Monthly Maximum Magnitude Prediction in the North–South Seismic Belt of China Based on Deep Learning
<p>A sketch map of the geological structure and the magnitude distribution in the study area.</p> "> Figure 2
<p>Original magnitude diagram of the North–South Seismic Belt.</p> "> Figure 3
<p>VMD results with a time window size of 12: (<b>a</b>) decomposition results for the first sample; (<b>b</b>) decomposition results for the second sample; (<b>c</b>) decomposition results for the entire dataset.</p> "> Figure 4
<p>Flow chart of the experiment.</p> "> Figure 5
<p>Basic structure of an LSTM.</p> "> Figure 6
<p>Basic structure of a BiLSTM.</p> "> Figure 7
<p>ATT-LSTM processing steps.</p> "> Figure 8
<p>ATT-BiLSTM processing steps.</p> "> Figure 9
<p>Earthquake prediction classification chart at different time windows using LSTM. “M” stands for the number of missed detections, “A” stands for the number of correct detections, and “F” stands for the number of false alarms. (<b>a</b>–<b>d</b>) represent the earthquake prediction classification results at time windows of 6, 12, 18, and 24, respectively.</p> "> Figure 9 Cont.
<p>Earthquake prediction classification chart at different time windows using LSTM. “M” stands for the number of missed detections, “A” stands for the number of correct detections, and “F” stands for the number of false alarms. (<b>a</b>–<b>d</b>) represent the earthquake prediction classification results at time windows of 6, 12, 18, and 24, respectively.</p> "> Figure 10
<p>Earthquake prediction classification chart at different time windows using BiLSTM. “M” stands for the number of missed detections, “A” stands for the number of correct detections, and “F” stands for the number of false alarms. (<b>a</b>–<b>d</b>) represent the earthquake prediction classification results at time windows of 6, 12, 18, and 24, respectively.</p> "> Figure 11
<p>Earthquake prediction classification chart at different time windows using ATT-LSTM. “M” stands for the number of missed detections, “A” stands for the number of correct detections, and “F” stands for the number of false alarms. (<b>a</b>–<b>d</b>) represent the earthquake prediction classification results at time windows of 6, 12, 18, and 24, respectively.</p> "> Figure 11 Cont.
<p>Earthquake prediction classification chart at different time windows using ATT-LSTM. “M” stands for the number of missed detections, “A” stands for the number of correct detections, and “F” stands for the number of false alarms. (<b>a</b>–<b>d</b>) represent the earthquake prediction classification results at time windows of 6, 12, 18, and 24, respectively.</p> "> Figure 12
<p>Earthquake prediction classification chart at different time windows using ATT-BiLSTM. “M” stands for the number of missed detections, “A” stands for the number of correct detections, and “F” stands for the number of false alarms. (<b>a</b>–<b>d</b>) represent the earthquake prediction classification results at time windows of 6, 12, 18, and 24, respectively.</p> "> Figure 13
<p>Prediction result graph of six modes for the ATT-BiLSTM model with a time window of 12. Blue represents the actual values, and red represents the predicted values. (<b>a</b>–<b>e</b>) and (<b>f</b>), respectively, illustrate the predicted and actual values of the model for modes 1 to 6.</p> "> Figure 14
<p>Final comparison of the predicted results and the original magnitudes. The black color represents the actual magnitudes, the red color represents the final predicted results, and the gray area represents the region corresponding to the actual magnitudes ±0.5.</p> "> Figure 15
<p>Prediction result chart without VMD.</p> ">
Abstract
:1. Introduction
2. Data and Data Preprocessing
2.1. Study Area
2.2. Data
- T Value
- 2.
- Average Magnitude
- 3.
- The square root rate of the earthquake energy released ()
- 4.
- Slope of the log of the earthquake frequency versus the magnitude curve (b value)
- 5.
- The mean square deviation (η)
- 6.
- Magnitude deficit (∆M value)
- 7.
