Journal article · 2026 · Open access

Enhancing Regional Machine Learning Weather Prediction Using Tailored Loss Functions and High-Resolution RRJ-ClimCORE Reanalysis

Hiroki Ikeuchi, Tsuyoshi Thomas Sekiyama, Takafumi Miyasaka, Kenichi Kuma, Hisashi Nakamura

SOLA, 22(1) · Published 16 January 2026 · DOI 10.1007/s44393-025-00006-8

Free PDFView at the publisherCite this paper

In brief

“Enhancing Regional Machine Learning Weather Prediction Using Tailored Loss Functions and High-Resolution RRJ-ClimCORE Reanalysis” is a 2026 journal article by Hiroki Ikeuchi and 4 co-authors, published in SOLA. OpenAlex counts 1 citations as of 15 November 2026, which puts it in the top 9% of works published in 2026 by citations. It is open access under a CC BY licence: the full text is free to read at SOLA.

Citations
1
Most cited in
2026 (1)
Field-weighted impact
1.63
References
24
Authors
5

Abstract

Recent advances in machine learning-based weather prediction (MLWP) have achieved accuracy comparable to operational numerical weather prediction systems, while offering much faster and more energy-efficient inference. However, global MLWP models struggle to forecast localized extremes, including typhoons and heavy rainfall. This is mainly due to coarse resolution of training data and the reliance on mean squared error (MSE) loss, which inclines toward spatial smoothing. This study develops a regional MLWP model for Japan trained on high-resolution regional reanalysis data with the employment of variable-specific loss functions for wind, pressure, geopotential height, and precipitation. Ablation experiments demonstrate that these loss functions contribute in complementary ways, substantially improving the forecast skill relative to conventional MSE loss. Case studies of an extratropical cyclone and Typhoon Nanmadol show improved forecasts of cyclone intensity, strong winds, and orographic rainfall. Leveraging regional reanalysis with the tailored loss design is therefore an effective strategy for regional MLWP.

Cite this paper

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

APA 7

Ikeuchi, H., Sekiyama, T. T., Miyasaka, T., Kuma, K., & Nakamura, H. (2026). Enhancing Regional Machine Learning Weather Prediction Using Tailored Loss Functions and High-Resolution RRJ-ClimCORE Reanalysis. SOLA, 22(1). https://doi.org/10.1007/s44393-025-00006-8

MLA 9

Ikeuchi, Hiroki, et al. “Enhancing Regional Machine Learning Weather Prediction Using Tailored Loss Functions and High-Resolution RRJ-ClimCORE Reanalysis.” SOLA, vol. 22, no. 1, 2026. https://doi.org/10.1007/s44393-025-00006-8.

Chicago

Ikeuchi, Hiroki, Tsuyoshi Thomas Sekiyama, Takafumi Miyasaka, Kenichi Kuma, and Hisashi Nakamura. 2026. “Enhancing Regional Machine Learning Weather Prediction Using Tailored Loss Functions and High-Resolution RRJ-ClimCORE Reanalysis.” SOLA 22 (1). https://doi.org/10.1007/s44393-025-00006-8.

Harvard

Ikeuchi, H. et al. (2026) ‘Enhancing Regional Machine Learning Weather Prediction Using Tailored Loss Functions and High-Resolution RRJ-ClimCORE Reanalysis’, SOLA, 22(1). doi:10.1007/s44393-025-00006-8.

IEEE

H. Ikeuchi, T. T. Sekiyama, T. Miyasaka, K. Kuma, and H. Nakamura, “Enhancing Regional Machine Learning Weather Prediction Using Tailored Loss Functions and High-Resolution RRJ-ClimCORE Reanalysis,” SOLA, vol. 22, no. 1, 2026, doi: 10.1007/s44393-025-00006-8.

BibTeX

@article{ikeuchi2026enhancing,
  title     = {{Enhancing Regional Machine Learning Weather Prediction Using Tailored Loss Functions and High-Resolution RRJ-ClimCORE Reanalysis}},
  author    = {Ikeuchi, Hiroki and Sekiyama, Tsuyoshi Thomas and Miyasaka, Takafumi and Kuma, Kenichi and Nakamura, Hisashi},
  journal   = {SOLA},
  year      = {2026},
  volume    = {22},
  number    = {1},
  doi       = {10.1007/s44393-025-00006-8},
  url       = {https://doi.org/10.1007/s44393-025-00006-8}
}

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

  • machine learning weather prediction
  • regional weather forecasting
  • high-resolution reanalysis
  • typhoon forecasting
  • heavy rainfall forecasting
  • orographic precipitation
  • mean squared error loss
  • Japan

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?

Ikeuchi, H., Sekiyama, T. T., Miyasaka, T., Kuma, K., & Nakamura, H. (2026). Enhancing Regional Machine Learning Weather Prediction Using Tailored Loss Functions and High-Resolution RRJ-ClimCORE Reanalysis. SOLA, 22(1). https://doi.org/10.1007/s44393-025-00006-8

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 SOLA.

Who wrote this paper?

Hiroki Ikeuchi, Tsuyoshi Thomas Sekiyama, Takafumi Miyasaka, Kenichi Kuma, Hisashi Nakamura.

What is the DOI of this paper?

10.1007/s44393-025-00006-8. The permanent link is https://doi.org/10.1007/s44393-025-00006-8.

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.