Track-Centric Machine Learning for 24-Hour Peak-Intensity Forecasting of Western North Pacific Typhoons

Yaoxiang Yu

doi:10.54254/2755-2721/2025.LD28444

Applied and Computational EngineeringOpen access

Track-Centric Machine Learning for 24-Hour Peak-Intensity Forecasting of Western North Pacific Typhoons

Research Article

Open Access

Track-Centric Machine Learning for 24-Hour Peak-Intensity Forecasting of Western North Pacific Typhoons

Yaoxiang Yu ^1*

¹ James B. Conant High School, Hoffman Estates, Illinois, United States

^*Corresponding author: Andrew.yuyx@gmail.com

Published on 22 October 2025

ACE Vol.196

ISSN (Print): 2755-273X

ISSN (Online): 2755-2721

ISBN (Print): 978-1-80590-451-9

ISBN (Online): 978-1-80590-452-6

Download Cover

Abstract

This study forecasts tropical-cyclone peak intensity 24 hours in advance using a parsimonious, track-centric feature set. From 400 Western North Pacific storms (2012–2025), standardized pre-peak histories are constructed from 37 three-hourly coordinates and augmented with month, initial wind and pressure, and 24-hour prior wind and pressure. Best-track records provide targets for peak maximum sustained wind and minimum central pressure, and models are assessed on a temporally held-out cohort of 151 post-2020 storms. Compared with a linear baseline, nonlinear learners substantially improve accuracy for peak wind (R² ≈ 0.82–0.83; RMSE ≈ 16.3–16.6 kt versus 22.8 kt) and for minimum pressure, where gradient-boosted trees perform best (R² ≈ 0.81; RMSE ≈ 13.2 hPa). Stratified analyses show consistent gains across months, latitude bands, and intensity classes, though errors increase for major and super typhoons. Interpretation of model behavior indicates that 24-hour prior wind and pressure dominate predictive skill, while latitude and longitude primarily modulate outcomes rather than acting as strong main effects. The approach is fast, portable, and interpretable, offering a low-latency prior when richer environmental or satellite inputs are unavailable.

Keywords:

Tropical cyclones, typhoons, machine learning, neural network

View PDF

References

[1]. A. M. F. Lagmay et al., “Devastating storm surges of Typhoon Haiyan, ” Int. J. Disaster Risk Reduct., vol. 11, pp. 1–12, Mar. 2015, doi: 10.1016/j.ijdrr.2014.10.006.

[2]. “Typhoon Yagi killed 318 people, damage reaches $3.3 billion, ” vietnamnews.vn. Accessed: Oct. 05, 2025. [Online]. Available: https: //vietnamnews.vn/society/1663938/typhoon-yagi-killed-318-people-damage-reaches-3-3-billion.html

[3]. X. Bi, J. Liu, and Y. Duan, “Review of Artificial Intelligence Application in Typhoon Forecasting, ” Trop. Cyclone Res. Rev., p. S2225603225000311, Jul. 2025, doi: 10.1016/j.tcrr.2025.07.005.

[4]. R. Chen, W. Zhang, and X. Wang, “Machine Learning in Tropical Cyclone Forecast Modeling: A Review, ” Atmosphere, vol. 11, no. 7, p. 676, Jun. 2020, doi: 10.3390/atmos11070676.

[5]. H. Xu, Y. Zhao, Z. Dajun, Y. Duan, and X. Xu, “Exploring the typhoon intensity forecasting through integrating AI weather forecasting with regional numerical weather model, ” Npj Clim. Atmospheric Sci., vol. 8, no. 1, p. 38, Feb. 2025, doi: 10.1038/s41612-025-00926-z.

[6]. A. S. Albahri et al., “A systematic review of trustworthy artificial intelligence applications in natural disasters, ” Comput. Electr. Eng., vol. 118, p. 109409, Sep. 2024, doi: 10.1016/j.compeleceng.2024.109409.

