A novel deep-learning image condition for locating earthquake

Kuang, Wenhuan1,2,3; Zhang, Jie4; Zhang, Wei2,3

2023-09-18

10.1093/gji/ggad350

GEOPHYSICAL JOURNAL INTERNATIONAL   影响因子和分区

0956-540X

1365-246X

Migration-based earthquake location methods may encounter the polarity reversal issue due to the non-explosive components of seismic sources, leading to an unfocused migration image. Such a problem usually makes it difficult to accurately retrieve the optimal location from the migrated source image. In this study, by taking advantage of the general pattern recognition ability of the convolutional neural network, we propose a novel deep-learning image condition (DLIC) to address this issue. The proposed DLIC measures the goodness of waveform alignments for both P and S waves, and it follows the geophysical principle of seismic imaging that the best-aligned waveforms represent fully a best-imaged source location. A synthetic test shows that the DLIC can effectively overcome the polarity reversal issues. Real data applications to southern California show that the DLIC can enhance the focusing of the migrated source image over the classic source scanning algorithm. Further tests show that the DLIC applies to continuous seismic data, to regions with few previously recorded earthquakes, and has the potential to locate small earthquakes. The proposed DLIC shall benefit the migration-based source location methods.

Neural networks, fuzzy logic Earthquake source observations

SCI ; EI

英语

通讯

We thank the financial support from the National Key Ramp;amp;D Program of China (grant no. 2021YFC3000703-05), the National Natural Science Foundation of China (grant nos 42104047 and U1901602), the Guangdong Provincial Key Laboratory of Geophysical High[2021YFC3000703-05] ; National Key Ramp;amp;D Program of China["42104047","U1901602"] ; National Natural Science Foundation of China[2022B1212010002] ; Guangdong Provincial Key Laboratory of Geophysical High-resolution Imaging Technology[2019QN01G801] ; Guangdong Provincial Pearl River Talents Program[KQTD20170810111725321]

Geochemistry & Geophysics

Geochemistry & Geophysics

WOS:001072675800001

OXFORD UNIV PRESS

20234314949836

Convolutional neural networks ; Deep neural networks ; Earthquakes ; Fuzzy neural networks ; Image enhancement ; Location ; Pattern recognition ; Shear waves

Ergonomics and Human Factors Engineering:461.4 ; Seismology:484 ; Computer Theory, Includes Formal Logic, Automata Theory, Switching Theory, Programming Theory:721.1 ; Artificial Intelligence:723.4 ; Mechanics:931.1

GEOSCIENCES

2-s2.0-85174587654

Web of Science

1.Ocean Univ China, Coll Marine Geosci, Key Lab Submarine Geosci & Prospecting Tech, MOE, Qingdao 266100, Peoples R China
2.Southern Univ Sci & Technol, Guangdong Prov Key Lab Geophys High Resolut Imagin, Shenzhen 518055, Peoples R China
3.Southern Univ Sci & Technol, Dept Earth & Space Sci, Shenzhen 518055, Peoples R China
4.Univ Sci & Technol China, Dept Geophys, Hefei 230026, Peoples R China

Kuang, Wenhuan,Zhang, Jie,Zhang, Wei. A novel deep-learning image condition for locating earthquake[J]. GEOPHYSICAL JOURNAL INTERNATIONAL,2023,235(3):2168-2178.

Kuang, Wenhuan,Zhang, Jie,&Zhang, Wei.(2023).A novel deep-learning image condition for locating earthquake.GEOPHYSICAL JOURNAL INTERNATIONAL,235(3),2168-2178.

Kuang, Wenhuan,et al."A novel deep-learning image condition for locating earthquake".GEOPHYSICAL JOURNAL INTERNATIONAL 235.3(2023):2168-2178.