Sheng Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sheng Li has a total of 33 co-authors. Here are the top co-authors by number of shared publications:
- Yang-Yi Sun
Institute of Geophysics and Geomatics China University of Geosciences Wuhan China
5 shared publications - Jana Safrankova
Faculty of Mathematics and Physics Charles University Prague Czech Republic
4 shared publications - Chieh-Hung Chen
State Key Laboratory of Geohazard Prevention and Geoenvironment Protection Chengdu University of Technology Chengdu China
3 shared publications - Gilbert Pi
Faculty of Mathematics and Physics Charles University Prague Czech Republic
3 shared publications - Zdenek Nemecek
Faculty of Mathematics and Physics Charles University Prague Czech Republic
3 shared publications Gilbert Pi
2 shared publications
Latest Publications
- Open Access
- 26 September 2026
- Published by American Geophysical Union (AGU) in Space Weather
- Vol. 24 (9)
Forecasting Geomagnetically Induced Currents From Solar Wind and Geoelectric Field Data Using Deep Learning: Application in Fujian, China
We developed a multi‐module convolutional neural network combined with a multi‐head attention mechanism (MM‐CNN‐MHA) to forecast geomagnetically induced currents (GICs) at the Huangmeishan (HMS) 220‐kV substation in Fujian Province, China. The model was trained using solar wind parameters, geomagnetic disturbances, and geoelectric field observations from 2010 to 2021. Five GIC estimation or prediction methods were evaluated: (a) GICs calculated from geoelectric fields predicted by MM‐CNN‐MHA; (b) direct GICs prediction using MM‐CNN‐MHA; (c) GICs calculated from measured geoelectric fields; (d) GICs calculated using a one‐dimensional (1D) conductivity model; and (e) GICs calculated using magnetotelluric (MT) impedance data. The results show that the GICs calculated from measured geoelectric fields achieved the highest accuracy, with a root‐mean‐square error (RMSE) of 0.24 A, and better reproduced the observed GICs peaks. The GICs calculated from MM‐CNN‐MHA‐predicted geoelectric fields outperformed the directly predicted GICs, with RMSE values of 0.26 and 0.28 A, respectively. In contrast, the GICs calculated using the 1D conductivity model and MT impedance method generally overestimate GICs peaks, with RMSE values of 0.52 and 0.39 A, respectively. These findings further highlight the importance of local geoelectric field observations for GIC monitoring and forecasting and demonstrate that preserving the physical chain from solar wind, geomagnetic disturbances, and geoelectric fields to GICs improves the stability and reliability of GIC predictions.
- 26 September 2026
- Published by American Geophysical Union (AGU) in Space Weather
- Vol. 24 (9)
Open AccessForecasting Geomagnetically Induced Currents From Solar Wind and Geoelectric Field Data Using Deep Learning: Application in Fujian, China
We developed a multi‐module convolutional neural network combined with a multi‐head attention mechanism (MM‐CNN‐MHA) to forecast geomagnetically induced currents (GICs) at the Huangmeishan (HMS) 220‐kV substation in Fujian Province, China. The model was trained using solar wind parameters, geomagnetic disturbances, and geoelectric field observations from 2010 to 2021. Five GIC estimation or prediction methods were evaluated: (a) GICs calculated from geoelectric fields predicted by MM‐CNN‐MHA; (b) direct GICs prediction using MM‐CNN‐MHA; (c) GICs calculated from measured geoelectric fields; (d) GICs calculated using a one‐dimensional (1D) conductivity model; and (e) GICs calculated using magnetotelluric (MT) impedance data. The results show that the GICs calculated from measured geoelectric fields achieved the highest accuracy, with a root‐mean‐square error (RMSE) of 0.24 A, and better reproduced the observed GICs peaks. The GICs calculated from MM‐CNN‐MHA‐predicted geoelectric fields outperformed the directly predicted GICs, with RMSE values of 0.26 and 0.28 A, respectively. In contrast, the GICs calculated using the 1D conductivity model and MT impedance method generally overestimate GICs peaks, with RMSE values of 0.52 and 0.39 A, respectively. These findings further highlight the importance of local geoelectric field observations for GIC monitoring and forecasting and demonstrate that preserving the physical chain from solar wind, geomagnetic disturbances, and geoelectric fields to GICs improves the stability and reliability of GIC predictions.
