Developing a Data-Driven Transfer Learning Model to Locate Tropical Cyclone Centers on Satellite Infrared Imagery

doi:10.1175/JTECH-D-23-0026.1

IOCAS-IR > 海洋环流与波动重点实验室

	Developing a Data-Driven Transfer Learning Model to Locate Tropical Cyclone Centers on Satellite Infrared Imagery
	Wang, Chong 1,2; Li, Xiaofeng 1
	2023-12-01
发表期刊	JOURNAL OF ATMOSPHERIC AND OCEANIC TECHNOLOGY
ISSN	0739-0572
卷号	40 期号:12 页码:1417-1430
通讯作者	Li, Xiaofeng(lixf@qdio.ac.cn)
摘要	In this paper, a data-driven transfer learning (TL) model for locating tropical cyclone (TC) centers from satellite infrared images in the northwest Pacific is developed. A total of 2450 satellite infrared TC images derived from 97 TCs between 2015 and 2018 were used for this paper. The TC center location model (ResNet-TCL) with added residual fully connected modules is built for the TC center location. The MAE of the ResNet-TCL model is 34.8 km. Then TL is used to improve the model performance, including obtaining a pretrained model based on the ImageNet dataset, transfer -ring the pretrained model parameters to the ResNet-TCL model, and using TC satellite infrared imagery to fine-train the ResNet-TCL model. The results show that the TL-based model improves the location accuracy by 14.1% (29.3 km) over the no-TL model. The model performance increases logarithmically with the amount of training data. When the training data are large, the benefit of increasing the training samples is smaller than the benefit of using TL. The comparison of model results with the best track data of TCs shows that the MAEs of TCs center is 29.3 km for all samples and less than 20 km for H2-H5 TCs. In addition, the visualization of the TL-based TC center location model shows that the TL model can accurately extract the most important features related to TC center location, including TC eye, TC texture, and con -tour. On the other hand, the no-TL model does not accurately extract these features.
关键词	Tropical cyclones Remote sensing Deep learning
DOI	10.1175/JTECH-D-23-0026.1
收录类别	SCI
语种	英语
资助项目	Qingdao National Laboratory for Marine Science and Technology ; Special fund of Shandong Province[LSKJ202204302] ; Key Project of the Center for Ocean Mega-Science, Chinese Academy of Sciences[COMS2019R02] ; Strategic Priority Research Program of the Chinese Academy of Sciences[XDB42000000] ; National Natural Science Foundation of China[U2006211] ; Major scientific and technological innovation projects in Shandong Province[2019JZZY010102]
WOS研究方向	Engineering ; Meteorology & Atmospheric Sciences
WOS类目	Engineering, Ocean ; Meteorology & Atmospheric Sciences
WOS记录号	WOS:001124830200001
出版者	AMER METEOROLOGICAL SOC
WOS关键词	ADVANCED DVORAK TECHNIQUE ; OBJECTIVE DETECTION ; INTENSITY ; HY-2
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.qdio.ac.cn/handle/337002/184180
专题	海洋环流与波动重点实验室
通讯作者	Li, Xiaofeng
作者单位	1.Chinese Acad Sci, Inst Oceanog, CAS Key Lab Ocean Circulat & Waves, Qingdao, Peoples R China 2.Univ Chinese Acad Sci, Beijing, Peoples R China
第一作者单位	中国科学院海洋研究所
通讯作者单位	中国科学院海洋研究所
推荐引用方式 GB/T 7714	Wang, Chong,Li, Xiaofeng. Developing a Data-Driven Transfer Learning Model to Locate Tropical Cyclone Centers on Satellite Infrared Imagery[J]. JOURNAL OF ATMOSPHERIC AND OCEANIC TECHNOLOGY,2023,40(12):1417-1430.
APA	Wang, Chong,&Li, Xiaofeng.(2023).Developing a Data-Driven Transfer Learning Model to Locate Tropical Cyclone Centers on Satellite Infrared Imagery.JOURNAL OF ATMOSPHERIC AND OCEANIC TECHNOLOGY,40(12),1417-1430.
MLA	Wang, Chong,et al."Developing a Data-Driven Transfer Learning Model to Locate Tropical Cyclone Centers on Satellite Infrared Imagery".JOURNAL OF ATMOSPHERIC AND OCEANIC TECHNOLOGY 40.12(2023):1417-1430.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
atot-JTECH-D-23-0026（40204KB）	期刊论文	出版稿	限制开放	CC BY-NC-SA	浏览