This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Typhoon Trajectory Prediction by Three CNN+ Deep-Learning Approaches
by
Gang Lin
Gang Lin 1,2,
Yanchun Liang
Yanchun Liang 1,*,
Adriano Tavares
Adriano Tavares 2,
Carlos Lima
Carlos Lima 2 and
Dong Xia
Dong Xia 3
1
School of Computer Science, Zhuhai College of Science and Technology, Zhuhai 519041, China
2
Department of Industrial Electronics, School of Engineering, University of Minho, 4800-058 Guimares, Portugal
3
Zhuhai-Macao Collaborative Research Center for Meteorological Innovation and Application, Zhuhai 519000, China
*
Author to whom correspondence should be addressed.
Electronics 2024, 13(19), 3851; https://doi.org/10.3390/electronics13193851 (registering DOI)
Submission received: 10 August 2024
/
Revised: 24 September 2024
/
Accepted: 27 September 2024
/
Published: 28 September 2024
Abstract
The accuracy in predicting the typhoon track can be key to minimizing their frequent disastrous effects. This article aims to study the accuracy of typhoon trajectory prediction obtained by combining several algorithms based on current deep-learning techniques. The combination of a Convolutional Neural Network with Long Short-Term Memory (CNN+LSTM), Patch Time-Series Transformer (CNN+PatchTST) and Transformer (CNN+Transformer) were the models chosen for this work. These algorithms were tested on the best typhoon track data from the China Meteorological Administration (CMA), ERA5 data from the European Centre for Medium-Range Weather Forecasts (ECMWF), and structured meteorological data from the Zhuhai Meteorological Bureau (ZMB) as an extension of existing studies that were based only on public data sources. The experimental results were obtained by testing two complete years of data (2021 and 2022), as an alternative to the frequent selection of a small number of typhoons in several years. Using the R-squared metric, results were obtained as significant as CNN+LSTM (0.991), CNN+PatchTST (0.989) and CNN+Transformer (0.969). CNN+LSTM without ZMB data can only obtain 0.987, i.e., 0.004 less than 0.991. Overall, our findings indicate that appropriately augmenting data near land and ocean boundaries around the coast improves typhoon track prediction.
Share and Cite
MDPI and ACS Style
Lin, G.; Liang, Y.; Tavares, A.; Lima, C.; Xia, D.
Typhoon Trajectory Prediction by Three CNN+ Deep-Learning Approaches. Electronics 2024, 13, 3851.
https://doi.org/10.3390/electronics13193851
AMA Style
Lin G, Liang Y, Tavares A, Lima C, Xia D.
Typhoon Trajectory Prediction by Three CNN+ Deep-Learning Approaches. Electronics. 2024; 13(19):3851.
https://doi.org/10.3390/electronics13193851
Chicago/Turabian Style
Lin, Gang, Yanchun Liang, Adriano Tavares, Carlos Lima, and Dong Xia.
2024. "Typhoon Trajectory Prediction by Three CNN+ Deep-Learning Approaches" Electronics 13, no. 19: 3851.
https://doi.org/10.3390/electronics13193851
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article Access Statistics
For more information on the journal statistics, click
here.
Multiple requests from the same IP address are counted as one view.