- Other parameters
2.3. Data Preprocessing
3. Methods
3.1. VMD
3.2. Deep Learning Model
3.2.1. LSTM
3.2.2. BiLSTM
3.2.3. Attention Mechanism
3.2.4. ATT-LSTM/ATT-BiLSTM
3.3. Evaluation Metrics
4. Experiment
4.1. VMD Processes the Data
4.2. Model Parameter Setting
- −
- Epochs: 30, 50, 100;
- −
- Batch size: 16, 32, 64;
- −
- Units: 32, 64, 128.
5. Results
5.1. Analysis of LSTM Model Prediction Results
5.2. Analysis of BiLSTM Model Prediction Results
5.3. Analysis of ATT-LSTM Model Prediction Results
5.4. Analysis of ATT-BiLSTM Model Prediction Results
5.5. Overall PA, FAR, and MR
5.6. MSE, RMSE, and MAE
6. Discussion
6.1. Using Time Window Sampling for VMD
6.2. Comparative Analysis of the Effectiveness of VMD in Magnitude Prediction
6.3. Limitations and Future Development
7. Conclusions
Author Contributions
Funding
Institutional Review Board Statement
Informed Consent Statement
Data Availability Statement
Acknowledgments
Conflicts of Interest
References
- Urlainis, A.; Shohet, I.M. A Comprehensive Approach to Earthquake-Resilient Infrastructure: Integrating Maintenance with Seismic Fragility Curves. Buildings 2023, 13, 2265. [Google Scholar] [CrossRef]
- Zhang, L.; Si, L.; Yang, H.; Hu, Y.; Qiu, J. Precursory pattern based feature extraction techniques for earthquake prediction. IEEE Access 2019, 7, 30991–31001. [Google Scholar] [CrossRef]
- Mignan, A.; Broccardo, M. Neural network applications in earthquake prediction (1994–2019): Meta-analytic and statistical insights on their limitations. Seismol. Res. Lett. 2019, 91, 2330–2342. [Google Scholar] [CrossRef]
- Uyeda, S.; Kamogawa, M. The Prediction of Two Large Earthquakes in Greece. Eos Trans. AGU 2008, 89, 363. [Google Scholar] [CrossRef]
- Rundle, J.B.; Donnellan, A.; Fox, G.; Crutchfield, J.P.; Granat, R. Nowcasting earthquakes: Imaging the earthquake cycle in California with machine learning. Earth Space Sci. 2021, 8, e2021EA001757. [Google Scholar] [CrossRef]
- Panakkat, A.; Adeli, H. Neural network models for earthquake magnitude prediction using multiple seismicity indicators. Int. J. Neural Syst. 2007, 17, 13–33. [Google Scholar] [CrossRef]
- Wang, J.H.; Jiang, H.K. Research progress in field of earthquake prediction by machine learning based on seismic data. J. Seismol. Res. 2023, 46, 173–187. [Google Scholar]
- Ridzwan, N.S.M.; Yusoff, S.H.M. Machine learning for earthquake prediction: A review (2017–2021). Earth Sci. Inform. 2023, 16, 1133–1149. [Google Scholar] [CrossRef]
- Sadhukhan, B.; Chakraborty, S.; Mukherjee, S. Predicting the magnitude of an impending earthquake using deep learning techniques. Earth Sci. Inform. 2023, 16, 803–823. [Google Scholar] [CrossRef]
- Li, R.; Lu, X.; Li, S.; Yang, H.; Qiu, J.; Zhang, L. DLEP: A Deep Learning Model for Earthquake Prediction. In Proceedings of the International Joint Conference on Neural Networks, Glasgow, UK, 19–24 July 2020. [Google Scholar]
