MSFF-CAA-ResNet: multi-scale and attention-enhanced residual network for tropical cyclone center location

Zhengtang CHEN; Ye TAO; Chong WANG; Yanli WU

doi:10.1007/s00343-025-5251-5

Your Location：

Home >

Browse articles >

MSFF-CAA-ResNet: multi-scale and attention-enhanced residual network for tropical cyclone center location

Updated：2026-09-15

- MSFF-CAA-ResNet: multi-scale and attention-enhanced residual network for tropical cyclone center location
- Journal of Oceanology and Limnology Pages: 1-13(2026)
- Affiliations：
  
  1.Qingdao University of Science and Technology, Qingdao 266061, China
  2.Key Laboratory of Ocean Circulation and Waves, Institute of Oceanology, Chinese Academy of Sciences, Qingdao 266071, China
- Author bio：
  
  ye.tao@qust.edu.cn
  wangchong1@qdio.ac.cn
- Funds：
- DOI：10.1007/s00343-025-5251-5
  CLC：
- Received：07 July 2025，
  
  Online First：15 September 2026，
- Accepted：
Scan QR Code
CHEN Zhengtang,TAO Ye,WANG Chong,et al.MSFF-CAA-ResNet: multi-scale and attention-enhanced residual network for tropical cyclone center location[J].Journal of Oceanology and Limnology,
DOI：

CHEN Zhengtang,TAO Ye,WANG Chong,et al.MSFF-CAA-ResNet: multi-scale and attention-enhanced residual network for tropical cyclone center location[J].Journal of Oceanology and Limnology, DOI：.

摘要

Abstract

To locate the tropical cyclone (TC) center is a critical task for reducing the impact of TC. However

traditional deep-learning methods struggle to extract high-dimensional features from the cloud structure of TC

leading to significant errors in the center location. We collected ~16 000 infrared images from the HURSAT-B1 Global Tropical Cyclone Satellite Dataset

covering TC samples from multiple satellite remote sensing platforms and ocean regions

and designed a TC center location model MSFF-CAA-ResNet that is built upon the classic residual structure by introducing the multi-scale feature fusion (MSFF) module and the center-aware attention (CAA) module

which works synergistically to enhance the model’s ability to locate the TC center position. Experimental results show that the MSFF-CAA-ResNet model could not only adapt to multi-source remote sensing platforms but also achieve high-precision TC center location worldwide. Ablation experiments indicate that both MSFF and CAA contribute to TC center location. The improved MSFF-CAA-ResNet-F model achieves an average location error of 23.9 km

representing a 12.7% reduction compared to the baseline model. Interpretability analysis shows that the MSFF-CAA-ResNet-F model focuses more on the central features of TCs compared to the baseline model. This indicates that the MSFF-CAA-ResNet-F model holds promising application prospects.

关键词

Keywords

references

Chavas D R , Knaff J A . 2022 . A simple model for predicting the tropical cyclone radius of maximum wind from outer size . Weather and Forecasting , 37 ( 5 ): 563 - 579 , https://doi.org/10.1175/WAF-D-21-0103.1 https://doi.org/10.1175/WAF-D-21-0103.1 .

Dumitru C O , Andrei V , Schwarz G et al . 2019 . Machine learning for sea ice monitoring from satellites. The International Archives of the Photogrammetry , Remote Sensing and Spatial Information Sciences , XLII-2/W16 : 83 - 89 , https://doi.org/10.5194/isprs-archives-XLII-2-W16-83-2019 https://doi.org/10.5194/isprs-archives-XLII-2-W16-83-2019 .

Fett R W , Brand S . 1975 . Tropical cyclone movement forecasts based on observations from satellites . Journal of Applied Meteorology , 14 ( 4 ): 452 - 465 , https://doi.org/10.1175/1520-0450(1975)014%3C0452:TCMFBO%3E2.0.CO;2 https://doi.org/10.1175/1520-0450(1975)014%3C0452:TCMFBO%3E2.0.CO;2 .

Giffard-Roisin S , Yang M , Charpiat G et al . 2020 . Tropical cyclone track forecasting using fused deep learning from aligned reanalysis data. Frontiers in Big Data , 3 : 1 , https://doi.org/10.3389/fdata.2020.00001 https://doi.org/10.3389/fdata.2020.00001 .

Horn M , Walsh K , Zhao M et al . 2014 . Tracking scheme dependence of simulated tropical cyclone response to idealized climate simulations . Journal of Climate , 27 ( 24 ): 9197 - 9213 , https://doi.org/10.1175/JCLI-D-14-00200.1 https://doi.org/10.1175/JCLI-D-14-00200.1 .

