Automatic detection method of polar cap arc based on YOLOX embedded with CBAM

• Published in: Frontiers in environmental science Vol. 12
• Main Authors: Lu, Yang, Jiang, Jianan, Zhong, Jia, Wang, Yong, Wang, Xiangyu, Zou, Ziming
• Format: Journal Article
• Language: English
• Published: Frontiers Media S.A 20.09.2024
• Subjects: aurora; deep-learning; DMSP; polar cap arc; SSUSI; YOLOX
• ISSN: 2296-665X; 2296-665X
• DOI: 10.3389/fenvs.2024.1418207

The aurora arc is a separate auroral structure from the aurora oval, whose location and morphology are related to various solar-terrestrial circumstances. However, because of the low occurring frequency of aurora arc and the lack of the automatic identification technique, it can only be manually distinguished from a huge number of observed images, which is very inefficient. In order to improve the identification efficiency, we propose an identification algorithm based on YOLOX network and Convolutional Block Attention Module attention mechanism. Using the aurora images observed by Special Sensor Ultraviolet Spectrographic Imager carried by the Defense Meteorological Satellite Program F16-F19 satellites from 2013 to 2019, the automatic detection models for global and local areas were trained separately. The identification outputs will be integrated by calculating the intersection. According to the test results, the event identification precision is 86% and the position identification precision is 79%, both of which are greater than the results before integration. Therefore, the proposed method is not only able to identify whether the image contains the aurora arcs, but also accurately locate them, making it a highly effective tool for the advancement of future study.