Journal article · 2024 · Open access

Downscaling Taiwan precipitation with a residual deep learning approach

Li‐Huan Hsu, Chou-Chun Chiang, Kuan-Ling Lin, Hsin‐Hung Lin, Jung‐Lien Chu, Yi‐Chiang Yu, Chin‐Shyurng Fahn

Geoscience Letters, 11(1), 23 · Published 9 May 2024 · DOI 10.1186/s40562-024-00340-y

Open PDFView at the publisherCite this paper

In brief

“Downscaling Taiwan precipitation with a residual deep learning approach” is a 2024 journal article by Li‐Huan Hsu and 6 co-authors, published in Geoscience Letters. OpenAlex counts 20 citations as of 21 November 2026, which puts it in the top 8% of works published in 2024 by citations. It is open access under a CC BY licence: the full text is free to read at Geoscience Letters.

Citations
20
Most cited in
2026 (13)
Field-weighted impact
2.64
References
32
Authors
7

Abstract

In response to the growing demand for high-resolution rainfall data to support disaster prevention in Taiwan, this study presents an innovative approach for downscaling precipitation data. We employed a hierarchical architecture of Multi-Scale Residual Networks (MSRN) to downscale rainfall from a coarse 0.25-degree resolution to a fine 0.0125-degree resolution, representing a substantial challenge due to a resolution increase of over 20 times. Our results demonstrate that the hierarchical MSRN outperforms both the one-step MSRN and linear interpolation methods when reconstructing high-resolution daily rainfall. It surpasses the linear interpolation method by 15.1 and 9.1% in terms of mean absolute error and root mean square error, respectively. Furthermore, the hierarchical MSRN excels in accurately reproducing high-resolution rainfall for various rainfall thresholds, displaying minimal biases. The threat score (TS) highlights the hierarchical MSRN's capability to replicate extreme rainfall events, achieving TS scores exceeding 0.54 and 0.46 at rainfall thresholds of 350 and 500 mm per day, outperforming alternative methods. This method is also applied to an operational global model, the ECMWF’s daily rainfall forecasts over Taiwan. The evaluation results indicate that our approach is effective at improving rainfall forecasts for thresholds greater than 100 mm per day, with more significant improvement for the 1- to 3-day lead forecast. This approach also offers a realistic visual representation of fine-grained rainfall distribution, showing promise for making significant contributions to disaster preparedness and weather forecasting in Taiwan.

Cite this paper

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

APA 7

Hsu, L., Chiang, C.-C., Lin, K.-L., Lin, H., Chu, J., Yu, Y., & Fahn, C. (2024). Downscaling Taiwan precipitation with a residual deep learning approach. Geoscience Letters, 11(1), 23. https://doi.org/10.1186/s40562-024-00340-y

MLA 9

Hsu, Li‐Huan, et al. “Downscaling Taiwan precipitation with a residual deep learning approach.” Geoscience Letters, vol. 11, no. 1, 2024, p. 23. https://doi.org/10.1186/s40562-024-00340-y.

Chicago

Hsu, Li‐Huan, Chou-Chun Chiang, Kuan-Ling Lin, Hsin‐Hung Lin, Jung‐Lien Chu, Yi‐Chiang Yu, and Chin‐Shyurng Fahn. 2024. “Downscaling Taiwan precipitation with a residual deep learning approach.” Geoscience Letters 11 (1): 23. https://doi.org/10.1186/s40562-024-00340-y.

Harvard

Hsu, L. et al. (2024) ‘Downscaling Taiwan precipitation with a residual deep learning approach’, Geoscience Letters, 11(1), p. 23. doi:10.1186/s40562-024-00340-y.

IEEE

L. Hsu et al., “Downscaling Taiwan precipitation with a residual deep learning approach,” Geoscience Letters, vol. 11, no. 1, p. 23, 2024, doi: 10.1186/s40562-024-00340-y.

BibTeX

@article{hsu2024downscaling,
  title     = {{Downscaling Taiwan precipitation with a residual deep learning approach}},
  author    = {Hsu, Li‐Huan and Chiang, Chou-Chun and Lin, Kuan-Ling and Lin, Hsin‐Hung and Chu, Jung‐Lien and Yu, Yi‐Chiang and Fahn, Chin‐Shyurng},
  journal   = {Geoscience Letters},
  year      = {2024},
  volume    = {11},
  number    = {1},
  pages     = {23},
  doi       = {10.1186/s40562-024-00340-y},
  url       = {https://doi.org/10.1186/s40562-024-00340-y}
}

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

Citations by year

YearCitationsShare of the best year
202422
202555
20261313

Its field-weighted citation impact is 2.64: it has been cited 2.64 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Precipitation Measurement and Analysis

  • precipitation downscaling
  • rainfall
  • multi-scale residual network
  • hierarchical neural networks
  • high-resolution rainfall
  • heavy rainfall
  • precipitation forecasting
  • ECMWF forecasts

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?

Hsu, L., Chiang, C.-C., Lin, K.-L., Lin, H., Chu, J., Yu, Y., & Fahn, C. (2024). Downscaling Taiwan precipitation with a residual deep learning approach. Geoscience Letters, 11(1), 23. https://doi.org/10.1186/s40562-024-00340-y

How many times has this paper been cited?

20 times, according to OpenAlex on 21 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 Geoscience Letters: sign in and open the PDF from this page.

Who wrote this paper?

Li‐Huan Hsu, Chou-Chun Chiang, Kuan-Ling Lin, Hsin‐Hung Lin, Jung‐Lien Chu, Yi‐Chiang Yu, Chin‐Shyurng Fahn.

What is the DOI of this paper?

10.1186/s40562-024-00340-y, permanently at https://doi.org/10.1186/s40562-024-00340-y. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 21 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.