Time Series and Non-Time Series Models of Earthquake Prediction Based on AETA Data: 16-Week Real Case Study
Source abstract
Abstract
The Key Laboratory of Integrated Microsystems (IMS) of Peking University Shenzhen Graduate School has deployed a self-developed acoustic and electromagnetics to artificial intelligence (AETA) system on a large scale and at a high density in China to comprehensively monitor and collect the precursor anomaly signals that occur before earthquakes for seismic prediction. This paper constructs several classic time series and non-time series prediction models for comparison and analysis in order to find the most suitable earthquake-prediction model among these models. The long short-term memory (LSTM) neural network, which gains the best results in earthquake prediction based on AETA data extracted from the precursor anomaly signals, is selected for real-earthquake prediction for 16 consecutive weeks.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Earthquake Detection and Analysis · Seismology and Earthquake Studies · earthquake and tectonic studies
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
The Key Laboratory of Integrated Microsystems, Peking University Shenzhen Graduate School, Shenzhen 518055, China
Faculty of Engineering, Shenzhen MSU-BIT University, Shenzhen 518172, China
Funding
Shenzhen Science and Technology Program · Youth Innovation Talent Project of Guangdong Province Universities
References (47)
Show source-provided references
1. Research and Implementation of Multi-component Seismic Monitoring System AETA
2. Physical properties of the variations of the electric field of the earth preceding earthquakes, I10.1016/0040-1951(84)90059-3 ↗
3. Low-frequency magnetic-field measurements near the epicenter of the ms-7.1 Loma-Prieta earthquake10.1029/GL017i009p01465 ↗
4. Seismic electromagnetic signals (SEMS) explained by a simulation experiment using electromagnetic waves10.1016/S0031-9201(98)00135-6 ↗
5. Magnetic field variations associated with SES10.2183/pjab.77.87 ↗
6. Electric Fields that “Arrive’’ before the Time Derivative of the Magnetic Field prior to Major Earthquakes10.1103/PhysRevLett.91.148501 ↗
7. Controlled analogue experiments on propagation of seismic electromagnetic signals10.1360/982004-312 ↗
8. Short-term earthquake prediction: Current status of seismo-electromagnetics10.1016/j.tecto.2008.07.019 ↗
9. Identifying long-range correlated signals upon significant periodic data loss10.1016/j.tecto.2011.02.011 ↗
10. Natural time analysis of critical phenomena: The case of pre-fracture electromagnetic emissions10.1063/1.4807908 ↗
11. Statistical analysis of ULF seismomagnetic phenomena at Kakioka, Japan, during 2001–201010.1002/2014JA019789 ↗
12. Criticality features in ULF magnetic fields prior to the 2011 Tohoku earthquake10.2183/pjab.91.25 ↗
13. Spatiotemporal characteristics of the geomagnetic diurnal variation anomalies prior to the 2011 Tohoku earthquake (Mw 9.0) and the possible coupling of multiple pre-earthquake phenomena10.1016/j.jseaes.2016.07.011 ↗
14. Sarlis, N.V. (2018). Statistical Significance of Earth’s Electric and Magnetic Field Variations Preceding Earthquakes in Greece and Japan Revisited. Entropy, 20.10.3390/e20080561 ↗
15. Seismic electric signals in seismic prone areas10.29382/eqs-2018-0005-5 ↗
16. Varotsos, P.A., Sarlis, N.V., and Skordas, E.S. (2022). Order Parameter and Entropy of Seismicity in Natural Time before Major Earthquakes: Recent Results. Geosciences, 12.10.3390/geosciences12060225 ↗
17. Detection Method of Earthquake Disaster Image Anomaly Based on SIFT Feature and SVM Classification
18. Rapid prediction of earthquake ground shaking intensity using raw waveform data and a convolutional neural network10.1093/gji/ggaa233 ↗