- Asim, K.M.; Martínez-Álvarez, F.; Basit, A.; Iqbal, T. Earthquake magnitude prediction in Hindukush region using machine learning techniques. Nat. Hazards 2017, 85, 471–486. [Google Scholar] [CrossRef]
- Wang, Q.; Guo, Y.; Yu, L.; Li, P. Earthquake Prediction Based on Spatio-Temporal Data Mining: An LSTM Network Approach. IEEE Trans. Emerg. Top. Comput. 2020, 8, 148–158. [Google Scholar] [CrossRef]
- Rafiei, M.H.; Adeli, H. NEEWS: A novel earthquake early warning model using neural dynamic classification and neural dynamic optimization. Soil. Dyn. Earthq. Eng. 2017, 100, 417–427. [Google Scholar] [CrossRef]
- Banna, M.H.; Ghosh, T.; Nahian, M.J.; Taher, K.A.; Kaiser, M.S.; Mahmud, M.; Hossain, M.S.; Andersson, K. Attention-Based Bi-Directional Long-Short Term Memory Network for Earthquake Prediction. IEEE Access 2021, 9, 56589–56603. [Google Scholar] [CrossRef]
- Zhang, Z.; Wang, Y. A Spatiotemporal Model for Global Earthquake Prediction Based on Convolutional LSTM. IEEE Trans. Geosci. Remote Sens. 2023, 61, 5915712. [Google Scholar] [CrossRef]
- Kavianpour, P.; Kavianpour, M.; Jahani, E.; Ramezani, A. A CNN-BiLSTM model with attention mechanism for earthquake prediction. J. Supercomput. 2023, 79, 19194–19226. [Google Scholar] [CrossRef]
- Last, M.; Rabinowitz, N.; Leonard, G.; Ebrahimi, M. Predicting the Maximum Earthquake Magnitude from Seismic Data in Israel and Its Neighboring Countries. PLoS ONE 2016, 11, e0146101. [Google Scholar] [CrossRef]
- Essam, Y.; Kumar, P.; Ahmed, A.N.; Murti, M.A.; El-Shafie, A. Exploring the reliability of different artificial intelligence techniques in predicting earthquakes for Malaysia. Soil. Dyn. Earthq. Eng. 2021, 147, 106826. [Google Scholar] [CrossRef]
- Zhang, B.; Hu, Z.; Wu, P.; Huang, H.W.; Xiang, J.S. EPT: A data-driven transformer model for earthquake prediction. Eng. Appl. Artif. Intell. 2023, 123, 106176. [Google Scholar] [CrossRef]
- Öncel Çekim, H.; Karakavak, H.N.; Özel, G.; Tekin, S. Earthquake magnitude prediction in Turkey: A comparative study of deep learning methods, ARIMA and singular spectrum analysis. Environ. Earth Sci. 2023, 82, 387. [Google Scholar] [CrossRef]
- Cekim, H.O.; Tekin, S.; Özel, G. Prediction of the earthquake magnitude by time series methods along the East Anatolian Fault, Turkey. Earth Sci. Inform. 2021, 14, 1339–1348. [Google Scholar] [CrossRef]
- Debnath, P.; Chittora, P.; Chakrabarti, T.; Chakrabarti, P.; Leonowicz, Z.; Jasinski, M.; Gono, R.; Jasińska, E. Analysis of Earthquake Forecasting in India Using Supervised Machine Learning Classifiers. Sustainability 2021, 13, 971. [Google Scholar] [CrossRef]
- Khawaja, M.; Asim, A.; Idris, A.; Iqbal, T.; Martínez-Álvarez, F. Seismic indicators based earthquake predictor system using Genetic Programming and AdaBoost classification. Soil. Dyn. Earthq. Eng. 2018, 111, 1–7. [Google Scholar]