Hu Y Y , Zou X L . 2021 . Tropical cyclone center positioning using single channel microwave satellite observations of brightness temperature . Remote Sensing , 13 ( 13 ): 2466 , https://doi.org/10.3390/rs13132466 https://doi.org/10.3390/rs13132466 .

Jin S H , Li X F , Yang X F et al . 2019 . Identification of tropical cyclone centers in SAR imagery based on template matching and particle swarm optimization algorithms . IEEE Transactions on Geoscience and Remote Sensing , 57 ( 1 ): 598 - 608 , https://doi.org/10.1109/TGRS.2018.2863259 https://doi.org/10.1109/TGRS.2018.2863259 .

Lee J , Moon I J , Im J et al . 2025 . Multi-task feature transfer deep learning-based tropical cyclone center estimation (MFT-TC) using geostationary satellite observations. Weather and Climate Extremes , 49 : 100796 , https://doi.org/10.1016/j.wace.2025.100796 https://doi.org/10.1016/j.wace.2025.100796 .

Lee R S T , Lin J N K . 2001 . An elastic contour matching model for tropical cyclone pattern recognition. IEEE Transactions on Systems , Man , and Cybernetics , Part B (Cybernetics) , 31 ( 3 ): 413 - 417 , https://doi.org/10.1109/3477.931532 https://doi.org/10.1109/3477.931532 .

Li X F , Zhou Y , Wang F . 2022 . Advanced information mining from ocean remote sensing imagery with deep learning. Journal of Remote Sensing , 2022 : 9849645 , https://doi.org/10.34133/2022/9849645 https://doi.org/10.34133/2022/9849645 .

Liu J , Zhang Q . 2022 . Objective detection of a tropical cyclone’s center using satellite image sequences in the northwest Pacific . Atmosphere , 13 ( 3 ): 381 , https://doi.org/10.3390/atmos13030381 https://doi.org/10.3390/atmos13030381 .

Olander T L , Velden C S . 2019 . The advanced Dvorak technique (ADT) for estimating tropical cyclone intensity: update and new capabilities . Weather and Forecasting , 34 ( 4 ): 905 - 922 , https://doi.org/10.1175/WAF-D-19-0007.1 https://doi.org/10.1175/WAF-D-19-0007.1 .

Pradhan R , Aygun R S , Maskey M et al . 2018 . Tropical cyclone intensity estimation using a deep convolutional neural network . IEEE Transactions on Image Processing , 27 ( 2 ): 692 - 702 , https://doi.org/10.1109/TIP.2017.2766358 https://doi.org/10.1109/TIP.2017.2766358 .

Szegedy C , Liu W , Jia Y Q et al . 2015 . Going deeper with convolutions . In: Proceedings of the 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) . IEEE , Boston, USA . p. 1 - 9 , https://doi.org/10.1109/CVPR.2015.7298594 https://doi.org/10.1109/CVPR.2015.7298594 .

Tan C . 2021 . TCLNet: learning to locate typhoon center using deep neural network . In: Proceedings of the 2021 IEEE International Geoscience and Remote Sensing Symposium (IGARSS) . IEEE, Brussels, Belgium . p. 4600 - 4603 , https://doi.org/10.1109/IGARSS47720.2021.9554524 https://doi.org/10.1109/IGARSS47720.2021.9554524 .

Velden C , Harper B , Wells F et al . 2006 . The Dvorak tropical cyclone intensity estimation technique: a satellite-based method that has endured for over 30 years . Bulletin of the American Meteorological Society , 87 ( 9 ): 1195 - 1210 , https://doi.org/10.1175/BAMS-87-9-1195 https://doi.org/10.1175/BAMS-87-9-1195 .

Wang C , Li X F , Zheng G . 2024a . Tropical cyclone intensity forecasting using model knowledge guided deep learning model . Environmental Research Letters , 19 ( 2 ): 024006 , https://doi.org/10.1088/1748-9326/ad1bde https://doi.org/10.1088/1748-9326/ad1bde .

Wang C , Li X F . 2023a . Developing a data-driven transfer learning model to locate tropical cyclone centers on satellite infrared imagery . Journal of Atmospheric and Oceanic Technology , 40 ( 12 ): 1605 - 1618 , https://doi.org/10.1175/JTECH-D-23-0026.1 https://doi.org/10.1175/JTECH-D-23-0026.1 .

Wang C , Li X F . 2023b . Deep learning in extracting tropical cyclone intensity and wind radius information from satellite infrared images—a review . Atmospheric and Oceanic Science Letters , 16 ( 4 ): 100373 , https://doi.org/10.1016/j.aosl.2023.100373 https://doi.org/10.1016/j.aosl.2023.100373 .