- 28 June 2026
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Space Physics
- Vol. 131 (7)
Disturbances in Atmospheric Electric Field and Collocated Geophysical Parameters Recorded by the MVP‐LAI System During the May 2024 Great Geomagnetic Storm
Our Earth experienced an extreme solar storm on the Mother's Day weekend from 10–12 May 2024, leading to the most severe geomagnetic storm in the past two decades. In addition to significant changes in the near‐Earth space environment from the magnetosphere to the ionosphere, this study primarily shows notable disturbances in the atmospheric electric field ( Ez ), as recorded by the electric field mill of the MVP‐LAI (Monitoring Vibrations and Perturbations in the Lithosphere, Atmosphere, and Ionosphere) system located in LeShan (29.6°N, 103.9°E; L‐shell value ∼1.12), Sichuan Province, during the initial and main phases of the storm. Here, we employed a data‐adaptive method to identify storm characteristics by resolving complex changes in atmospheric Ez over short to long periods. For further investigating causal mechanisms, we also analyzed the collocated measurements of the MVP‐LAI system, including atmospheric pressure, geomagnetic fields, ionospheric total electron content (TEC), and High‐frequency Doppler echoes over LeShan, as well as the ionosonde echoes at DaoFu (31.0°N, 101.12°E) and the magnetic field observation from Geostationary Operational Environmental Satellite (GOES) 16 at ∼6.6 Earth radii. The key finding is the nearly coincident disturbances from space to the atmospheric Ez at ∼20:00 UT, which indicated the possible impact of electrodynamic changes on the atmosphere at the time of storm onset. Short‐period perturbations (with frequency >1 mHz) observed in the ionospheric TEC, atmospheric pressure and electric field suggest the appearance of acoustic resonance in the atmosphere during the storm's main phase.
- 28 June 2026
- Published by American Geophysical Union (AGU) in Journal of Geophysical Research: Space Physics
- Vol. 131 (7)
Disturbances in Atmospheric Electric Field and Collocated Geophysical Parameters Recorded by the MVP‐LAI System During the May 2024 Great Geomagnetic Storm
Our Earth experienced an extreme solar storm on the Mother's Day weekend from 10–12 May 2024, leading to the most severe geomagnetic storm in the past two decades. In addition to significant changes in the near‐Earth space environment from the magnetosphere to the ionosphere, this study primarily shows notable disturbances in the atmospheric electric field ( Ez ), as recorded by the electric field mill of the MVP‐LAI (Monitoring Vibrations and Perturbations in the Lithosphere, Atmosphere, and Ionosphere) system located in LeShan (29.6°N, 103.9°E; L‐shell value ∼1.12), Sichuan Province, during the initial and main phases of the storm. Here, we employed a data‐adaptive method to identify storm characteristics by resolving complex changes in atmospheric Ez over short to long periods. For further investigating causal mechanisms, we also analyzed the collocated measurements of the MVP‐LAI system, including atmospheric pressure, geomagnetic fields, ionospheric total electron content (TEC), and High‐frequency Doppler echoes over LeShan, as well as the ionosonde echoes at DaoFu (31.0°N, 101.12°E) and the magnetic field observation from Geostationary Operational Environmental Satellite (GOES) 16 at ∼6.6 Earth radii. The key finding is the nearly coincident disturbances from space to the atmospheric Ez at ∼20:00 UT, which indicated the possible impact of electrodynamic changes on the atmosphere at the time of storm onset. Short‐period perturbations (with frequency >1 mHz) observed in the ionospheric TEC, atmospheric pressure and electric field suggest the appearance of acoustic resonance in the atmosphere during the storm's main phase.
- Open Access
- 10 April 2026
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 53 (8)
Evolution of Magnetospheric Boundary Layers Under the 10 May 2024 ICME Impact
On 10 May 2024, an interplanetary coronal mass ejection‐driven shock impacted the dayside magnetopause, compressing it to ∼5 R E . A northward interplanetary magnetic field suppressed dayside reconnection and allowed a clear investigation of the magnetosphere response. We use coordinated GOES and THEMIS observations to examine the magnetopause motion and its boundary layer evolution. Our study provides, for the first time, ion energy flux spectra, pitch angle distributions, and ion moments derived from the GOES‐16 data. The energy flux spectrum from GOES‐16 reveals a geostationary magnetopause crossing 32 s prior to the magnetosheath magnetic field turning southward. The magnetopause was compressed at a speed of ∼300 km s −1 , with the depletion layer thickening by a factor of 3.8. We identify a localized compressed region that expands rapidly earthward. Within this region, a rare three‐energy‐level ion structure is observed, indicating the transport of ions from a plasmaspheric plume.