- Shan, W.; Zhang, M.; Wang, M.; Chen, H.; Zhang, R.; Yang, G.; Tang, Y.; Teng, Y.; Chen, J. EPM–DCNN: Earthquake Prediction Models Using Deep Convolutional Neural Networks. Bull. Seismol. Soc. Am. 2022, 112, 2933–2945. [Google Scholar] [CrossRef]
- Dragomiretskiy, K.; Zosso, D. Variational Mode Decomposition. IEEE Trans. Signal Process 2014, 62, 531–544. [Google Scholar] [CrossRef]
- Banjade, T.P.; Liu, J.; Li, H.; Ma, J.M. Enhancing earthquake signal based on variational mode decomposition and S-G filter. J. Seismol. 2021, 25, 41–54. [Google Scholar] [CrossRef]
- Sarlis, N.V.; Skordas, E.S.; Mintzelas, A.; Papadopoulou, K.A. Micro-scale, mid-scale, and macro-scale in global seismicity identified by empirical mode decomposition and their multifractal characteristics. Sci. Rep. 2018, 8, 9206. [Google Scholar] [CrossRef] [PubMed]
- Granda, F.; Benítez, D.S.; Yépez, F. On the analysis of strong earthquake seismic signals using variational-mode decomposition. In Proceedings of the IEEE Conference on Electrical, Electronics Engineering, Information and Communication Technologies, Valparaiso, Chile, 13–27 November 2019; pp. 1–6. [Google Scholar]
- Chi, C.; Li, C.; Han, Y.; Yu, Z.N.; Zhang, D. Pre-earthquake anomaly extraction from borehole strain data based on machine learning. Sci. Rep. 2023, 13, 20095. [Google Scholar] [CrossRef] [PubMed]
- Wang, Y.; Ma, J.; Li, C. Strong earthquake migration characteristics in the North-South seismic belt and their relationship with the South Asian seismic belt. Seismol. Geol. 2007, 01, 1–14. [Google Scholar]
- Tian, W.X.; Zhang, Y.X. Earthquake prediction in the North-South seismic belt based on image information methods. Earthquake 2023, 43, 159–177. [Google Scholar]
- Kang, L.X. Discussion on the basic characteristics and formation mechanism of the North-South seismic belt in China. Geod. Geodyn. 1991, 04, 76–85. [Google Scholar]
- Deng, Q.D.; Zhang, P.Z.; Ran, Y.K.; Yang, X.P.; Min, W.; Chu, Q.Z. Basic characteristics of active tectonics in China. Sci. China Ser. D Earth Sci. 2002, 12, 1020–1030+1057. [Google Scholar] [CrossRef]
- Xie, M.Y.; Meng, L.Y. Application of the maximum aftershock magnitude estimation method in the North-South seismic belt. Seismol. Res. 2022, 45, 424–433. [Google Scholar]
- Kagan, Y.Y.; Jackson, D.D.; Rong, Y. A testable five-year forecast of moderate and large earthquakes in southern California based on smoothed seismicity. Seismol. Res. Lett. 2007, 78, 94–98. [Google Scholar] [CrossRef]
- Kanamori, H. Quantification of Earthquakes. Nature 1978, 271, 411–414. [Google Scholar] [CrossRef]
- Narayanakumar, S.; Raja, K. A BP artificial neural network model for earthquake magnitude prediction in Himalayas, India. Circuits Syst. 2016, 7, 3456–3468. [Google Scholar] [CrossRef]
