Statistical Analysis of Medium‐Scale Traveling Ionospheric Disturbances Over Japan Based on Deep Learning Instance Segmentation
Abstract Medium‐scale traveling ionospheric disturbances (MSTIDs) are observed as parallelly arrayed wavelike perturbations of Total Electron Content (TEC) in ionospheric F region leading to satellite navigation error and communication signal scintillation. The observation method for MSTIDs, detrend...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-07-01
|
| Series: | Space Weather |
| Subjects: | |
| Online Access: | https://doi.org/10.1029/2022SW003151 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536458006986752 |
|---|---|
| author | Peng Liu Tatsuhiro Yokoyama Weizheng Fu Mamoru Yamamoto |
| author_facet | Peng Liu Tatsuhiro Yokoyama Weizheng Fu Mamoru Yamamoto |
| author_sort | Peng Liu |
| collection | DOAJ |
| description | Abstract Medium‐scale traveling ionospheric disturbances (MSTIDs) are observed as parallelly arrayed wavelike perturbations of Total Electron Content (TEC) in ionospheric F region leading to satellite navigation error and communication signal scintillation. The observation method for MSTIDs, detrended TEC (dTEC) map, summarizes the perturbation component of TEC having the merits of full‐time and two‐dimensional. However, previous automatic processing methods for dTEC map cannot discriminate MSTIDs from other irregular ionospheric perturbations intelligently. With the development of artificial intelligence in recent years, deep learning approach is expecting to clarify the controversy of MSTID external dependence (season and solar/geomagnetic activity) under debating for decades. Therefore, this research proposes a real‐time processing algorithm for dTEC maps based on Mask Region‐Convolutional Neural Network (R‐CNN) model of deep learning instance segmentation to detect wavelike perturbations intelligently with an accuracy of about 80% and a processing speed of about 8 fps. Then isolated perturbations are eliminated and only MSTID waveforms are chosen to obtain statistical characteristics of MSTIDs. With this algorithm, we analyzed up to 1,209,600 dTEC maps from 1997 to 2019 over Japan automatically and established a database of hourly averaged MSTID characteristics. This research introduces the partial correlation coefficient for the first time to clarify the solar/geomagnetic activity dependence of MSTID characteristics which is independent with each other. |
| format | Article |
| id | doaj-art-0a47b89f623848e0b377892b67b61747 |
| institution | Kabale University |
| issn | 1542-7390 |
| language | English |
| publishDate | 2022-07-01 |
| publisher | Wiley |
| record_format | Article |
| series | Space Weather |
| spelling | doaj-art-0a47b89f623848e0b377892b67b617472025-01-14T16:26:58ZengWileySpace Weather1542-73902022-07-01207n/an/a10.1029/2022SW003151Statistical Analysis of Medium‐Scale Traveling Ionospheric Disturbances Over Japan Based on Deep Learning Instance SegmentationPeng Liu0Tatsuhiro Yokoyama1Weizheng Fu2Mamoru Yamamoto3Research Institute for Sustainable Humanosphere Kyoto University Uji JapanResearch Institute for Sustainable Humanosphere Kyoto University Uji JapanResearch Institute for Sustainable Humanosphere Kyoto University Uji JapanResearch Institute for Sustainable Humanosphere Kyoto University Uji JapanAbstract Medium‐scale traveling ionospheric disturbances (MSTIDs) are observed as parallelly arrayed wavelike perturbations of Total Electron Content (TEC) in ionospheric F region leading to satellite navigation error and communication signal scintillation. The observation method for MSTIDs, detrended TEC (dTEC) map, summarizes the perturbation component of TEC having the merits of full‐time and two‐dimensional. However, previous automatic processing methods for dTEC map cannot discriminate MSTIDs from other irregular ionospheric perturbations intelligently. With the development of artificial intelligence in recent years, deep learning approach is expecting to clarify the controversy of MSTID external dependence (season and solar/geomagnetic activity) under debating for decades. Therefore, this research proposes a real‐time processing algorithm for dTEC maps based on Mask Region‐Convolutional Neural Network (R‐CNN) model of deep learning instance segmentation to detect wavelike perturbations intelligently with an accuracy of about 80% and a processing speed of about 8 fps. Then isolated perturbations are eliminated and only MSTID waveforms are chosen to obtain statistical characteristics of MSTIDs. With this algorithm, we analyzed up to 1,209,600 dTEC maps from 1997 to 2019 over Japan automatically and established a database of hourly averaged MSTID characteristics. This research introduces the partial correlation coefficient for the first time to clarify the solar/geomagnetic activity dependence of MSTID characteristics which is independent with each other.https://doi.org/10.1029/2022SW003151MSTIDionospheric irregularitywavelike perturbationstatistical analysisdeep learninginstance segmentation |
| spellingShingle | Peng Liu Tatsuhiro Yokoyama Weizheng Fu Mamoru Yamamoto Statistical Analysis of Medium‐Scale Traveling Ionospheric Disturbances Over Japan Based on Deep Learning Instance Segmentation Space Weather MSTID ionospheric irregularity wavelike perturbation statistical analysis deep learning instance segmentation |
| title | Statistical Analysis of Medium‐Scale Traveling Ionospheric Disturbances Over Japan Based on Deep Learning Instance Segmentation |
| title_full | Statistical Analysis of Medium‐Scale Traveling Ionospheric Disturbances Over Japan Based on Deep Learning Instance Segmentation |
| title_fullStr | Statistical Analysis of Medium‐Scale Traveling Ionospheric Disturbances Over Japan Based on Deep Learning Instance Segmentation |
| title_full_unstemmed | Statistical Analysis of Medium‐Scale Traveling Ionospheric Disturbances Over Japan Based on Deep Learning Instance Segmentation |
| title_short | Statistical Analysis of Medium‐Scale Traveling Ionospheric Disturbances Over Japan Based on Deep Learning Instance Segmentation |
| title_sort | statistical analysis of medium scale traveling ionospheric disturbances over japan based on deep learning instance segmentation |
| topic | MSTID ionospheric irregularity wavelike perturbation statistical analysis deep learning instance segmentation |
| url | https://doi.org/10.1029/2022SW003151 |
| work_keys_str_mv | AT pengliu statisticalanalysisofmediumscaletravelingionosphericdisturbancesoverjapanbasedondeeplearninginstancesegmentation AT tatsuhiroyokoyama statisticalanalysisofmediumscaletravelingionosphericdisturbancesoverjapanbasedondeeplearninginstancesegmentation AT weizhengfu statisticalanalysisofmediumscaletravelingionosphericdisturbancesoverjapanbasedondeeplearninginstancesegmentation AT mamoruyamamoto statisticalanalysisofmediumscaletravelingionosphericdisturbancesoverjapanbasedondeeplearninginstancesegmentation |