- 10 April 2026
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 53 (8)
Open AccessEvolution of Magnetospheric Boundary Layers Under the 10 May 2024 ICME Impact
On 10 May 2024, an interplanetary coronal mass ejection‐driven shock impacted the dayside magnetopause, compressing it to ∼5 R E . A northward interplanetary magnetic field suppressed dayside reconnection and allowed a clear investigation of the magnetosphere response. We use coordinated GOES and THEMIS observations to examine the magnetopause motion and its boundary layer evolution. Our study provides, for the first time, ion energy flux spectra, pitch angle distributions, and ion moments derived from the GOES‐16 data. The energy flux spectrum from GOES‐16 reveals a geostationary magnetopause crossing 32 s prior to the magnetosheath magnetic field turning southward. The magnetopause was compressed at a speed of ∼300 km s −1 , with the depletion layer thickening by a factor of 3.8. We identify a localized compressed region that expands rapidly earthward. Within this region, a rare three‐energy‐level ion structure is observed, indicating the transport of ions from a plasmaspheric plume.
- Open Access
- 13 March 2026
- Published by Copernicus GmbH
GOES Plasma Observations Applied to the Magnetospheric Boundary Study
Geostationary Operational Environmental Satellites (GOES) in geostationary orbit (GEO) have previously been utilized for magnetospheric studies using magnetic field data; however, plasma measurements from GOES have received little attention. Since GOES-16, the onboard Magnetospheric Particle Sensors - Low Energy instrument has allowed measurements of ions and electrons in the range from ~30 eV to 30 keV. During extreme solar wind conditions, boundary layers, dayside magnetopause, and even the bow shock may be compressed to GEO, making plasma measurements from GOES valuable for providing energy flux spectra, pitch-angle distributions, and plasma moments at this position, as well as for conjunction observations with other missions. In this study, we present coordinated GOES and THEMIS observations during the 10 May 2024 solar wind event. The energy flux data for both missions are shown. We identify a new structure on the inner side of the magnetopause, which we term a “compression layer”, within which a “three-energy-level” structure is observed. We suggest that both structures are related to pure compression under northward IMF and the plasmaspheric plume. We also show that the bow shock was temporarily compressed to GEO during this event, and we further present additional examples illustrating the application of GOES plasma observations to magnetospheric boundary studies.
- 13 March 2026
- Published by Copernicus GmbH
Open AccessGOES Plasma Observations Applied to the Magnetospheric Boundary Study
Geostationary Operational Environmental Satellites (GOES) in geostationary orbit (GEO) have previously been utilized for magnetospheric studies using magnetic field data; however, plasma measurements from GOES have received little attention. Since GOES-16, the onboard Magnetospheric Particle Sensors - Low Energy instrument has allowed measurements of ions and electrons in the range from ~30 eV to 30 keV. During extreme solar wind conditions, boundary layers, dayside magnetopause, and even the bow shock may be compressed to GEO, making plasma measurements from GOES valuable for providing energy flux spectra, pitch-angle distributions, and plasma moments at this position, as well as for conjunction observations with other missions. In this study, we present coordinated GOES and THEMIS observations during the 10 May 2024 solar wind event. The energy flux data for both missions are shown. We identify a new structure on the inner side of the magnetopause, which we term a “compression layer”, within which a “three-energy-level” structure is observed. We suggest that both structures are related to pure compression under northward IMF and the plasmaspheric plume. We also show that the bow shock was temporarily compressed to GEO during this event, and we further present additional examples illustrating the application of GOES plasma observations to magnetospheric boundary studies.
- Open Access
- 18 March 2025
- Published by Copernicus GmbH
Magnetospheric Response to the Mother’s Day Weekend Geomagnetic Storm: Observations from Geostationary Satellites
The Mother’s Day weekend geomagnetic storm during 10-11 May 2024 is one of the most intense events in recent decades. At least two interplanetary coronal mass ejections (ICMEs) erupted from the active region 13664 on 8 May stacked together, causing the shock observed at the L1 point on 10 May at 17:05 UT. In this study, we utilized geostationary orbit satellite observations to investigate the disturbance of magnetic fields and particles inside the Earth’s magnetosphere. There are four significant findings in this study. First, the subsolar magnetopause had already compressed from about 11.7 RE (at 13:18 UT) to 8.6 RE (at 16:59 UT) before the shock arrival, which THEMIS-A observed, then compressed below 6.6 RE (i.e., geostationary orbit) because of the ICME. Second, Magnetospheric Particle Sensors onboard GOES-16 and GOES-18 detected proton flux increases inside the magnetosphere from about 15:00 UT before the shock arrived. Third, the Energetic Heavy Ion Sensor onboard the GOES-16 and GOES-18 satellites detected helium flux increases on 10 May at about 14:09 and 14:44 UT, respectively. Fourth, the GOES magnetometer recorded the southward magnetic field BZ on 11 May when the two satellites were in the tail region.
