GNSS TEC-Based Earthquake Ionospheric Perturbation Detection Using a Novel Deep Learning Framework
In this article, a new method for seismic ionospheric Global Navigation Satellite System (GNSS) total electron content (TEC) based anomaly detection using a deep learning framework is proposed. The performance of the proposed encoder–decoder long short-term memory extended model is compar...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9779580/ |
| _version_ | 1818253866370596864 |
|---|---|
| author | Pan Xiong Cheng Long Huiyu Zhou Xuemin Zhang Xuhui Shen |
| author_facet | Pan Xiong Cheng Long Huiyu Zhou Xuemin Zhang Xuhui Shen |
| author_sort | Pan Xiong |
| collection | DOAJ |
| description | In this article, a new method for seismic ionospheric Global Navigation Satellite System (GNSS) total electron content (TEC) based anomaly detection using a deep learning framework is proposed. The performance of the proposed encoder–decoder long short-term memory extended model is compared with those of five other benchmarking predictors. The proposed model achieves the best performance (<italic>R</italic><sup>2</sup> = 0.9105 and root-mean-square error (RMSE) = 2.6759) in predicting TEC time series data, demonstrating a 20% improvement in <italic>R</italic><sup>2</sup> and 39.1% improvement in the RMSE over the autoregressive integrated moving average model. To detect the pre-earthquake ionospheric disturbances more accurately, a reasonable strategy for determining anomaly limits is also proposed. Finally, the method is applied to analyze the pre-earthquake ionospheric TEC disturbance of the 2016 Xinjiang <italic>M</italic><sub><italic>s</italic></sub> 6.2 earthquake. By excluding the effects of solar activity and geomagnetic activity, obvious ionospheric anomalies could be observed, occurring during 4–8 days prior to, and on 1 day before, the earthquake. Negative anomalies tended to occur in the earlier period, whereas positive anomalies occurred closer to the earthquake time, with increasing anomaly intensity with temporal proximity. Furthermore, confusion analysis is used in this article to verify the reliability of the proposed model. The proposed model achieves significant improvements in predicting GNSS TEC time series and is shown to advance the performance of earthquake anomaly detection technology. |
| first_indexed | 2024-12-12T16:46:53Z |
| format | Article |
| id | doaj.art-fa1e69cacc994007b42dfea9c42d3ab9 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-12-12T16:46:53Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-fa1e69cacc994007b42dfea9c42d3ab92022-12-22T00:18:27ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352022-01-01154248426310.1109/JSTARS.2022.31759619779580GNSS TEC-Based Earthquake Ionospheric Perturbation Detection Using a Novel Deep Learning FrameworkPan Xiong0https://orcid.org/0000-0003-1447-7806Cheng Long1https://orcid.org/0000-0001-6806-8405Huiyu Zhou2https://orcid.org/0000-0003-1634-9840Xuemin Zhang3Xuhui Shen4https://orcid.org/0000-0001-9796-9149Institute of Earthquake Forecasting, China Earthquake Administration, Beijing, ChinaSchool of Computer Science and Engineering, Nanyang Technological University, SingaporeSchool of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K.Institute of Earthquake Forecasting, China Earthquake Administration, Beijing, ChinaNational Institute of Natural Hazards, Ministry of Emergency Management of China, Beijing, ChinaIn this article, a new method for seismic ionospheric Global Navigation Satellite System (GNSS) total electron content (TEC) based anomaly detection using a deep learning framework is proposed. The performance of the proposed encoder–decoder long short-term memory extended model is compared with those of five other benchmarking predictors. The proposed model achieves the best performance (<italic>R</italic><sup>2</sup> = 0.9105 and root-mean-square error (RMSE) = 2.6759) in predicting TEC time series data, demonstrating a 20% improvement in <italic>R</italic><sup>2</sup> and 39.1% improvement in the RMSE over the autoregressive integrated moving average model. To detect the pre-earthquake ionospheric disturbances more accurately, a reasonable strategy for determining anomaly limits is also proposed. Finally, the method is applied to analyze the pre-earthquake ionospheric TEC disturbance of the 2016 Xinjiang <italic>M</italic><sub><italic>s</italic></sub> 6.2 earthquake. By excluding the effects of solar activity and geomagnetic activity, obvious ionospheric anomalies could be observed, occurring during 4–8 days prior to, and on 1 day before, the earthquake. Negative anomalies tended to occur in the earlier period, whereas positive anomalies occurred closer to the earthquake time, with increasing anomaly intensity with temporal proximity. Furthermore, confusion analysis is used in this article to verify the reliability of the proposed model. The proposed model achieves significant improvements in predicting GNSS TEC time series and is shown to advance the performance of earthquake anomaly detection technology.https://ieeexplore.ieee.org/document/9779580/Anomaly detectiondeep learningearthquakeionospheric perturbationtime series prediction |
| spellingShingle | Pan Xiong Cheng Long Huiyu Zhou Xuemin Zhang Xuhui Shen GNSS TEC-Based Earthquake Ionospheric Perturbation Detection Using a Novel Deep Learning Framework IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Anomaly detection deep learning earthquake ionospheric perturbation time series prediction |
| title | GNSS TEC-Based Earthquake Ionospheric Perturbation Detection Using a Novel Deep Learning Framework |
| title_full | GNSS TEC-Based Earthquake Ionospheric Perturbation Detection Using a Novel Deep Learning Framework |
| title_fullStr | GNSS TEC-Based Earthquake Ionospheric Perturbation Detection Using a Novel Deep Learning Framework |
| title_full_unstemmed | GNSS TEC-Based Earthquake Ionospheric Perturbation Detection Using a Novel Deep Learning Framework |
| title_short | GNSS TEC-Based Earthquake Ionospheric Perturbation Detection Using a Novel Deep Learning Framework |
| title_sort | gnss tec based earthquake ionospheric perturbation detection using a novel deep learning framework |
| topic | Anomaly detection deep learning earthquake ionospheric perturbation time series prediction |
| url | https://ieeexplore.ieee.org/document/9779580/ |
| work_keys_str_mv | AT panxiong gnsstecbasedearthquakeionosphericperturbationdetectionusinganoveldeeplearningframework AT chenglong gnsstecbasedearthquakeionosphericperturbationdetectionusinganoveldeeplearningframework AT huiyuzhou gnsstecbasedearthquakeionosphericperturbationdetectionusinganoveldeeplearningframework AT xueminzhang gnsstecbasedearthquakeionosphericperturbationdetectionusinganoveldeeplearningframework AT xuhuishen gnsstecbasedearthquakeionosphericperturbationdetectionusinganoveldeeplearningframework |