Yan Feng
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Yan Feng has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Jiaxuan Zhang
Institute of Space Weather, School of Atmospheric Physics, Nanjing University of Information Science & Technology, Nanjing 210044, China
2 shared publications - Jinyuan Zhang
Institute of Space Weather, School of Atmospheric Physics, Nanjing University of Information Science & Technology, Nanjing 210044, China
2 shared publications - PengFei Liu
Macau Institute of Space Technology and Application, Macau University of Science and Technology, Macau 999078, China
1 shared publication - Qing Yan
Macau Institute of Space Technology and Application, Macau University of Science and Technology, Macau 999078, China
1 shared publication - Xinwu Li
Institute of Space Weather, School of Atmospheric Physics, Nanjing University of Information Science & Technology, Nanjing 210044, China
1 shared publication - Yi Jiang
Macau Institute of Space Technology and Application, Macau University of Science and Technology, Macau 999078, China
1 shared publication
Latest Publications
- Open Access
- 21 March 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (7) , 1114
Utilising Macau Science Satellite-1 Data and Comprehensive Datasets to Develop a Lithospheric Magnetic Field Model of the Chinese Mainland
We incorporated a comprehensive dataset encompassing recent measurements from satellites such as the Macau Science Satgellite-1 (MSS-1), Swarm, and CHAMP, as well as aero and ocean magnetic measurements, alongside ground-based data from 1936 to 2000. This amalgamation is the basis for constructing a lithospheric magnetic field model of the Chinese mainland, employing the three-dimensional Surface Spline (3DSS) model. Additionally, we used the World Digital Magnetic Anomaly Map (WDMAM)-2.1 and CHAOS-7.13 models to address data gaps horizontally and vertically. To evaluate the efficacy of the new model, we compared it not only with established models such as SHA1050, NGDC720, and LCS-1 but also with the new model excluding the MSS-1 data. The results show a high agreement between the 3DSS model and other global models at a spatial resolution of 0.05°. Furthermore, we inspected the rapid variations in the magnetic field with increasing altitude, demonstrating a smooth transition across the altitudes covered by the three satellites. Error analyses reflected the importance of MSS-1 data, which contributed notably to modelling by capturing finer-scale magnetic structures. The increased data availability correlated positively with the model’s accuracy, as evidenced by the Root Mean Square Error (RMSE), registering an optimal value of 0.02 nT. The new model reveals additional geological details in southern Tibet, northeastern Inner Mongolia, and the adjacent areas of Liaoning and Jilin provinces, which are not discernible in other global models. The relationship between these anomalies and heat flow in northeastern China appears less evident, suggesting a complex interplay of orogenic processes and surface mineralogy in shaping these magnetic signatures.
- 21 March 2025
- Published by MDPI AG in Remote Sensing
- Vol. 17 (7) , 1114
Open AccessUtilising Macau Science Satellite-1 Data and Comprehensive Datasets to Develop a Lithospheric Magnetic Field Model of the Chinese Mainland
We incorporated a comprehensive dataset encompassing recent measurements from satellites such as the Macau Science Satgellite-1 (MSS-1), Swarm, and CHAMP, as well as aero and ocean magnetic measurements, alongside ground-based data from 1936 to 2000. This amalgamation is the basis for constructing a lithospheric magnetic field model of the Chinese mainland, employing the three-dimensional Surface Spline (3DSS) model. Additionally, we used the World Digital Magnetic Anomaly Map (WDMAM)-2.1 and CHAOS-7.13 models to address data gaps horizontally and vertically. To evaluate the efficacy of the new model, we compared it not only with established models such as SHA1050, NGDC720, and LCS-1 but also with the new model excluding the MSS-1 data. The results show a high agreement between the 3DSS model and other global models at a spatial resolution of 0.05°. Furthermore, we inspected the rapid variations in the magnetic field with increasing altitude, demonstrating a smooth transition across the altitudes covered by the three satellites. Error analyses reflected the importance of MSS-1 data, which contributed notably to modelling by capturing finer-scale magnetic structures. The increased data availability correlated positively with the model’s accuracy, as evidenced by the Root Mean Square Error (RMSE), registering an optimal value of 0.02 nT. The new model reveals additional geological details in southern Tibet, northeastern Inner Mongolia, and the adjacent areas of Liaoning and Jilin provinces, which are not discernible in other global models. The relationship between these anomalies and heat flow in northeastern China appears less evident, suggesting a complex interplay of orogenic processes and surface mineralogy in shaping these magnetic signatures.
- Open Access
- 26 September 2023
- Published by MDPI AG in Preprints.org
The Short Time Prediction of the Dst Index Based on the LSTM and the EMD-LSTM Models
The Dst index is the geomagnetic storm index used to measure the energy level of geomagnetic storms, and the prediction of this index is of great significance for the geomagnetic storm study and the solar activity. In contrast to traditional numerical modelling techniques, machine learning, which has emerged in decades ago based on rapidly developing computer hardware and software and artificial intelligence methods, has been unprecedentedly developed in geophysics, especially solar-terrestrial space physics. This study chooses two machine learning models, the LSTM (Long-Short Time Memory, LSTM) and EMD-LSTM model (Empirical Mode Decomposition, EMD), to model and predict the Dst index. By building the Dst index data series from 2018-2023, two models were built to fit and predict the data. Firstly, we evaluated the influences of the learning rate and the amount of training data on the prediction accuracy of the LSTM model, and finally, 10-3 was thought as the optimal learning rate; secondly, the two models were used to predict the Dst index in the solar active and quiet periods, respectively, and the RMSE (Root Mean Square Error) of the LSTM model in the active period is 7.34 nT, the CC (correlation coefficient) is 0.96, those of the quiet period are 2.64nT and 0.97; the RMSE and r of EMD-LSTM model are 8.87nT and 0.93 in active time and 3.29nT and 0.95 in the quiet time. Finally, the prediction accuracy of the LSTM model in short time period is slightly better than the EMD-LSTM model. However, there will be a problem of prediction lag, which the EMD-LSTM model can then solve, and can better predict the geomagnetic storm.
- 26 September 2023
- Published by MDPI AG in Preprints.org
Open AccessThe Short Time Prediction of the Dst Index Based on the LSTM and the EMD-LSTM Models
The Dst index is the geomagnetic storm index used to measure the energy level of geomagnetic storms, and the prediction of this index is of great significance for the geomagnetic storm study and the solar activity. In contrast to traditional numerical modelling techniques, machine learning, which has emerged in decades ago based on rapidly developing computer hardware and software and artificial intelligence methods, has been unprecedentedly developed in geophysics, especially solar-terrestrial space physics. This study chooses two machine learning models, the LSTM (Long-Short Time Memory, LSTM) and EMD-LSTM model (Empirical Mode Decomposition, EMD), to model and predict the Dst index. By building the Dst index data series from 2018-2023, two models were built to fit and predict the data. Firstly, we evaluated the influences of the learning rate and the amount of training data on the prediction accuracy of the LSTM model, and finally, 10-3 was thought as the optimal learning rate; secondly, the two models were used to predict the Dst index in the solar active and quiet periods, respectively, and the RMSE (Root Mean Square Error) of the LSTM model in the active period is 7.34 nT, the CC (correlation coefficient) is 0.96, those of the quiet period are 2.64nT and 0.97; the RMSE and r of EMD-LSTM model are 8.87nT and 0.93 in active time and 3.29nT and 0.95 in the quiet time. Finally, the prediction accuracy of the LSTM model in short time period is slightly better than the EMD-LSTM model. However, there will be a problem of prediction lag, which the EMD-LSTM model can then solve, and can better predict the geomagnetic storm.