Use of the shearlet energy entropy and of the support vector machine classifier to process weak microseismic and desert seismic signals
Low-amplitude signal detection is a key procedure in borehole microseismic and desert seismic exploration. Usually, signals are difficult to detect due to their low amplitude and noise contamination. To solve this problem, we propose a method combining shearlet energy entropy with a support vector m...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Académie des sciences
2020-06-01
|
| Series: | Comptes Rendus. Géoscience |
| Subjects: | |
| Online Access: | https://comptes-rendus.academie-sciences.fr/geoscience/articles/10.5802/crgeos.3/ |
| _version_ | 1797651334972833792 |
|---|---|
| author | Li, Yue Fan, Shiyu Zhang, Chao Yang, Baojun |
| author_facet | Li, Yue Fan, Shiyu Zhang, Chao Yang, Baojun |
| author_sort | Li, Yue |
| collection | DOAJ |
| description | Low-amplitude signal detection is a key procedure in borehole microseismic and desert seismic exploration. Usually, signals are difficult to detect due to their low amplitude and noise contamination. To solve this problem, we propose a method combining shearlet energy entropy with a support vector machine (SVM) to detect low-amplitude signals. In the proposed method, the signal feature is extracted using shearlet energy entropy. The signal is more sparsely represented in the shearlet domain because of the multi-scale and multi-direction characteristic of the shearlet transform, which favours signal feature extraction. Furthermore, in calculating shearlet energy entropy, we use the correlation of shearlet coefficients to enhance the difference between signal and noise in the shearlet domain. Shearlet energy entropy makes the SVM achieve a more accurate classification result compared with other traditional features such as amplitude and energy. The results of synthetic and field data show that our method is more effective than the STA/LTA and the convolutional neural network for low-amplitude microseismic signal and desert seismic signal detection. |
| first_indexed | 2024-03-11T16:14:31Z |
| format | Article |
| id | doaj.art-b4688f0db82041ecaa3ff736fde1d94d |
| institution | Directory Open Access Journal |
| issn | 1778-7025 |
| language | English |
| last_indexed | 2024-03-11T16:14:31Z |
| publishDate | 2020-06-01 |
| publisher | Académie des sciences |
| record_format | Article |
| series | Comptes Rendus. Géoscience |
| spelling | doaj.art-b4688f0db82041ecaa3ff736fde1d94d2023-10-24T14:24:26ZengAcadémie des sciencesComptes Rendus. Géoscience1778-70252020-06-01352110311310.5802/crgeos.310.5802/crgeos.3Use of the shearlet energy entropy and of the support vector machine classifier to process weak microseismic and desert seismic signalsLi, Yue0Fan, Shiyu1Zhang, Chao2Yang, Baojun3Department of Information, College of Communication Engineering, Jilin University, Changchun, Jilin, ChinaDepartment of Information, College of Communication Engineering, Jilin University, Changchun, Jilin, ChinaDepartment of Information, College of Communication Engineering, Jilin University, Changchun, Jilin, ChinaDepartment of Geophysics, Jilin University, Changchun, Jilin, ChinaLow-amplitude signal detection is a key procedure in borehole microseismic and desert seismic exploration. Usually, signals are difficult to detect due to their low amplitude and noise contamination. To solve this problem, we propose a method combining shearlet energy entropy with a support vector machine (SVM) to detect low-amplitude signals. In the proposed method, the signal feature is extracted using shearlet energy entropy. The signal is more sparsely represented in the shearlet domain because of the multi-scale and multi-direction characteristic of the shearlet transform, which favours signal feature extraction. Furthermore, in calculating shearlet energy entropy, we use the correlation of shearlet coefficients to enhance the difference between signal and noise in the shearlet domain. Shearlet energy entropy makes the SVM achieve a more accurate classification result compared with other traditional features such as amplitude and energy. The results of synthetic and field data show that our method is more effective than the STA/LTA and the convolutional neural network for low-amplitude microseismic signal and desert seismic signal detection.https://comptes-rendus.academie-sciences.fr/geoscience/articles/10.5802/crgeos.3/Shearlet energy entropySVMMicroseismic signalDesert seismic signalSignal detection |
| spellingShingle | Li, Yue Fan, Shiyu Zhang, Chao Yang, Baojun Use of the shearlet energy entropy and of the support vector machine classifier to process weak microseismic and desert seismic signals Comptes Rendus. Géoscience Shearlet energy entropy SVM Microseismic signal Desert seismic signal Signal detection |
| title | Use of the shearlet energy entropy and of the support vector machine classifier to process weak microseismic and desert seismic signals |
| title_full | Use of the shearlet energy entropy and of the support vector machine classifier to process weak microseismic and desert seismic signals |
| title_fullStr | Use of the shearlet energy entropy and of the support vector machine classifier to process weak microseismic and desert seismic signals |
| title_full_unstemmed | Use of the shearlet energy entropy and of the support vector machine classifier to process weak microseismic and desert seismic signals |
| title_short | Use of the shearlet energy entropy and of the support vector machine classifier to process weak microseismic and desert seismic signals |
| title_sort | use of the shearlet energy entropy and of the support vector machine classifier to process weak microseismic and desert seismic signals |
| topic | Shearlet energy entropy SVM Microseismic signal Desert seismic signal Signal detection |
| url | https://comptes-rendus.academie-sciences.fr/geoscience/articles/10.5802/crgeos.3/ |
| work_keys_str_mv | AT liyue useoftheshearletenergyentropyandofthesupportvectormachineclassifiertoprocessweakmicroseismicanddesertseismicsignals AT fanshiyu useoftheshearletenergyentropyandofthesupportvectormachineclassifiertoprocessweakmicroseismicanddesertseismicsignals AT zhangchao useoftheshearletenergyentropyandofthesupportvectormachineclassifiertoprocessweakmicroseismicanddesertseismicsignals AT yangbaojun useoftheshearletenergyentropyandofthesupportvectormachineclassifiertoprocessweakmicroseismicanddesertseismicsignals |