- Kail, R.; Burnaev, E.; Zaytsev, A. Recurrent convolutional neural networks help to predict location of earthquakes. IEEE Geosci. Remote Sens. Lett. 2022, 19, 8019005. [Google Scholar] [CrossRef]
- Hochreiter, S.; Schmidhuber, J. Long short-term memory. Neural Comput. 1997, 9, 1735–1780. [Google Scholar] [CrossRef] [PubMed]
- Graves, A.; Jaitly, N. Bidirectional LSTM networks for improved phoneme classification and recognition. In Proceedings of the ICASSP, Vancouver, BC, Canada, 26–31 May 2013; pp. 4155–4159. [Google Scholar]
- Tay, Y.; Luu, A.T.; Hui, S.C. Multi-pointer co-attention networks for recommendation. In Proceedings of the KDD, New York, NY, USA, 19–23 August 2018; ACM: New York, NY, USA, 2018; pp. 2309–2318. [Google Scholar]
- Niu, Z.; Zhong, G.; Yu, H. A review on the attention mechanism of deep learning. Neurocomputing 2021, 452, 48–62. [Google Scholar] [CrossRef]
- Chen, Y.T. Earthquake prediction: Review and prospects. Sci. China Earth Sci. 2009, 39, 1633–1658. [Google Scholar]
- Li, Y.; Xu, F.Y. Acoustic emission sources localization of laser cladding metallic panels using improved fruit fly optimization algorithm-based independent variational mode decomposition. Mech. Syst. Signal Pr. 2022, 166, 108514. [Google Scholar] [CrossRef]
- Shi, G.; Qin, C.; Tao, J.; Liu, C. A VMD-EWT-LSTM-based multi-step prediction approach for shield tunneling machine cutterhead torque. Knowl. Based Syst. 2021, 228, 107213. [Google Scholar] [CrossRef]
- Proaño, E.; Benítez, D.S.; Lara-Cueva, R.; Ruiz, M. On the use of variational mode decomposition for seismic event detection. In Proceedings of the 2018 IEEE International Autumn Meeting on Power, Electronics and Computing (ROPEC), Ixtapa, Mexico, 14–16 November 2018; pp. 1–6. [Google Scholar]
- MSE and RMSE: A Clear Guide to Understanding These Evaluation Metrics in Machine Learning. Available online: https://thecontentfarm.net/a-clear-guide-to-understanding-mse-rmse-evaluation-metrics/ (accessed on 2 October 2024). (In Chinese).
- Choosing between MAE, MSE and RMSE. Available online: https://hmatalonga.com/blog/choosing-between-mae-mse-and-rmse/ (accessed on 29 March 2023). (In Chinese).
- Zhang, J.; Sun, K.; Zhu, J.; Mao, N.; Ouzounov, D. Application of Model-Based Time Series Prediction of Infrared Long-Wave Radiation Data for Exploring the Precursory Patterns Associated with the 2021 Madoi Earthquake. Remote Sens. 2023, 15, 4748. [Google Scholar] [CrossRef]
- Cui, Y.; Ouzounov, D.; Hatzopoulos, N.; Sun, K.; Zou, Z.; Du, J. Satellite observation of CH4 and CO anomalies associated with the Wenchuan Ms 8.0 and Lushan Ms 7.0 earthquakes in China. Chem. Geol. 2017, 469, 185–191. [Google Scholar] [CrossRef]
- Xiong, B.; Li, X.; Wang, Y.Q.; Zhang, H.M.; Liu, Z.J.; Ding, F.; Zhao, B.Q. Prediction of ionospheric TEC over China based on long and short-term memory neural network. Chin. J. Geophys. 2022, 65, 2365–2377. [Google Scholar]
