Aurora retrieval in all-sky images based on hash vision transformer
Auroras are bright occurrences when high-energy particles from the magnetosphere and solar wind enter Earth's atmosphere through the magnetic field and collide with atoms in the upper atmosphere. The morphological and temporal characteristics of auroras are essential for studying large-scale ma...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2023-10-01
|
| Series: | Heliyon |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2405844023078179 |
| _version_ | 1797646513350901760 |
|---|---|
| author | Hengyue Zhang Hailiang Tang Wenxiao Zhang |
| author_facet | Hengyue Zhang Hailiang Tang Wenxiao Zhang |
| author_sort | Hengyue Zhang |
| collection | DOAJ |
| description | Auroras are bright occurrences when high-energy particles from the magnetosphere and solar wind enter Earth's atmosphere through the magnetic field and collide with atoms in the upper atmosphere. The morphological and temporal characteristics of auroras are essential for studying large-scale magnetospheric processes. While auroras are visible to the naked eye from the ground, scientists use deep learning algorithms to analyze all-sky images to understand this phenomenon better. However, the current algorithms face challenges due to inefficient utilization of global features and neglect the excellent fusion of local and global feature representations extracted from aurora images. Hence, this paper introduces a Hash-Transformer model based on Vision Transformer for aurora retrieval from all-sky images. Experimental results based on real-world data demonstrate that the proposed method effectively improves aurora image retrieval performance. It provides a new avenue to study aurora phenomena and facilitates the development of related fields. |
| first_indexed | 2024-03-11T15:02:43Z |
| format | Article |
| id | doaj.art-57c4e262e4f4472199e441f35d44195b |
| institution | Directory Open Access Journal |
| issn | 2405-8440 |
| language | English |
| last_indexed | 2024-03-11T15:02:43Z |
| publishDate | 2023-10-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Heliyon |
| spelling | doaj.art-57c4e262e4f4472199e441f35d44195b2023-10-30T06:06:45ZengElsevierHeliyon2405-84402023-10-01910e20609Aurora retrieval in all-sky images based on hash vision transformerHengyue Zhang0Hailiang Tang1Wenxiao Zhang2School of Information Science and Engineering, Qilu Normal University, Jinan, 250200, ChinaSchool of Information Science and Engineering, Qilu Normal University, Jinan, 250200, China; Corresponding author.School of Finance and Economics, Shandong University of Engineering and Vocational Technology, Jinan, ChinaAuroras are bright occurrences when high-energy particles from the magnetosphere and solar wind enter Earth's atmosphere through the magnetic field and collide with atoms in the upper atmosphere. The morphological and temporal characteristics of auroras are essential for studying large-scale magnetospheric processes. While auroras are visible to the naked eye from the ground, scientists use deep learning algorithms to analyze all-sky images to understand this phenomenon better. However, the current algorithms face challenges due to inefficient utilization of global features and neglect the excellent fusion of local and global feature representations extracted from aurora images. Hence, this paper introduces a Hash-Transformer model based on Vision Transformer for aurora retrieval from all-sky images. Experimental results based on real-world data demonstrate that the proposed method effectively improves aurora image retrieval performance. It provides a new avenue to study aurora phenomena and facilitates the development of related fields.http://www.sciencedirect.com/science/article/pii/S2405844023078179Aurora image retrievalVision transformerDeep learningAll-sky images |
| spellingShingle | Hengyue Zhang Hailiang Tang Wenxiao Zhang Aurora retrieval in all-sky images based on hash vision transformer Heliyon Aurora image retrieval Vision transformer Deep learning All-sky images |
| title | Aurora retrieval in all-sky images based on hash vision transformer |
| title_full | Aurora retrieval in all-sky images based on hash vision transformer |
| title_fullStr | Aurora retrieval in all-sky images based on hash vision transformer |
| title_full_unstemmed | Aurora retrieval in all-sky images based on hash vision transformer |
| title_short | Aurora retrieval in all-sky images based on hash vision transformer |
| title_sort | aurora retrieval in all sky images based on hash vision transformer |
| topic | Aurora image retrieval Vision transformer Deep learning All-sky images |
| url | http://www.sciencedirect.com/science/article/pii/S2405844023078179 |
| work_keys_str_mv | AT hengyuezhang auroraretrievalinallskyimagesbasedonhashvisiontransformer AT hailiangtang auroraretrievalinallskyimagesbasedonhashvisiontransformer AT wenxiaozhang auroraretrievalinallskyimagesbasedonhashvisiontransformer |