Journal article · 2023 · Open access

Deep Learning Image Segmentation for Atmospheric Rivers

Daniel Galea, Hsi‐Yen Ma, Wen‐Ying Wu, Daigo Kobayashi

Artificial Intelligence for the Earth Systems, 3(1) · Published 8 November 2023 · DOI 10.1175/aies-d-23-0048.1

Open PDFView at the publisherCite this paper

In brief

“Deep Learning Image Segmentation for Atmospheric Rivers” is a 2023 journal article by Daniel Galea and 3 co-authors, published in Artificial Intelligence for the Earth Systems. OpenAlex counts 13 citations as of 20 November 2026, which puts it in the top 5% of works published in 2023 by citations. It is open access: the full text is free to read at Artificial Intelligence for the Earth Systems.

Citations
13
Most cited in
2025 (5)
Field-weighted impact
1.06
References
23
Authors
4

Abstract

The identification of atmospheric rivers (ARs) is crucial for weather and climate predictions as they are often associated with severe storm systems and extreme precipitation, which can cause large impacts on society. This study presents a deep learning model, termed ARDetect, for image segmentation of ARs using ERA5 data from 1960 to 2020 with labels obtained from the TempestExtremes tracking algorithm. ARDetect is a convolutional neural network (CNN)-based U-Net model, with its structure having been optimized using automatic hyperparameter tuning. Inputs to ARDetect were selected to be the integrated water vapor transport (IVT) and total column water (TCW) fields, as well as the AR mask from TempestExtremes from the previous time step to the one being considered. ARDetect achieved a mean intersection-over-union (mIoU) rate of 89.04% for ARs, indicating its high accuracy in identifying these weather patterns and a superior performance than most deep learning–based models for AR detection. In addition, ARDetect can be executed faster than the TempestExtremes method (seconds vs minutes) for the same period. This provides a significant benefit for online AR detection, especially for high-resolution global models. An ensemble of 10 models, each trained on the same dataset but having different starting weights, was used to further improve on the performance produced by ARDetect, thus demonstrating the importance of model diversity in improving performance. ARDetect provides an effective and fast deep learning–based model for researchers and weather forecasters to better detect and understand ARs, which have significant impacts on weather-related events such as floods and droughts.

Cite this paper

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

APA 7

Galea, D., Ma, H., Wu, W., & Kobayashi, D. (2023). Deep Learning Image Segmentation for Atmospheric Rivers. Artificial Intelligence for the Earth Systems, 3(1). https://doi.org/10.1175/aies-d-23-0048.1

MLA 9

Galea, Daniel, et al. “Deep Learning Image Segmentation for Atmospheric Rivers.” Artificial Intelligence for the Earth Systems, vol. 3, no. 1, 2023. https://doi.org/10.1175/aies-d-23-0048.1.

Chicago

Galea, Daniel, Hsi‐Yen Ma, Wen‐Ying Wu, and Daigo Kobayashi. 2023. “Deep Learning Image Segmentation for Atmospheric Rivers.” Artificial Intelligence for the Earth Systems 3 (1). https://doi.org/10.1175/aies-d-23-0048.1.

Harvard

Galea, D. et al. (2023) ‘Deep Learning Image Segmentation for Atmospheric Rivers’, Artificial Intelligence for the Earth Systems, 3(1). doi:10.1175/aies-d-23-0048.1.

IEEE

D. Galea, H. Ma, W. Wu, and D. Kobayashi, “Deep Learning Image Segmentation for Atmospheric Rivers,” Artificial Intelligence for the Earth Systems, vol. 3, no. 1, 2023, doi: 10.1175/aies-d-23-0048.1.

BibTeX

@article{galea2023deep,
  title     = {{Deep Learning Image Segmentation for Atmospheric Rivers}},
  author    = {Galea, Daniel and Ma, Hsi‐Yen and Wu, Wen‐Ying and Kobayashi, Daigo},
  journal   = {Artificial Intelligence for the Earth Systems},
  year      = {2023},
  volume    = {3},
  number    = {1},
  doi       = {10.1175/aies-d-23-0048.1},
  url       = {https://doi.org/10.1175/aies-d-23-0048.1}
}

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

Citations by year

YearCitationsShare of the best year
202444
202555
202644

Its field-weighted citation impact is 1.06: it has been cited 1.06 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 › Meteorological Phenomena and Simulations

  • atmospheric rivers
  • atmospheric river detection
  • image segmentation
  • U-Net
  • convolutional neural networks
  • integrated vapor transport
  • ERA5 reanalysis
  • ensemble learning

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?

Galea, D., Ma, H., Wu, W., & Kobayashi, D. (2023). Deep Learning Image Segmentation for Atmospheric Rivers. Artificial Intelligence for the Earth Systems, 3(1). https://doi.org/10.1175/aies-d-23-0048.1

How many times has this paper been cited?

13 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 Artificial Intelligence for the Earth Systems: sign in and open the PDF from this page.

Who wrote this paper?

Daniel Galea, Hsi‐Yen Ma, Wen‐Ying Wu, Daigo Kobayashi.

What is the DOI of this paper?

10.1175/aies-d-23-0048.1, permanently at https://doi.org/10.1175/aies-d-23-0048.1. 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.