Conference paper · 2026 · Open access

Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields

Evangelia Rafaela Frastali, Achyut Paudel, Maryam Golbazi, Frank Liu

International Conference on Machine Learning and Applications, 355–362 · Published 1 October 2026 · DOI 10.1109/icmla69890.2026.00057

Read the free full textCite this paper

In brief

“Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields” is a 2026 conference paper by Evangelia Rafaela Frastali and 3 co-authors, published in International Conference on Machine Learning and Applications. OpenAlex counts 0 citations as of 15 November 2026. It is open access under a CC BY licence: the full text is free to read at International Conference on Machine Learning and Applications.

Citations
0
References
36
Authors
4

Abstract

High-resolution atmospheric data are required to resolve mesoscale and localized meteorological structures, however, such datasets remain limited in many regions of the world. Existing high-resolution weather products are typically produced through dynamical downscaling, which is computationally expensive and difficult to scale across locations, variables, and forecast scenarios. These limitations motivate machine-learning-based downscaling systems that can generate multiple weather variables stochastically while producing new high-resolution fields directly. In this paper we present Apeliotes, a framework for high-resolution weather forecasting. Built on the global re-analysis atmospheric data, a pre-trained global weather foundation model, and a regionally trained generative diffusion model, Apeliotes not only provides accurate kilometer-scale weather variables, but also multi-level atmospheric fields which are not directly available in the existing global atmospheric data. Our comprehensive evaluation demonstrates that Apeliotes achieves highly competitive performance. The model predicts vertical wind profile with less than 3% error between truth and predicted fields, achieving correlations of 0.91 for 10-m wind speed and 0.99 for 2-m temperature, with NRMSE values of 0.42 and 0.17, respectively.

Cite this paper

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

APA 7

Frastali, E. R., Paudel, A., Golbazi, M., & Liu, F. (2026). Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields. International Conference on Machine Learning and Applications, 355–362. https://doi.org/10.1109/icmla69890.2026.00057

MLA 9

Frastali, Evangelia Rafaela, et al. “Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields.” International Conference on Machine Learning and Applications, 2026, pp. 355–362. https://doi.org/10.1109/icmla69890.2026.00057.

Chicago

Frastali, Evangelia Rafaela, Achyut Paudel, Maryam Golbazi, and Frank Liu. 2026. “Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields.” International Conference on Machine Learning and Applications: 355–362. https://doi.org/10.1109/icmla69890.2026.00057.

Harvard

Frastali, E. R. et al. (2026) ‘Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields’, International Conference on Machine Learning and Applications, pp. 355–362. doi:10.1109/icmla69890.2026.00057.

IEEE

E. R. Frastali, A. Paudel, M. Golbazi, and F. Liu, “Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields,” International Conference on Machine Learning and Applications, pp. 355–362, 2026, doi: 10.1109/icmla69890.2026.00057.

BibTeX

@inproceedings{frastali2026apeliotes,
  title     = {{Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields}},
  author    = {Frastali, Evangelia Rafaela and Paudel, Achyut and Golbazi, Maryam and Liu, Frank},
  booktitle = {International Conference on Machine Learning and Applications},
  year      = {2026},
  pages     = {355--362},
  doi       = {10.1109/icmla69890.2026.00057},
  url       = {https://doi.org/10.1109/icmla69890.2026.00057}
}

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

  • generative diffusion models
  • machine learning downscaling
  • wind profiles
  • reanalysis data
  • 10 m wind speed
  • 2 m air temperature

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?

Frastali, E. R., Paudel, A., Golbazi, M., & Liu, F. (2026). Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields. International Conference on Machine Learning and Applications, 355–362. https://doi.org/10.1109/icmla69890.2026.00057

How many times has this paper been cited?

0 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 International Conference on Machine Learning and Applications.

Who wrote this paper?

Evangelia Rafaela Frastali, Achyut Paudel, Maryam Golbazi, Frank Liu.

What is the DOI of this paper?

10.1109/icmla69890.2026.00057. The permanent link is https://doi.org/10.1109/icmla69890.2026.00057.

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.