文章详情

摘要

在气象学和灾害管理领域，热带气旋（Tropical Cyclone, TC）的强度估测具有至关重要的意义。随着科技的进步，基于深度学习的方法在热带气旋强度估测上展现出了卓越的性能，为相关领域的研究和实践提供了有力支持。文章聚焦于热带气旋的时空特征，并结合深度学习技术提出了一种创新的TC强度估测方法—Time-space 3D Network（T3D-Net）模型。该模型在TCIR数据集上的MAE为6.92 kt，RMSE为9.14 kt，与现有的多个热带气旋强度估测方法相比，该方法展现出了一定的竞争性和优越性。

关键词

热带气旋强度估测；3D卷积神经网络；TCIR；时空特征

参考文献

1. [1] 丁嘉慕，乐璐辉，杭仁龙.融合物理信息的热带气旋强度估计 [J].计算机系统应用，2024，33（9）：28-37.
2. [2] MOLINARI J，VOLLARO D，ROBASKY F. Use of ECMWF Operational Analyses for Studies of the Tropical Cyclone Environment [J].Meteorology and Atmospheric Physics，1992，47（2）：127-144.
3. [3] DVORAK V F. A Technique for the Analysis and Forecasting of Tropical Cyclone Intensities from Satellite Pictures [C]//NOAA Technical Memorandum NESS 45.Washington：NOAA，1973：1-47.
4. [4] DVORAK V F. Tropical Cyclone Intensity Analysis and Forecasting from Satellite Imagery [J].Monthly Weather Review，1975，103（5）：420-430.
5. [5] MA Z，YAN Y，LIN J，MA D. A Multiscale and Multilayer Feature Extraction Network with Dual Attention for Tropical Cyclone Intensity Estimation [J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：1-15.
6. [6] ZHANG R，LIU Q S，HANG R L. Tropical Cyclone Intensity Estimation Using Two-Branch Convolutional Neural Network from Infrared and Water Vapor Images [J].IEEE Transactions on Geoscience and Remote Sensing，2020，58（1）：586-597.
7. [7] TIAN W，ZHOU X，HUANG W，et al. Tropical Cyclone Intensity Estimation Using Multidimensional Convolutional Neural Network from Multichannel Satellite Imagery [J].IEEE Geoscience and Remote Sensing Letters，2021，19：1-5.
8. [8] ZHANG C J，WANG X J，MA L M，et al. Tropical Cyclone Intensity Classification and Estimation Using Infrared Satellite Images with Deep Learning [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2021，14：2070-2086.
9. [9] ZHANG R，LIU Y，YUE L，et al. Estimating Tropical Cyclone Intensity Using an STIA Model from Himawari-8 Satellite Images in the Western North Pacific Basin [J].IEEE Transactions on Geoscience and Remote Sensing，2024，62：1-13.
10. [10] TIAN M，ZHANG T，LIU G，et al. Estimation of Tropical Cyclone Intensity Using Synthetic Satellite Microwave Temperature Anomaly Structure and a Multifeature Distribution Learning Network [J].IEEE Transactions on Geoscience and Remote Sensing，2022，60：1-12.
11. [11] JIANG W，ZHANG H，TIAN M. Tropical Cyclone Intensity Estimation Based on Satellite Microwave Brightness Temperature Data: Utilizing the Maa Network and Dual-Branch Network Training Method [C]//2024 IEEE International Geoscience and Remote Sensing Symposium.Athens：IEEE，2024：7146-7150.
12. [12] LIN L，WENG F. Estimation of Hurricane Maximum Wind Speed Using Temperature Anomaly Derived from Advanced Technology Microwave Sounder [J].IEEE Geoscience and Remote Sensing Letters，2018，15（5）：639-643.
13. [13] CHEN Z，YU X. A Novel Tensor Network for Tropical Cyclone Intensity Estimation [J].IEEE Transactions on Geoscience and Remote Sensing，2021，59：3226-3243.
14. [14] ZHUO J Y，TAN Z M. Physics-Augmented Deep Learning to Improve Tropical Cyclone Intensity and Size Estimation from Satellite Imagery [J].Monthly Weather Review，2021，149（7）：2097-2113.
15. [15] CHEN B，CHEN B F，LIN H T. Rotation-Blended CNNs on a New Open Dataset for Tropical Cyclone Image-to-Intensity Regression [C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York：ACM，2018：90-99.
16. [16] JIANG W J，HU G，WU T T，et al. DMANet_KF: Tropical Cyclone Intensity Estimation Based on Deep Learning and Kalman Filter from Multispectral Infrared Images [J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2023，16：4469-4483.

作者简介

王瑜（1998—），女，汉族，河北沧州人，硕士研究生，研究方向：深度学习、图像处理。