Next Article in Journal
Landslide Susceptibility Assessment in Ya’an Based on Coupling of GWR and TabNet
Previous Article in Journal
A Case Study on the Vertical Distribution and Correlation Between Low-Frequency Lightning Sources and Hydrometeors During a Thunderstorm
 
 
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Review

Beyond the Backbone: A Quantitative Review of Deep-Learning Architectures for Tropical Cyclone Track Forecasting

1
School of Systems and Computing, University of New South Wales at Canberra, Canberra 2612, Australia
2
School of Science, University of New South Wales at Canberra, Canberra 2612, Australia
3
Geoscience Australia, Canberra 2609, Australia
*
Author to whom correspondence should be addressed.
Remote Sens. 2025, 17(15), 2675; https://doi.org/10.3390/rs17152675 (registering DOI)
Submission received: 30 June 2025 / Revised: 30 July 2025 / Accepted: 31 July 2025 / Published: 2 August 2025
(This article belongs to the Section AI Remote Sensing)

Abstract

Accurate forecasting of tropical cyclone (TC) tracks is critical for disaster preparedness and risk mitigation. While traditional numerical weather prediction (NWP) systems have long served as the backbone of operational forecasting, they face limitations in computational cost and sensitivity to initial conditions. In recent years, deep learning (DL) has emerged as a promising alternative, offering data-driven modeling capabilities for capturing nonlinear spatiotemporal patterns. This paper presents a comprehensive review of DL-based approaches for TC track forecasting. We categorize all DL-based TC tracking models according to the architecture, including recurrent neural networks (RNNs), convolutional neural networks (CNNs), Transformers, graph neural networks (GNNs), generative models, and Fourier-based operators. To enable rigorous performance comparison, we introduce a Unified Geodesic Distance Error (UGDE) metric that standardizes evaluation across diverse studies and lead times. Based on this metric, we conduct a critical comparison of state-of-the-art models and identify key insights into their relative strengths, limitations, and suitable application scenarios. Building on this framework, we conduct a critical cross-model analysis that reveals key trends, performance disparities, and architectural tradeoffs. Our analysis also highlights several persistent challenges, such as long-term forecast degradation, limited physical integration, and generalization to extreme events, pointing toward future directions for developing more robust and operationally viable DL models for TC track forecasting. To support reproducibility and facilitate standardized evaluation, we release an open-source UGDE conversion tool on GitHub.
Keywords: tropical cyclone forecasting; deep learning; artificial intelligence; track prediction; tropical cyclone forecasting review tropical cyclone forecasting; deep learning; artificial intelligence; track prediction; tropical cyclone forecasting review

Share and Cite

MDPI and ACS Style

Huang, H.; Deng, D.; Hu, L.; Chen, Y.; Sun, N. Beyond the Backbone: A Quantitative Review of Deep-Learning Architectures for Tropical Cyclone Track Forecasting. Remote Sens. 2025, 17, 2675. https://doi.org/10.3390/rs17152675

AMA Style

Huang H, Deng D, Hu L, Chen Y, Sun N. Beyond the Backbone: A Quantitative Review of Deep-Learning Architectures for Tropical Cyclone Track Forecasting. Remote Sensing. 2025; 17(15):2675. https://doi.org/10.3390/rs17152675

Chicago/Turabian Style

Huang, He, Difei Deng, Liang Hu, Yawen Chen, and Nan Sun. 2025. "Beyond the Backbone: A Quantitative Review of Deep-Learning Architectures for Tropical Cyclone Track Forecasting" Remote Sensing 17, no. 15: 2675. https://doi.org/10.3390/rs17152675

APA Style

Huang, H., Deng, D., Hu, L., Chen, Y., & Sun, N. (2025). Beyond the Backbone: A Quantitative Review of Deep-Learning Architectures for Tropical Cyclone Track Forecasting. Remote Sensing, 17(15), 2675. https://doi.org/10.3390/rs17152675

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.
Back to TopTop