[7]. A. Mosavi, P. Ozturk, and K. Chau, “Flood Prediction Using Machine Learning Models: Literature Review, ” Water, vol. 10, no. 11, p. 1536, Oct. 2018, doi: 10.3390/w10111536.

[8]. K. M. Asim, A. Idris, T. Iqbal, and F. Martínez-Álvarez, “Earthquake prediction model using support vector regressor and hybrid neural networks, ” PLOS ONE, vol. 13, no. 7, p. e0199004, Jul. 2018, doi: 10.1371/journal.pone.0199004.

[9]. J. Buch, A. P. Williams, C. S. Juang, W. D. Hansen, and P. Gentine, “SMLFire1.0: a stochastic machine learning (SML) model for wildfire activity in the western United States, ” Geosci. Model Dev., vol. 16, no. 12, pp. 3407–3433, Jun. 2023, doi: 10.5194/gmd-16-3407-2023.

[10]. L. Jin, C. Yao, and X.-Y. Huang, “A Nonlinear Artificial Intelligence Ensemble Prediction Model for Typhoon Intensity, ” Mon. Weather Rev., vol. 136, no. 12, pp. 4541–4554, Dec. 2008, doi: 10.1175/2008MWR2269.1.

[11]. F. Meng, Y. Yao, Z. Wang, S. Peng, D. Xu, and T. Song, “Probabilistic forecasting of tropical cyclones intensity using machine learning model, ” Environ. Res. Lett., vol. 18, no. 4, p. 044042, Apr. 2023, doi: 10.1088/1748-9326/acc8eb.

[12]. H. Liu et al., “A Hybrid Machine Learning/Physics‐Based Modeling Framework for 2‐Week Extended Prediction of Tropical Cyclones, ” J. Geophys. Res. Mach. Learn. Comput., vol. 1, no. 3, p. e2024JH000207, Sep. 2024, doi: 10.1029/2024JH000207.

[13]. X.-Y. Xu, M. Shao, P.-L. Chen, and Q.-G. Wang, “Tropical Cyclone Intensity Prediction Using Deep Convolutional Neural Network, ” Atmosphere, vol. 13, no. 5, p. 783, May 2022, doi: 10.3390/atmos13050783.

References

[1]. A. M. F. Lagmay et al., “Devastating storm surges of Typhoon Haiyan, ” Int. J. Disaster Risk Reduct., vol. 11, pp. 1–12, Mar. 2015, doi: 10.1016/j.ijdrr.2014.10.006.

[4]. R. Chen, W. Zhang, and X. Wang, “Machine Learning in Tropical Cyclone Forecast Modeling: A Review, ” Atmosphere, vol. 11, no. 7, p. 676, Jun. 2020, doi: 10.3390/atmos11070676.

[7]. A. Mosavi, P. Ozturk, and K. Chau, “Flood Prediction Using Machine Learning Models: Literature Review, ” Water, vol. 10, no. 11, p. 1536, Oct. 2018, doi: 10.3390/w10111536.

Cite this article

Yu,Y. (2025). Track-Centric Machine Learning for 24-Hour Peak-Intensity Forecasting of Western North Pacific Typhoons. Applied and Computational Engineering,196,14-23.

Data availability

The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.

About volume

Volume title: Proceedings of CONF-MLA 2025 Symposium: Intelligent Systems and Automation: AI Models, IoT, and Robotic Algorithms

ISBN: 978-1-80590-451-9(Print) / 978-1-80590-452-6(Online)

Editor: Hisham AbouGrad

Conference website: https://www.confmla.org/london.html

Conference date: 12 November 2025

Series: Applied and Computational Engineering

Volume number: Vol.196

ISSN: 2755-2721(Print) / 2755-273X(Online)

© 2024 by the author(s). Licensee EWA Publishing, Oxford, UK. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license. Authors who publish this series agree to the following terms:

1. Authors retain copyright and grant the series right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this series.

2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the series's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this series.

3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open access policy for details).