Articles | Volume 19, issue 10
https://doi.org/10.5194/gmd-19-4009-2026
https://doi.org/10.5194/gmd-19-4009-2026
Development and technical paper
 | 
18 May 2026
Development and technical paper |  | 18 May 2026

From reanalysis to climatology: deep learning reconstruction of tropical cyclogenesis in the western North Pacific

Duc-Trong Le, Tran-Binh Dang, Anh-Duc Hoang Gia, Duc-Hai Nguyen, Minh-Hoa Tien, Xuan-Truong Ngo, Quang-Trung Luu, Quang-Lap Luu, Tai-Hung Nguyen, Thanh T. N. Nguyen, and Chanh Kieu

Download

Interactive discussion

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on egusphere-2025-4333', Anonymous Referee #1, 24 Dec 2025
    • AC1: 'Reply on RC1', Duc-Trong Le, 04 Mar 2026
  • RC2: 'Comment on egusphere-2025-4333', Anonymous Referee #2, 27 Dec 2025
    • AC2: 'Reply on RC2', Duc-Trong Le, 04 Mar 2026

Peer review completion

AR – Author's response | RR – Referee report | ED – Editor decision | EF – Editorial file upload
AR by Duc-Trong Le on behalf of the Authors (04 Mar 2026)  Author's response   Author's tracked changes   Manuscript 
ED: Referee Nomination & Report Request started (08 Mar 2026) by Tao Zhang
RR by Anonymous Referee #3 (01 Apr 2026)
RR by Anonymous Referee #2 (06 Apr 2026)
ED: Publish as is (19 Apr 2026) by Tao Zhang
AR by Duc-Trong Le on behalf of the Authors (28 Apr 2026)  Manuscript 
Download
Short summary

We study how and where tropical storms, i.e., tropical cyclogenesis, begin in the Western North Pacific. Using many years of global weather data and a modern pattern-recognition method, i.e., deep learning,  we built a model that learns signals that come before storm formation and maps when and where formation is likely. It reproduces known seasonal and regional patterns and identifies key environmental cues. These results can support better risk planning and help refine climate projections.

Share