Automatic Identification of Aurora Fold Structure in All-Sky Images
Identification of small-scale auroral structures is key to searching for auroral events. However, it is impracticable for humans to manually select sufficient aurora events for statistical analysis, and it is also challenging for computers because of the non-rigid shape and fluid nature of auroras....
Published in: | Universe |
---|---|
Main Authors: | , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
MDPI AG
2023
|
Subjects: | |
Online Access: | https://doi.org/10.3390/universe9020079 https://doaj.org/article/2e25533422ac4d03a4b06be68c92e67f |
id |
ftdoajarticles:oai:doaj.org/article:2e25533422ac4d03a4b06be68c92e67f |
---|---|
record_format |
openpolar |
spelling |
ftdoajarticles:oai:doaj.org/article:2e25533422ac4d03a4b06be68c92e67f 2023-05-15T17:48:28+02:00 Automatic Identification of Aurora Fold Structure in All-Sky Images Qian Wang Haonan Fang Bin Li 2023-02-01T00:00:00Z https://doi.org/10.3390/universe9020079 https://doaj.org/article/2e25533422ac4d03a4b06be68c92e67f EN eng MDPI AG https://www.mdpi.com/2218-1997/9/2/79 https://doaj.org/toc/2218-1997 doi:10.3390/universe9020079 2218-1997 https://doaj.org/article/2e25533422ac4d03a4b06be68c92e67f Universe, Vol 9, Iss 79, p 79 (2023) aurora all-sky image aurora fold structure small-scale structure skeleton extraction automatic identification Elementary particle physics QC793-793.5 article 2023 ftdoajarticles https://doi.org/10.3390/universe9020079 2023-02-26T01:28:04Z Identification of small-scale auroral structures is key to searching for auroral events. However, it is impracticable for humans to manually select sufficient aurora events for statistical analysis, and it is also challenging for computers because of the non-rigid shape and fluid nature of auroras. Fold structure is the most common type of auroral small-scale structure, and its appearance is indicative of a variety of auroral events. This paper proposes a small-scale aurora structure identification framework to automatically detect aurora fold structures. First, the location and shape of auroras are identified based on a deep learning segmentation network. Then, the skeleton of the auroral shape is extracted to represent the trajectories of auroras. Finally, the proposed skeleton-based fold identification module (SFIM) can detect the aurora fold structure. To evaluate the effectiveness of the proposed method, we built an aurora fold structure sample dataset, namely F-dataset, containing 2000 images at 557.7 nm obtained by the all-sky imagers at Yellow River Station (YRS), Ny-Ålesund, Svalbard. Experimental results show that automatic identification can achieve good consistency with human perception. Statistical analysis of over 30,000 images shows that the fold occurrence has a distinct double-peak distribution at pre-noon and post-noon. Article in Journal/Newspaper Ny Ålesund Ny-Ålesund Svalbard Directory of Open Access Journals: DOAJ Articles Ny-Ålesund Svalbard Universe 9 2 79 |
institution |
Open Polar |
collection |
Directory of Open Access Journals: DOAJ Articles |
op_collection_id |
ftdoajarticles |
language |
English |
topic |
aurora all-sky image aurora fold structure small-scale structure skeleton extraction automatic identification Elementary particle physics QC793-793.5 |
spellingShingle |
aurora all-sky image aurora fold structure small-scale structure skeleton extraction automatic identification Elementary particle physics QC793-793.5 Qian Wang Haonan Fang Bin Li Automatic Identification of Aurora Fold Structure in All-Sky Images |
topic_facet |
aurora all-sky image aurora fold structure small-scale structure skeleton extraction automatic identification Elementary particle physics QC793-793.5 |
description |
Identification of small-scale auroral structures is key to searching for auroral events. However, it is impracticable for humans to manually select sufficient aurora events for statistical analysis, and it is also challenging for computers because of the non-rigid shape and fluid nature of auroras. Fold structure is the most common type of auroral small-scale structure, and its appearance is indicative of a variety of auroral events. This paper proposes a small-scale aurora structure identification framework to automatically detect aurora fold structures. First, the location and shape of auroras are identified based on a deep learning segmentation network. Then, the skeleton of the auroral shape is extracted to represent the trajectories of auroras. Finally, the proposed skeleton-based fold identification module (SFIM) can detect the aurora fold structure. To evaluate the effectiveness of the proposed method, we built an aurora fold structure sample dataset, namely F-dataset, containing 2000 images at 557.7 nm obtained by the all-sky imagers at Yellow River Station (YRS), Ny-Ålesund, Svalbard. Experimental results show that automatic identification can achieve good consistency with human perception. Statistical analysis of over 30,000 images shows that the fold occurrence has a distinct double-peak distribution at pre-noon and post-noon. |
format |
Article in Journal/Newspaper |
author |
Qian Wang Haonan Fang Bin Li |
author_facet |
Qian Wang Haonan Fang Bin Li |
author_sort |
Qian Wang |
title |
Automatic Identification of Aurora Fold Structure in All-Sky Images |
title_short |
Automatic Identification of Aurora Fold Structure in All-Sky Images |
title_full |
Automatic Identification of Aurora Fold Structure in All-Sky Images |
title_fullStr |
Automatic Identification of Aurora Fold Structure in All-Sky Images |
title_full_unstemmed |
Automatic Identification of Aurora Fold Structure in All-Sky Images |
title_sort |
automatic identification of aurora fold structure in all-sky images |
publisher |
MDPI AG |
publishDate |
2023 |
url |
https://doi.org/10.3390/universe9020079 https://doaj.org/article/2e25533422ac4d03a4b06be68c92e67f |
geographic |
Ny-Ålesund Svalbard |
geographic_facet |
Ny-Ålesund Svalbard |
genre |
Ny Ålesund Ny-Ålesund Svalbard |
genre_facet |
Ny Ålesund Ny-Ålesund Svalbard |
op_source |
Universe, Vol 9, Iss 79, p 79 (2023) |
op_relation |
https://www.mdpi.com/2218-1997/9/2/79 https://doaj.org/toc/2218-1997 doi:10.3390/universe9020079 2218-1997 https://doaj.org/article/2e25533422ac4d03a4b06be68c92e67f |
op_doi |
https://doi.org/10.3390/universe9020079 |
container_title |
Universe |
container_volume |
9 |
container_issue |
2 |
container_start_page |
79 |
_version_ |
1766154542867546112 |