Fahad, Naveen Sudharsan, Prabhjot Singh, Cenlin He, Harsh Kamath, Zong-Liang Yang, Krishnagopal Halder, Sandeep Juneja, Parthasarathi Mukhopadhyay and 2 more.

What is the DOI of this paper?

10.48550/arxiv.2605.26130. The permanent link is https://doi.org/10.48550/arxiv.2605.26130.

Bibliographic data from OpenAlex (CC0), last checked 15 November 2026. ResearchGuru does not host this paper; the links go to the publisher or the repository that does.