Application of high generalization model in the b-value and medium and strong earthquake backtracking of the central and southern section of the Tanlu fault zone
The indication of b-value change and earthquake preparation has always been an important reference index for earthquake situation research and judgment. Based on the advantage that deep learning technology can mine the implicit characteristics of data, taking into account the natural phenomenon of f...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Office of Progress in Earthquake Sciences
2024-12-01
|
| Series: | 地震科学进展 |
| Subjects: | |
| Online Access: | https://www.gjdzdt.cn/en/article/doi/10.19987/j.dzkxjz.2024-077 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1846141468878569472 |
|---|---|
| author | Jianbin Xiang Teng Yu Dandan Zhang Yimin Zhu Yujia Xi |
| author_facet | Jianbin Xiang Teng Yu Dandan Zhang Yimin Zhu Yujia Xi |
| author_sort | Jianbin Xiang |
| collection | DOAJ |
| description | The indication of b-value change and earthquake preparation has always been an important reference index for earthquake situation research and judgment. Based on the advantage that deep learning technology can mine the implicit characteristics of data, taking into account the natural phenomenon of frequent earthquakes in Sichuan and Yunnan in recent years and the high attention paid to the seismic activity of the Tanlu fault, this study uses the self-made data set of seismic events in Sichuan and Yunnan region from the earthquake catalogue of the China Earthquake Networks Center, and medium and strong earthquakes above \begin{document}$ {M}_{\mathrm{L}} $\end{document}4.5 are labeled as 1, weak earthquakes below \begin{document}$ {M}_{\mathrm{L}} $\end{document}3.0 are labeled as 0. The grid b-value in Sichuan-Yunnan region is calculated using the time sliding window method, and the b-value changes of each earthquake event in the five years before the earthquake are mapped to the labels. By using convolutional neural network models for training and classification, the optimized model is applied to the retrospective testing of medium and strong earthquakes in the central and southern section of the Tanlu fault zone. The verification accuracy can reach about 90%. Although the Sichuan-Yunnan region and the central and southern section of the Tanlu fault zone and their neighboring areas have different geographical and structural backgrounds, data-driven methods, reasonable generalization ideas, training datasets production, and deep learning model construction still have reference significance for mining strong earthquake laws. |
| format | Article |
| id | doaj-art-a182c97a40b149a0af03a191f65890c0 |
| institution | Kabale University |
| issn | 2096-7780 |
| language | zho |
| publishDate | 2024-12-01 |
| publisher | Editorial Office of Progress in Earthquake Sciences |
| record_format | Article |
| series | 地震科学进展 |
| spelling | doaj-art-a182c97a40b149a0af03a191f65890c02024-12-04T08:48:28ZzhoEditorial Office of Progress in Earthquake Sciences地震科学进展2096-77802024-12-01541286887710.19987/j.dzkxjz.2024-0772024-077Application of high generalization model in the b-value and medium and strong earthquake backtracking of the central and southern section of the Tanlu fault zoneJianbin Xiang0Teng Yu1Dandan Zhang2Yimin Zhu3Yujia Xi4School of Architecture and Engineering, Suqian University, Jiangsu Suqian 223800, ChinaSchool of Architecture and Engineering, Suqian University, Jiangsu Suqian 223800, ChinaSchool of Architecture and Engineering, Suqian University, Jiangsu Suqian 223800, ChinaSchool of Land Science and Technology, China University of Geosciences (Beijing), Beijing 100083, ChinaSchool of Architecture and Engineering, Suqian University, Jiangsu Suqian 223800, ChinaThe indication of b-value change and earthquake preparation has always been an important reference index for earthquake situation research and judgment. Based on the advantage that deep learning technology can mine the implicit characteristics of data, taking into account the natural phenomenon of frequent earthquakes in Sichuan and Yunnan in recent years and the high attention paid to the seismic activity of the Tanlu fault, this study uses the self-made data set of seismic events in Sichuan and Yunnan region from the earthquake catalogue of the China Earthquake Networks Center, and medium and strong earthquakes above \begin{document}$ {M}_{\mathrm{L}} $\end{document}4.5 are labeled as 1, weak earthquakes below \begin{document}$ {M}_{\mathrm{L}} $\end{document}3.0 are labeled as 0. The grid b-value in Sichuan-Yunnan region is calculated using the time sliding window method, and the b-value changes of each earthquake event in the five years before the earthquake are mapped to the labels. By using convolutional neural network models for training and classification, the optimized model is applied to the retrospective testing of medium and strong earthquakes in the central and southern section of the Tanlu fault zone. The verification accuracy can reach about 90%. Although the Sichuan-Yunnan region and the central and southern section of the Tanlu fault zone and their neighboring areas have different geographical and structural backgrounds, data-driven methods, reasonable generalization ideas, training datasets production, and deep learning model construction still have reference significance for mining strong earthquake laws.https://www.gjdzdt.cn/en/article/doi/10.19987/j.dzkxjz.2024-077b-valueconvolutional neural networksmedium and strong earthquaketanlu fault |
| spellingShingle | Jianbin Xiang Teng Yu Dandan Zhang Yimin Zhu Yujia Xi Application of high generalization model in the b-value and medium and strong earthquake backtracking of the central and southern section of the Tanlu fault zone 地震科学进展 b-value convolutional neural networks medium and strong earthquake tanlu fault |
| title | Application of high generalization model in the b-value and medium and strong earthquake backtracking of the central and southern section of the Tanlu fault zone |
| title_full | Application of high generalization model in the b-value and medium and strong earthquake backtracking of the central and southern section of the Tanlu fault zone |
| title_fullStr | Application of high generalization model in the b-value and medium and strong earthquake backtracking of the central and southern section of the Tanlu fault zone |
| title_full_unstemmed | Application of high generalization model in the b-value and medium and strong earthquake backtracking of the central and southern section of the Tanlu fault zone |
| title_short | Application of high generalization model in the b-value and medium and strong earthquake backtracking of the central and southern section of the Tanlu fault zone |
| title_sort | application of high generalization model in the b value and medium and strong earthquake backtracking of the central and southern section of the tanlu fault zone |
| topic | b-value convolutional neural networks medium and strong earthquake tanlu fault |
| url | https://www.gjdzdt.cn/en/article/doi/10.19987/j.dzkxjz.2024-077 |
| work_keys_str_mv | AT jianbinxiang applicationofhighgeneralizationmodelinthebvalueandmediumandstrongearthquakebacktrackingofthecentralandsouthernsectionofthetanlufaultzone AT tengyu applicationofhighgeneralizationmodelinthebvalueandmediumandstrongearthquakebacktrackingofthecentralandsouthernsectionofthetanlufaultzone AT dandanzhang applicationofhighgeneralizationmodelinthebvalueandmediumandstrongearthquakebacktrackingofthecentralandsouthernsectionofthetanlufaultzone AT yiminzhu applicationofhighgeneralizationmodelinthebvalueandmediumandstrongearthquakebacktrackingofthecentralandsouthernsectionofthetanlufaultzone AT yujiaxi applicationofhighgeneralizationmodelinthebvalueandmediumandstrongearthquakebacktrackingofthecentralandsouthernsectionofthetanlufaultzone |