Wang C , Li X F . 2023c . A deep learning model for estimating tropical cyclone wind radius from geostationary satellite infrared imagery . Monthly Weather Review , 151 ( 2 ): 403 - 417 , https://doi.org/10.1175/MWR-D-22-0166.1 https://doi.org/10.1175/MWR-D-22-0166.1 .

Wang C , Xu Q , Li X F et al . 2019 . An objective technique for typhoon monitoring with satellite infrared imagery . In: Proceedings of the 2019 Photonics & Electromagnetics Research Symposium-Fall (PIERS-Fall) . IEEE, Xiamen, China . p. 3218 - 3221 , https://doi.org/10.1109/PIERS-Fall48861.2019.9021497 https://doi.org/10.1109/PIERS-Fall48861.2019.9021497 .

Wang C , Yang N , Li X F . 2025 . Advancing forecasting capabilities: a contrastive learning model for forecasting tropical cyclone rapid intensification . Proceedings of the National Academy of Sciences of the United States of America , 122 ( 4 ): e 2415501122 , https://doi.org/10.1073/pnas.2415501122 https://doi.org/10.1073/pnas.2415501122 .

Wang C , Zheng G , Li X F et al . 2021a . Tropical cyclone intensity estimation from geostationary satellite imagery using deep convolutional neural networks. IEEE Transactions on Geoscience and Remote Sensing , 60 : 4101416 , https://doi.org/10.1109/TGRS.2021.3066299 https://doi.org/10.1109/TGRS.2021.3066299 .

Wang H Y , Li X F . 2024a . Expanding horizons: U-net enhancements for semantic segmentation, forecasting, and super-resolution in ocean remote sensing. Journal of Remote Sensing , 4 : 0196 , https://doi.org/10.34133/remotesensing.0196 https://doi.org/10.34133/remotesensing.0196 .

Wang H Y , Li X F . 2024b . DeepBlue: advanced convolutional neural network applications for ocean remote sensing . IEEE Geoscience and Remote Sensing Magazine , 12 ( 1 ): 138 - 161 , https://doi.org/10.1109/MGRS.2023.3343623 https://doi.org/10.1109/MGRS.2023.3343623 .

Wang H , Xu Q , Yin X B et al . 2024b . Determination of low-intensity tropical cyclone centers in geostationary satellite images using a physics-enhanced deep-learning model. IEEE Transactions on Geoscience and Remote Sensing , 62 : 4202810 , https://doi.org/10.1109/TGRS.2024.3363842 https://doi.org/10.1109/TGRS.2024.3363842 .

Wang L , Wan B C , Zhou S H et al . 2023 . Forecasting tropical cyclone tracks in the northwestern Pacific based on a deep-learning model . Geoscientific Model Development , 16 ( 8 ): 2167 - 2179 , https://doi.org/10.5194/gmd-16-2167-2023 https://doi.org/10.5194/gmd-16-2167-2023 .

Wang P P , Wang P , Wang C et al . 2020 . A center location algorithm for tropical cyclone in satellite infrared images . IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing , 13 : 2161 - 2172 , https://doi.org/10.1109/JSTARS.2020.2995158 https://doi.org/10.1109/JSTARS.2020.2995158 .

Wang P , Yang X , Ji Z et al . 2021b . A typhoon center location method on satellite images based on deep reinforcement learning . In: Proceedings of the 40th Chinese Control Conference (CCC) . IEEE , Shanghai, China . p. 7046 - 7053 , https://doi.org/10.23919/CCC52363.2021.9550197 https://doi.org/10.23919/CCC52363.2021.9550197 .

Wu Y X , He K M . 2018 . Group Normalization . arXiv e-prints , 2018: arXiv: 1803 . 08494 . https://doi.org/10.48550/arXiv.1803.08494 https://doi.org/10.48550/arXiv.1803.08494 .

Xiao F J , Xiao Z N . 2010 . Characteristics of tropical cyclones in China and their impacts analysis . Natural Hazards , 54 ( 3 ): 827 - 837 , https://doi.org/10.1007/s11069-010-9508-7 https://doi.org/10.1007/s11069-010-9508-7 .

Xu J , Li Z , Du B et al . 2020 Reluplex made more practical: Leaky ReLU . In 2020 IEEE Symposium on Computers and communications (ISCC) . IEEE, Rennes, France , p. 1 - 7 , https://doi.org/10.1109/ISCC50000.2020.9219587.

Yang X , Zhan Z Q , Shen J P et al . 2019 . A deep learning based method for typhoon recognition and typhoon center location . In: Proceedings of the 2019 IEEE International Geoscience and Remote Sensing Symposium . IEEE, Yokohama, Japan . p. 3218 - 3221 , https://doi.org/10.1109/IGARSS.2019.8899322 https://doi.org/10.1109/IGARSS.2019.8899322 .

