Identification of tropical cyclone centre based on satellite images via deep learning techniques. (14th November 2022)

• Record Type: Journal Article
• Authors: Long, Teng; Fu, Jiyang; Tong, Biao; Chan, Pakwai; He, Yuncheng
• Is Part Of: International journal of climatology. Volume 42:Number 16(2022)
• Page Start: 10373
• Page End: 10386
• Publication Date: 2022-11-14
• Subjects: deep learning -- identification of tropical cyclone centre -- satellite image -- tropical cyclone -- YOLOv4; Climatology -- Periodicals; Climat -- Périodiques; Climatologie -- Périodiques; 551.605
• DOI: 10.1002/joc.7909
• Languages: English
• ISSNs: 0899-8418

Abstract

Abstract: A tropical cyclone (TC) is a highly destructive natural disaster. Accurate identification of key parameters of TCs is prerequisite for most TC‐related research and practices. The centre position is one of TC's basic parameters. However, comparison of TC best track data released by different meteorological institutes usually indicates a noticeable discrepancy for this parameter among varied data sources. In this study, efforts are made towards identifying the centre location of TCs via deep learning techniques, based on TC satellite cloud images (SCIs). Six deep learning models are analysed and compared. YOLOv4 model achieved a confidence of 99.84%, which is better than other models. In addition, we further explore the factors affecting the positioning accuracy of the YOLOv4 model and its application to the location identification of multiple TCs and the tracking of individual TCs. Results demonstrate that the YOLOv4 model has a probability exceeding 99% for identifying multiple TC locations and also performs well for single TC tracking. Abstract : Centre position is one of TC's basic parameters, but significant discrepancies exist among the TC best track data about this parameter issued by different meteorological institutes. In this study, efforts are made towards identifying the centre location of TCs via deep learning techniques, based on TC satellite cloud images. The results are expected to be useful for determining TCs' centre location objectively and efficiently.