- Varotsos, P.; Sarlis, N.; Skordas, E. Magnetic field variations associated with the SES before the 6.6 Grevena-Kozani earthquake. Proc. Jpn. Acad. Ser. B-Phys. Biol. Sci. 2001, 77, 93–97. [Google Scholar] [CrossRef]
- Kang, C.L.; Han, Y.B.; Liu, D.F.; Cao, Z.Q. The OLR anomaly and mechanism before Tibet earthquake (M6.9). Prog. Geophys. 2008, 23, 1703–1708. [Google Scholar]
- Senturk, E.; Saqib, M.; Adil, M.A. A multi-network based hybrid LSTM model for ionospheric anomaly detection: A case study of the Mw 7.8 Nepal earthquake. Adv. Space Res. 2022, 70, 440–455. [Google Scholar] [CrossRef]
- Nazari, M.; Sakhaei, S.M. Successive Variational Mode Decomposition. Signal Process. 2020, 174, 107582. [Google Scholar] [CrossRef]
- Miao, Y.; Zhang, B.; Li, C.; Lin, J.; Zhang, D. Feature Mode Decomposition: New Decomposition Theory for Rotating Machinery Fault Diagnosis. IEEE Trans. Ind. Electron. 2023, 70, 1949–1960. [Google Scholar] [CrossRef]
- Daubechies, I. Orthonormal Bases of Compactly Supported Wavelets. Commun. Pure Appl. Math. 1988, 41, 909–996. [Google Scholar] [CrossRef]
Time Period | Seismological Parameters | |||||||||
---|---|---|---|---|---|---|---|---|---|---|
T (Days) | Mmean | dE1/2(108ergs) | a | b | Lat (°N) | Lon (°E) | Mmax | |||
1971.01 | 294 | 3.645 | 3.73 | 3.60 | 0.544 | 0.0036 | −1.12 | 29.03 | 95.02 | 4.8 |
1971.02 | 321 | 3.633 | 3.03 | 3.71 | 0.578 | 0.0057 | −0.94 | 25.27 | 99.5 | 5.8 |
1971.03 | 332 | 3.599 | 3.22 | 3.72 | 0.586 | 0.0035 | −0.55 | 35.5 | 98.1 | 6.3 |
1971.04 | 330 | 3.614 | 4.44 | 3.63 | 0.557 | 0.0023 | −0.21 | 22.8 | 101.1 | 6.7 |
1971.05 | 310 | 3.683 | 10.5 | 3.34 | 0.469 | 0.0041 | −0.42 | 41.0 | 108.0 | 4.0 |
1971.06 | 300 | 3.589 | 10.3 | 3.34 | 0.480 | 0.0093 | −0.26 | 25.12 | 105.48 | 4.9 |
1971.07 | 283 | 3.63 | 10.9 | 3.38 | 0.486 | 0.0059 | −0.25 | 35.83 | 105.9 | 3.8 |
1971.08 | 290 | 3.639 | 10.7 | 3.39 | 0.487 | 0.0054 | −0.25 | 28.8 | 103.6 | 5.8 |
1971.09 | 164 | 3.676 | 21.1 | 3.24 | 0.441 | 0.0072 | −0.63 | 22.95 | 100.55 | 5.4 |
1971.10 | 149 | 3.552 | 8.58 | 3.49 | 0.525 | 0.0085 | −0.84 | 38.0 | 102.08 | 4.5 |
1971.11 | 175 | 3.586 | 7.55 | 3.47 | 0.516 | 0.0077 | −0.92 | 28.82 | 103.58 | 4.9 |
1971.12 | 163 | 3.615 | 8.39 | 3.46 | 0.509 | 0.0069 | −0.99 | 39.98 | 96.57 | 4.5 |
Time Window | 6 | 12 | |||||
---|---|---|---|---|---|---|---|
PA | FAR | MR | PA | FAR | MR | ||
Ms ∈ [5,6) | LSTM | 54.55% | 0 | 45.45% | 63.64% | 0 | 36.36% |
BiLSTM | 59.09% | 0 | 40.91% | 65.91% | 0 | 34.09% | |
ATT-LSTM | 47.73% | 0 | 52.27% | 72.73% | 0 | 27.27% | |
ATT-BiLSTM | 63.64% | 0 | 36.36% | 77.27% | 0 | 22.73% | |
Ms ∈ [6,8] | LSTM | 0 | 0 | 100% | 0 | 0 | 100% |
BiLSTM | 0 | 0 | 100% | 6.25% | 0 | 93.75% | |
ATT-LSTM | 0 | 0 | 100% | 12.5% | 0 | 87.5% | |