19. Xiong, P., Long, C., Zhou, H.Y., Battiston, R., Zhang, X.M., and Shen, X.H. (2020). Identification of Electromagnetic Pre-Earthquake Perturbations from the DEMETER Data by Machine Learning. Remote Sens., 12.10.5194/egusphere-egu2020-2506 ↗
20. Efficient Seismic Stability Analysis of Embankment Slopes Subjected to Water Level Changes Using Gradient Boosting Algorithms10.3389/feart.2021.807317 ↗
21. Machine Learning for Fast and Reliable Source-Location Estimation in Earthquake Early Warning10.1109/LGRS.2022.3142714 ↗
22. Detecting anomalies in time series data via a deep learning algorithm combining wavelets, neural networks and Hilbert transform10.1016/j.eswa.2017.04.028 ↗
23. Hybrid Event Detection and Phase-Picking Algorithm Using Convolutional and Recurrent Neural Networks10.1785/0220180319 ↗
24. Detection and Classification of Continuous Volcano-Seismic Signals with Recurrent Neural Networks. IEEE Trans10.1109/TGRS.2018.2870202 ↗
25. Jena, R., Pradhan, B., and Alamri, A.M. (2020). Susceptibility to Seismic Amplification and Earthquake Probability Estimation Using Recurrent Neural Network (RNN) Model in Odisha, India. Appl. Sci., 10.10.3390/app10155355 ↗
26. Real-time regional seismic damage assessment framework based on long short-term memory neural network10.1111/mice.12628 ↗
27. Detection of possible hydrological precursor anomalies using long short-term memory: A case study of the 1996 Lijiang earthquake10.1016/j.jhydrol.2021.126369 ↗
28. Recurrent neural networks for complicated seismic dynamic response prediction of a slope system10.1016/j.enggeo.2021.106198 ↗
29. LSTM-Autoencoder Network for the Detection of Seismic Electric Signals. IEEE Trans10.1109/TGRS.2022.3183389 ↗
30. Periodic electromagnetic signals as potential precursor for seismic activity10.1007/s11771-021-4739-1 ↗
31. Bao, Z., Zhao, J., Huang, P., Yong, S., and Wang, X. (2021). Deep Learning-Based Electromagnetic Signal for Earthquake Magnitude Prediction. Sensors, 21.10.3390/s21134434 ↗
32. Development of Inductive Magnetic Sensor for Multi-component Seismic Monitoring System AETA
33. A sliding window-based algorithm for faster transformation of time series into complex networks10.1063/1.5112782 ↗
34. Bao, Z., Yong, S., Wang, X., Yang, C., Xie, J., and He, C. (2021). Seismic Reflection Analysis of AETA Electromagnetic Signals. Appl. Sci., 11.10.3390/app11135869 ↗
35. A-SMOTE: A New Preprocessing Approach for Highly Imbalanced Datasets by Improving SMOTE10.2991/ijcis.d.191114.002 ↗
36. Liang, W., Luo, S., Zhao, G., and Wu, H. (2020). Predicting Hard Rock Pillar Stability Using GBDT, XGBoost, and LightGBM Algorithms. Mathematics, 8.10.3390/math8050765 ↗
37. The Comparison of LightGBM and XGBoost Coupling Factor Analysis and Prediagnosis of Acute Liver Failure10.1109/ACCESS.2020.3042848 ↗
38. A neural network primer10.1142/S0218339094000179 ↗
39. Core vector machines: Fast SVM training on very large data sets
40. A comparison of random forest variable selection methods for classification prediction modeling10.1016/j.eswa.2019.05.028 ↗
41. Displacement prediction of Jiuxianping landslide using gated recurrent unit (GRU) networks10.1007/s11440-022-01495-8 ↗
42. Liu, Y., Yong, S., He, C., Wang, X., Bao, Z., Xie, J., and Zhang, X. (2022). An Earthquake Forecast Model Based on Multi-Station PCA Algorithm. Appl. Sci., 12.10.3390/app12073311 ↗
43. Time Series Feature Extraction on basis of Scalable Hypothesis tests (tsfresh-A Python package)10.1016/j.neucom.2018.03.067 ↗
44. Cross-Validation for Imbalanced Datasets: Avoiding Overoptimistic and Overfitting Approaches10.1109/MCI.2018.2866730 ↗
45. Hosmer, D.W., and Lemeshow, S. (2000). Applied Logistic Regression, John Wiley & Sons, Ltd.10.1002/0471722146 ↗
46. An introduction to ROC analysis10.1016/j.patrec.2005.10.010 ↗
47. Visualization of the significance of Receiver Operating Characteristics based on confidence ellipses10.1016/j.cpc.2013.12.009 ↗