Conference paper · 2026 · Open access
R34 Forecasting for Tropical Cyclone by Combining Deep Learning with Multi-modal Satellite Imagery
International Conference on Artificial Intelligence Technologies and Applications (ICAITA), 777–780 · Published 1 August 2026 · DOI 10.1109/icaita71179.2026.11737049
In brief
“R34 Forecasting for Tropical Cyclone by Combining Deep Learning with Multi-modal Satellite Imagery” is a 2026 conference paper by Jiacheng Ruan and Changjiang Zhang, published in International Conference on Artificial Intelligence Technologies and Applications (ICAITA). 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 at International Conference on Artificial Intelligence Technologies and Applications (ICAITA).
- Citations
- 0
- References
- 11
- Authors
- 2
Abstract
Tropical cyclones (TCs) are characterized by highly nonlinear evolution, with their intensity, structure, and area of influence often changing substantially within a short period. These rapid changes introduce considerable uncertainty into strong-wind, precipitation, and disaster-risk assessments. As an important indicator of the area affected by a tropical cyclone, the radius of 34-kt winds (R34) is directly relevant to disaster prevention, mitigation, and emergency response. However, existing intelligent forecasting studies for tropical cyclones have mainly focused on track and intensity prediction, while the direct prediction of wind radii such as R34 remains insufficiently explored. To address this issue, this study proposes a multimodal cascaded forecasting model, TCPR34, for 24-h R34 prediction by integrating historical size variations, intensity changes, and multi-frame satellite imagery. TCPR34 takes the offset sequences of R34 and intensity, together with nine consecutive historical satellite images, as inputs. It extracts structural evolution features of tropical cyclones through image encoding and temporal modeling, and further constructs a cascaded multi-task mechanism in which wind-speed evolution is learned as an auxiliary representation to support R34 prediction. In addition, CoordConv, initial-state context, radial-basis residual pooling, and multi-scale convolution modules are incorporated to enhance spatial-position awareness and size-structure representation. Experimental results show that TCPR34 achieves a mean absolute error of 23.28 n mi for 24-h R34 prediction. Ablation experiments further demonstrate that image information, the cascaded multi-task structure, and the spatial-enhancement modules contribute to medium- and long-range size forecasting, suggesting the effectiveness of multimodal satellite imagery and wind-evolution-conditioned multi-task learning for tropical cyclone size prediction. Overall, TCPR34 provides an efficient and robust framework for R34 wind-radius forecasting by integrating multi-source temporal information and structural features from satellite imagery, and it can offer technical support for assessing tropical cyclone impact areas, issuing strong-wind risk warnings, and supporting operational disaster-prevention decisions.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Ruan, J., & Zhang, C. (2026). R34 Forecasting for Tropical Cyclone by Combining Deep Learning with Multi-modal Satellite Imagery. International Conference on Artificial Intelligence Technologies and Applications (ICAITA), 777–780. https://doi.org/10.1109/icaita71179.2026.11737049
MLA 9
Ruan, Jiacheng, and Changjiang Zhang. “R34 Forecasting for Tropical Cyclone by Combining Deep Learning with Multi-modal Satellite Imagery.” International Conference on Artificial Intelligence Technologies and Applications (ICAITA), 2026, pp. 777–780. https://doi.org/10.1109/icaita71179.2026.11737049.
Chicago
Ruan, Jiacheng and Changjiang Zhang. 2026. “R34 Forecasting for Tropical Cyclone by Combining Deep Learning with Multi-modal Satellite Imagery.” International Conference on Artificial Intelligence Technologies and Applications (ICAITA): 777–780. https://doi.org/10.1109/icaita71179.2026.11737049.
Harvard
Ruan, J. and Zhang, C. (2026) ‘R34 Forecasting for Tropical Cyclone by Combining Deep Learning with Multi-modal Satellite Imagery’, International Conference on Artificial Intelligence Technologies and Applications (ICAITA), pp. 777–780. doi:10.1109/icaita71179.2026.11737049.
IEEE
J. Ruan and C. Zhang, “R34 Forecasting for Tropical Cyclone by Combining Deep Learning with Multi-modal Satellite Imagery,” International Conference on Artificial Intelligence Technologies and Applications (ICAITA), pp. 777–780, 2026, doi: 10.1109/icaita71179.2026.11737049.
BibTeX
@inproceedings{ruan2026forecasting,
title = {{R34 Forecasting for Tropical Cyclone by Combining Deep Learning with Multi-modal Satellite Imagery}},
author = {Ruan, Jiacheng and Zhang, Changjiang},
booktitle = {International Conference on Artificial Intelligence Technologies and Applications (ICAITA)},
year = {2026},
pages = {777--780},
doi = {10.1109/icaita71179.2026.11737049},
url = {https://doi.org/10.1109/icaita71179.2026.11737049}
}
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 › Tropical and Extratropical Cyclones Research
- tropical cyclones
- CoordConv
- multi-scale convolution
- disaster risk assessment
Work with this paper
Most-cited papers in Earth and Planetary Sciences
- The ERA5 global reanalysisHans Hersbach, Bill Bell, Paul Berrisford and 40 more · Quarterly Journal of the Royal Meteorological Society · 2020 · 35,424 citations
- The NCEP/NCAR 40-Year Reanalysis ProjectEugenia Kalnay, Masao Kanamitsu, Robert E. Kistler and 19 more · Bulletin of the American Meteorological Society · 1996 · 28,486 citations
- Chemical and isotopic systematics of oceanic basalts: implications for mantle composition and processesShen‐Su Sun, W. F. McDonough · Geological Society London Special Publications · 1989 · 26,603 citations
- The ERA‐Interim reanalysis: configuration and performance of the data assimilation systemDick P. Dee, Sakari M. Uppala, A. J. Simmons and 33 more · Quarterly Journal of the Royal Meteorological Society · 2011 · 25,245 citations
- PAST: PALEONTOLOGICAL STATISTICAL SOFTWARE PACKAGE FOR EDUCATION AND DATA ANALYSISØyvind Hammer, David A. T. Harper, Paul D. Ryan · 2001 · 17,871 citations
Questions about this paper
How do I cite this paper in APA style?
Ruan, J., & Zhang, C. (2026). R34 Forecasting for Tropical Cyclone by Combining Deep Learning with Multi-modal Satellite Imagery. International Conference on Artificial Intelligence Technologies and Applications (ICAITA), 777–780. https://doi.org/10.1109/icaita71179.2026.11737049
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 International Conference on Artificial Intelligence Technologies and Applications (ICAITA): sign in and open the full text from this page.
Who wrote this paper?
Jiacheng Ruan, Changjiang Zhang.
What is the DOI of this paper?
10.1109/icaita71179.2026.11737049, permanently at https://doi.org/10.1109/icaita71179.2026.11737049. 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.