Preprint · 2026 · Open access

Quantifying the responses of AI precipitation forecast errors to reanalysis errors using analysis of covariance

Qiang Li, Tongtiegang Zhao

EGUsphere · Published 29 September 2026 · DOI 10.5194/egusphere-2026-5557

Open PDFView at the publisherCite this paper

In brief

“Quantifying the responses of AI precipitation forecast errors to reanalysis errors using analysis of covariance” is a 2026 preprint by Qiang Li and Tongtiegang Zhao, published in EGUsphere. OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read.

Citations
0
References
51
Authors
2

Abstract

AI weather models are commonly trained by climate reanalysis datasets that inevitably influence AI weather forecasts. Given the importance of precipitation, it is essential to quantify how AI forecast errors respond to reanalysis errors. This paper proposes the use of the analysis of covariance (ANCOVA) method to diagnose the responses. Specifically, extreme precipitation events are identified from historical observations; both forecast and reanalysis errors are calculated against observations during the evaluation period; and the ANCOVA method is fitted to separate the responses to reanalysis errors from changes in response coefficients and additional offsets associated with extreme precipitation. A case study is devised for GraphCast forecasts and European Centre for Medium-range Weather Forecasts (ECMWF) Reanalysis v5 (ERA5), using Daymet observations across 1426 catchments in the Catchment Attributes and MEteorology for Large-Sample SPATially distributed analysis (CAMELS-SPAT) dataset. The results show that the responses of GraphCast forecast errors to ERA5 reanalysis errors weaken progressively with increasing lead time. Under non-extreme conditions, the median response coefficient declines from 0.70 at the 1d lead time to 0.27 at 9d, indicating that each 1 mm/d increase in ERA5 precipitation errors leads to a median increase of 0.70 and 0.27 mm/d in GraphCast precipitation errors, respectively. Extreme precipitation amplifies the underestimation by GraphCast forecasts, with the median additional offset across 1426 catchments decreasing from −1.75 to −10.43 mm/d when the lead time increases from 1d to 9d. Overall, the ANCOVA method contributes to understandings of factors governing precipitation forecast errors and highlights the need to consider inherent uncertainties in climate reanalysis when training and evaluating AI weather models.

Cite this paper

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

APA 7

Li, Q., & Zhao, T. (2026). Quantifying the responses of AI precipitation forecast errors to reanalysis errors using analysis of covariance. EGUsphere. https://doi.org/10.5194/egusphere-2026-5557

MLA 9

Li, Qiang, and Tongtiegang Zhao. “Quantifying the responses of AI precipitation forecast errors to reanalysis errors using analysis of covariance.” EGUsphere, 2026. https://doi.org/10.5194/egusphere-2026-5557.

Chicago

Li, Qiang and Tongtiegang Zhao. 2026. “Quantifying the responses of AI precipitation forecast errors to reanalysis errors using analysis of covariance.” EGUsphere. https://doi.org/10.5194/egusphere-2026-5557.

Harvard

Li, Q. and Zhao, T. (2026) ‘Quantifying the responses of AI precipitation forecast errors to reanalysis errors using analysis of covariance’, EGUsphere. doi:10.5194/egusphere-2026-5557.

IEEE

Q. Li and T. Zhao, “Quantifying the responses of AI precipitation forecast errors to reanalysis errors using analysis of covariance,” EGUsphere, 2026, doi: 10.5194/egusphere-2026-5557.

BibTeX

@misc{li2026quantifying,
  title     = {{Quantifying the responses of AI precipitation forecast errors to reanalysis errors using analysis of covariance}},
  author    = {Li, Qiang and Zhao, Tongtiegang},
  howpublished = {EGUsphere},
  year      = {2026},
  doi       = {10.5194/egusphere-2026-5557},
  url       = {https://doi.org/10.5194/egusphere-2026-5557}
}

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

  • covariance analysis
  • heavy rainfall
  • GraphCast
  • ERA5 reanalysis
  • lead time
  • forecast bias
  • catchment hydrology

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?

Li, Q., & Zhao, T. (2026). Quantifying the responses of AI precipitation forecast errors to reanalysis errors using analysis of covariance. EGUsphere. https://doi.org/10.5194/egusphere-2026-5557

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: sign in and open the PDF from this page.

Who wrote this paper?

Qiang Li, Tongtiegang Zhao.

What is the DOI of this paper?

10.5194/egusphere-2026-5557, permanently at https://doi.org/10.5194/egusphere-2026-5557. 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.