- 18 March 2025
- Published by Copernicus GmbH
Open AccessMagnetospheric Response to the Mother’s Day Weekend Geomagnetic Storm: Observations from Geostationary Satellites
The Mother’s Day weekend geomagnetic storm during 10-11 May 2024 is one of the most intense events in recent decades. At least two interplanetary coronal mass ejections (ICMEs) erupted from the active region 13664 on 8 May stacked together, causing the shock observed at the L1 point on 10 May at 17:05 UT. In this study, we utilized geostationary orbit satellite observations to investigate the disturbance of magnetic fields and particles inside the Earth’s magnetosphere. There are four significant findings in this study. First, the subsolar magnetopause had already compressed from about 11.7 RE (at 13:18 UT) to 8.6 RE (at 16:59 UT) before the shock arrival, which THEMIS-A observed, then compressed below 6.6 RE (i.e., geostationary orbit) because of the ICME. Second, Magnetospheric Particle Sensors onboard GOES-16 and GOES-18 detected proton flux increases inside the magnetosphere from about 15:00 UT before the shock arrived. Third, the Energetic Heavy Ion Sensor onboard the GOES-16 and GOES-18 satellites detected helium flux increases on 10 May at about 14:09 and 14:44 UT, respectively. Fourth, the GOES magnetometer recorded the southward magnetic field BZ on 11 May when the two satellites were in the tail region.
- Open Access
- 15 May 2023
- Published by Copernicus GmbH
Interpretable Machine Learning Procedure Unravels Hidden Interplanetary Drivers of the Low Latitude Dayside Magnetopause
Interplanetary parameters such as solar wind and interplanetary magnetic fields (IMF) drive the shape and size of the magnetopause jointly, which has complex relationships. In this study, we proposed an interpretable machine learning procedure to disentangle the influences of interplanetary parameters on the magnetopause standoff distance (MSD) and sort their importance in the MSD simulation. A magnetopause crossings database from the THEMIS satellites and interplanetary parameters from OMNI during the period of 2007-2016 are utilized to construct machine learning magnetopause models. SHapley Additive exPlanations (SHAP) is the basis of the interpretable procedure, which introduces interpretability and makes the machine learning magnetopause model to be a “white box”. The solar wind dynamic pressure and IMF BZ are widely considered the top two important parameters that drive the MSD. However, the interpretable procedure suggests that the IMF magnitude (i.e. strength of the IMF) leads BZ as the second most important interplanetary driver. This ranking result is unexpected, and it implies that the role of IMF magnitude is underestimated although magnetic pressure, which is a function of the IMF magnitude was considered in previous studies. The examination of disentangled effects of interplanetary parameters reveals that the combined influence of the IMF magnitude and BZ can cause an MSD sag near BZ = 5 nT. This is for the first time we conduct the interpretable concept into the machine learning model in the study of the magnetosphere.
- 15 May 2023
- Published by Copernicus GmbH
Open AccessInterpretable Machine Learning Procedure Unravels Hidden Interplanetary Drivers of the Low Latitude Dayside Magnetopause
Interplanetary parameters such as solar wind and interplanetary magnetic fields (IMF) drive the shape and size of the magnetopause jointly, which has complex relationships. In this study, we proposed an interpretable machine learning procedure to disentangle the influences of interplanetary parameters on the magnetopause standoff distance (MSD) and sort their importance in the MSD simulation. A magnetopause crossings database from the THEMIS satellites and interplanetary parameters from OMNI during the period of 2007-2016 are utilized to construct machine learning magnetopause models. SHapley Additive exPlanations (SHAP) is the basis of the interpretable procedure, which introduces interpretability and makes the machine learning magnetopause model to be a “white box”. The solar wind dynamic pressure and IMF BZ are widely considered the top two important parameters that drive the MSD. However, the interpretable procedure suggests that the IMF magnitude (i.e. strength of the IMF) leads BZ as the second most important interplanetary driver. This ranking result is unexpected, and it implies that the role of IMF magnitude is underestimated although magnetic pressure, which is a function of the IMF magnitude was considered in previous studies. The examination of disentangled effects of interplanetary parameters reveals that the combined influence of the IMF magnitude and BZ can cause an MSD sag near BZ = 5 nT. This is for the first time we conduct the interpretable concept into the machine learning model in the study of the magnetosphere.