ATT-BiLSTM | 0 | 0 | 100% | 12.5% | 0 | 87.5% |
Time Window | 18 | 24 | |||||
---|---|---|---|---|---|---|---|
PA | FAR | MR | PA | FAR | MR | ||
Ms ∈ [5,6) | LSTM | 72.09% | 0 | 27.91% | 60% | 0 | 40% |
BiLSTM | 67.44% | 0 | 32.56% | 47.5% | 2.5% | 50% | |
ATT-LSTM | 62.79% | 0 | 37.21% | 57.5% | 0 | 42.5% | |
ATT-BiLSTM | 65.12% | 0 | 34.08% | 62.5% | 0 | 37.5% | |
Ms ∈ [6,8] | LSTM | 6.25% | 0 | 93.75% | 0 | 0 | 100% |
BiLSTM | 0 | 0 | 100% | 0 | 0 | 100% | |
ATT-LSTM | 0 | 0 | 100% | 0 | 0 | 100% | |
ATT-BiLSTM | 6.25% | 0 | 93.75% | 0 | 0 | 100% |
Time Window | 6 | 12 | ||||
---|---|---|---|---|---|---|
MSE | RMSE | MAE | MSE | RMSE | MAE | |
LSTM | 0.699 | 0.836 | 0.638 | 0.683 | 0.827 | 0.622 |
BiLSTM | 0.666 | 0.816 | 0.623 | 0.717 | 0.847 | 0.650 |
Att-LSTM | 0.718 | 0.846 | 0.645 | 0.710 | 0.842 | 0.639 |
Att-BiLSTM | 0.708 | 0.841 | 0.666 | 0.678 | 0.824 | 0.635 |
18 | 24 | |||||
MSE | RMSE | MAE | MSE | RMSE | MAE | |
LSTM | 0.685 | 0.828 | 0.622 | 0.711 | 0.843 | 0.625 |
BiLSTM | 0.674 | 0.821 | 0.623 | 0.745 | 0.863 | 0.658 |
Att-LSTM | 0.679 | 0.824 | 0.609 | 0.681 | 0.826 | 0.621 |
Att-BiLSTM | 0.695 | 0.834 | 0.622 | 0.690 | 0.831 | 0.638 |
Time Window | 6 | 12 | ||||
---|---|---|---|---|---|---|
MSE | RMSE | MAE | MSE | RMSE | MAE | |
LSTM | 0.758 | 0.871 | 0.658 | 0.725 | 0.851 | 0.640 |
BiLSTM | 0.782 | 0.884 | 0.670 | 0.706 | 0.840 | 0.655 |
Att-LSTM | 0.707 | 0.841 | 0.632 | 0.705 | 0.840 | 0.625 |
Att-BiLSTM | 0.738 | 0.859 | 0.652 | 0.724 | 0.851 | 0.641 |
18 | 24 | |||||
MSE | RMSE | MAE | MSE | RMSE | MAE | |
LSTM | 0.724 | 0.850 | 0.644 | 0.755 | 0.869 | 0.657 |
BiLSTM | 0.760 | 0.871 | 0.673 | 0.725 | 0.851 | 0.653 |
Att-LSTM | 0.731 | 0.855 | 0.653 | 0.700 | 0.836 | 0.637 |
Att-BiLSTM | 0.734 | 0.857 | 0.649 | 0.694 | 0.833 | 0.636 |
Disclaimer/Publisher’s Note: The statements, opinions and data contained in all publications are solely those of the individual author(s) and contributor(s) and not of MDPI and/or the editor(s). MDPI and/or the editor(s) disclaim responsibility for any injury to people or property resulting from any ideas, methods, instructions or products referred to in the content. |
© 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
Share and Cite
Mao, N.; Sun, K.; Zhang, J. Monthly Maximum Magnitude Prediction in the North–South Seismic Belt of China Based on Deep Learning. Appl. Sci. 2024, 14, 9001. https://doi.org/10.3390/app14199001
Mao N, Sun K, Zhang J. Monthly Maximum Magnitude Prediction in the North–South Seismic Belt of China Based on Deep Learning. Applied Sciences. 2024; 14(19):9001. https://doi.org/10.3390/app14199001
Chicago/Turabian StyleMao, Ning, Ke Sun, and Jingye Zhang. 2024. "Monthly Maximum Magnitude Prediction in the North–South Seismic Belt of China Based on Deep Learning" Applied Sciences 14, no. 19: 9001. https://doi.org/10.3390/app14199001