Yurchak B S . 2007 . Description of cloud-rain bands in a tropical cyclone by a hyperbolic-logarithmic spiral . Russian Meteorology and Hydrology , 32 ( 1 ): 8 - 18 , https://doi.org/10.3103/S1068373907010025 https://doi.org/10.3103/S1068373907010025 .

Zhang G S , Perrie W , Zhang B et al . 2020 . Monitoring of tropical cyclone structures in ten years of RADARSAT-2 SAR images. Remote Sensing of Environment , 236 : 111449 , https://doi.org/10.1016/j.rse.2019.111449 https://doi.org/10.1016/j.rse.2019.111449 .

Zhang Q , Wu L G , Liu Q F . 2009 . Tropical cyclone damages in China 1983-2006 . Bulletin of the American Meteorological Society , 90 ( 4 ): 489 - 496 , https://doi.org/10.1175/2008BAMS2631.1 https://doi.org/10.1175/2008BAMS2631.1 .

Zhang X D , Li X F . 2022 . Satellite data-driven and knowledge-informed machine learning model for estimating global internal solitary wave speed. Remote Sensing of Environment , 283 : 113328 , https://doi.org/10.1016/j.rse.2022.113328 https://doi.org/10.1016/j.rse.2022.113328 .

Zhang X D , Li X F . 2024 . Constructing a 22-year internal wave dataset for the northern South China Sea: spatiotemporal analysis using MODIS imagery and deep learning . Earth System Science Data , 16 ( 11 ): 5131 - 5144 , https://doi.org/10.5194/essd-16-5131-2024 https://doi.org/10.5194/essd-16-5131-2024 .

Zheng Y G , Zhang H S , Qi K T et al . 2022 . Stripe segmentation of oceanic internal waves in SAR images based on SegNet . Geocarto International , 37 ( 25 ): 8567 - 8578 , https://doi.org/10.1080/10106049.2021.2002430 https://doi.org/10.1080/10106049.2021.2002430 .

Zhou F F , Toth Z . 2020 . On the prospects for improved tropical cyclone track forecasts . Bulletin of the American Meteorological Society , 101 ( 12 ): E2058 - E2077 , https://doi.org/10.1175/BAMS-D-19-0166.1 https://doi.org/10.1175/BAMS-D-19-0166.1 .

Zhou P , Xie X Y , Lin Z C et al . 2024a . Towards understanding convergence and generalization of AdamW . IEEE Transactions on Pattern Analysis and Machine Intelligence , 46 ( 9 ): 6486 - 6493 , https://doi.org/10.1109/TPAMI.2024.3382294 https://doi.org/10.1109/TPAMI.2024.3382294 .

Zhou Y X , Min M , Li J et al . 2024b . Enhanced typhoon center localization using geostationary satellite imagery . Geophysical Research Letters , 51 ( 22 ): e2024 GL 112252 , https://doi.org/10.1029/2024GL112252 https://doi.org/10.1029/2024GL112252 .

Views

Downloads

CSCD

Alert me when the article has been cited

Submit

Tools

Publicity Resources

A global-local multi-scale feature extraction network for fine-grained segmentation of cyanobacterial blooms and aquatic vegetation

Enhancing sea ice classification on SAR imagery by integrating texture and polarimetric information with a deep learning model

A multi-attention and edge deep supervision neural network for capturing floating Ulva prolifera using GF-1 satellite imagery

A physics-enhanced deep-learning model for estimating turbid shallow water depth from SAR images

Prediction of sea surface pCO2 in the South China Sea using Spatiotemporal Convolutional LSTM model

Related Author

Yunchang MU

Junsheng LI

Huan ZHAO

Xiaodi ZHU

Zeyan ZHANG

Fangfang ZHANG

Shenglei WANG

Lichen GAO

Related Institution

Beijing Institute of Surveying and Mapping

College of Resources and Environment, University of Chinese Academy of Sciences

Satellite Application Center for Ecology and Environment, Ministry of Ecology and Environment of the People's Republic of China

School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences

Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences

Address：Editorial Office of JOL, 88 Haijun Rd. Qingdao, 266000, China
Tel：+86-532-82898754 Email：jol@qdio.ac.cn
Technical support is provided by Beijing Founder electronics co., LTD 京ICP备09064830号-19 京公网安备11010802024621
It is recommended to read the content of this site in Chrome&IE9+. Please switch to extreme mode in browser 360.
Cookies We use cookies to help provide and enhance our service and tailor content. By continuing, you agree to the use of cookies.

⁰