- Open Access
- 6 March 2023
- Published by American Geophysical Union (AGU) in Space Weather
- Vol. 21 (3)
An Interpretable Machine Learning Procedure Which Unravels Hidden Interplanetary Drivers of the Low Latitude Dayside Magnetopause
In this study, we propose an interpretable machine learning procedure to unravel the importance of multiple interplanetary parameters to the Earth's magnetopause standoff distance (MSD). We construct the interpretable procedure based on SHapley Additive exPlanations. A magnetopause crossings database from the Time History of Events and Macroscale Interactions during Substorms satellites and the multiple interplanetary parameters from OMNI during the period of 2007–2016 are utilized. The solar wind dynamic pressure and the interplanetary magnetic field (IMF) BZ are widely suggested as the important two interplanetary parameters that drive the MSD. However, the examination of the interpretable procedure suggests that the magnitude of the IMF is the second significant parameter after the dynamic pressure. Although the magnetic pressure, which is the function of the IMF magnitude was considered in previous studies, the importance of the IMF magnitude was underestimated. The interpretable procedure also reveals that the IMF magnitude and the BZ have different effects on the MSD. Their joint effect is the formation of the MSD sag near BZ = 5 nT. This is for the first time the interpretable concept is being applied to construct a machine‐learning magnetopause model.
- 6 March 2023
- Published by American Geophysical Union (AGU) in Space Weather
- Vol. 21 (3)
Open AccessAn Interpretable Machine Learning Procedure Which Unravels Hidden Interplanetary Drivers of the Low Latitude Dayside Magnetopause
In this study, we propose an interpretable machine learning procedure to unravel the importance of multiple interplanetary parameters to the Earth's magnetopause standoff distance (MSD). We construct the interpretable procedure based on SHapley Additive exPlanations. A magnetopause crossings database from the Time History of Events and Macroscale Interactions during Substorms satellites and the multiple interplanetary parameters from OMNI during the period of 2007–2016 are utilized. The solar wind dynamic pressure and the interplanetary magnetic field (IMF) BZ are widely suggested as the important two interplanetary parameters that drive the MSD. However, the examination of the interpretable procedure suggests that the magnitude of the IMF is the second significant parameter after the dynamic pressure. Although the magnetic pressure, which is the function of the IMF magnitude was considered in previous studies, the importance of the IMF magnitude was underestimated. The interpretable procedure also reveals that the IMF magnitude and the BZ have different effects on the MSD. Their joint effect is the formation of the MSD sag near BZ = 5 nT. This is for the first time the interpretable concept is being applied to construct a machine‐learning magnetopause model.
- 12 August 2022
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 49 (15)
Explosive Eruption of the Tonga Underwater Volcano Modulates the Ionospheric E‐Region Current on 15 January 2022
The sudden eruption of the Tonga underwater volcano (20.53°S, 175.38°W) on 15 January 2022 generated explosions that triggered blast waves traveling away from the eruption. In this study, the analysis of the geomagnetic field observations on the ground shows that the eruption perturbed the E‐region current density by 22–55 mA/m within a radius of 8,000 km away from the eruption. The perturbation evolved into large scales of ∼5 hr and thousands of kilometers as it traveled away. The traveling speed of the leading front is ∼740 m/s that is near acoustic in the ionosphere. The magnetic fields and total electron content observations suggest that the dynamics changes further induced significant ionospheric disturbances that lasted ∼10 hr after the eruption. The examination of the Tonga volcanic eruption inspires us that a near‐surface perturbation can change the dynamics of the upper atmosphere.
- 12 August 2022
- Published by American Geophysical Union (AGU) in Geophysical Research Letters
- Vol. 49 (15)
Explosive Eruption of the Tonga Underwater Volcano Modulates the Ionospheric E‐Region Current on 15 January 2022
The sudden eruption of the Tonga underwater volcano (20.53°S, 175.38°W) on 15 January 2022 generated explosions that triggered blast waves traveling away from the eruption. In this study, the analysis of the geomagnetic field observations on the ground shows that the eruption perturbed the E‐region current density by 22–55 mA/m within a radius of 8,000 km away from the eruption. The perturbation evolved into large scales of ∼5 hr and thousands of kilometers as it traveled away. The traveling speed of the leading front is ∼740 m/s that is near acoustic in the ionosphere. The magnetic fields and total electron content observations suggest that the dynamics changes further induced significant ionospheric disturbances that lasted ∼10 hr after the eruption. The examination of the Tonga volcanic eruption inspires us that a near‐surface perturbation can change the dynamics of the upper atmosphere.