Journal article · 2026 · Open access

Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea

Seong‐Ho Hong, Kyeongjoo Park, Dong Hwi Kim, Jong‐Jin Baik, Han-Gyul Jin

Theoretical and Applied Climatology, 157(9) · Published 1 September 2026 · DOI 10.1007/s00704-026-06536-w

Open full textCite this paper

In brief

“Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea” is a 2026 journal article by Seong‐Ho Hong and 4 co-authors, published in Theoretical and Applied Climatology. OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY-NC-ND licence: the full text is free to read at Theoretical and Applied Climatology.

Citations
0
References
45
Authors
5

Abstract

As AI-based weather prediction model emerges, its prediction skill for extreme weather draws great attention. This study assesses the skill of GraphCast in heavy precipitation prediction against rain gauge observations focusing on 10 heavy precipitation cases in South Korea. For comparisons, the Weather Research and Forecasting (WRF) model simulations with different horizontal resolutions of 27 (WRF 27km ), 9 (WRF 9km ), and 3 km (WRF 3km ) are used. When the skill in predicting general patterns of precipitation is evaluated using the normalized mean bias, normalized centered root-mean-square error, and spatial correlation coefficient, GraphCast shows better or comparable skill compared with WRF 27km , WRF 9km , and WRF 3km . When the skill for different precipitation thresholds is separately examined using the equitable threat score (ETS), neighborhood ETS, and other contingency table-based metrics, GraphCast shows relatively large overprediction of light precipitation (≤ 20 mm) and underprediction of heavy precipitation (≥ 70 mm) compared with WRF 27km as well as WRF 9km and WRF 3km . GraphCast reproduces observed topographic enhancements of precipitation over the Sobaek Mountains by 42%, which is less than those reproduced by WRF 27km (71%), WRF 9km (63%), and WRF 3km (90%). While the synoptic conditions and their associated water vapor transports are similarly simulated by GraphCast and WRF 27km , the upward motions over the Sobaek Mountains are weaker for GraphCast than for WRF 27km . The underpredictions of heavy precipitation and topographically enhanced precipitation by GraphCast are mainly associated with its weak ability to predict large precipitation peaks with scales of about 25–100 km.

Cite this paper

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

APA 7

Hong, S., Park, K., Kim, D. H., Baik, J., & Jin, H.-G. (2026). Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea. Theoretical and Applied Climatology, 157(9). https://doi.org/10.1007/s00704-026-06536-w

MLA 9

Hong, Seong‐Ho, et al. “Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea.” Theoretical and Applied Climatology, vol. 157, no. 9, 2026. https://doi.org/10.1007/s00704-026-06536-w.

Chicago

Hong, Seong‐Ho, Kyeongjoo Park, Dong Hwi Kim, Jong‐Jin Baik, and Han-Gyul Jin. 2026. “Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea.” Theoretical and Applied Climatology 157 (9). https://doi.org/10.1007/s00704-026-06536-w.

Harvard

Hong, S. et al. (2026) ‘Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea’, Theoretical and Applied Climatology, 157(9). doi:10.1007/s00704-026-06536-w.

IEEE

S. Hong, K. Park, D. H. Kim, J. Baik, and H.-G. Jin, “Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea,” Theoretical and Applied Climatology, vol. 157, no. 9, 2026, doi: 10.1007/s00704-026-06536-w.

BibTeX

@article{hong2026skill,
  title     = {{Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea}},
  author    = {Hong, Seong‐Ho and Park, Kyeongjoo and Kim, Dong Hwi and Baik, Jong‐Jin and Jin, Han-Gyul},
  journal   = {Theoretical and Applied Climatology},
  year      = {2026},
  volume    = {157},
  number    = {9},
  doi       = {10.1007/s00704-026-06536-w},
  url       = {https://doi.org/10.1007/s00704-026-06536-w}
}

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
  • equitable threat score
  • water vapor transport
  • upward motion
  • South Korea

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?

Hong, S., Park, K., Kim, D. H., Baik, J., & Jin, H.-G. (2026). Skill assessment of AI-based weather model in heavy precipitation prediction over South Korea. Theoretical and Applied Climatology, 157(9). https://doi.org/10.1007/s00704-026-06536-w

How many times has this paper been cited?

0 times, according to OpenAlex on 20 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 at Theoretical and Applied Climatology: sign in and open the full text from this page.

Who wrote this paper?

Seong‐Ho Hong, Kyeongjoo Park, Dong Hwi Kim, Jong‐Jin Baik, Han-Gyul Jin.

What is the DOI of this paper?

10.1007/s00704-026-06536-w, permanently at https://doi.org/10.1007/s00704-026-06536-w. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.