Deep-Learning-Based Seismic-Signal P-Wave First-Arrival Picking Detection Using Spectrogram Images
The accurate detection of P-wave FAP (First-Arrival Picking) in seismic signals is crucial across various industrial domains, including coal and oil exploration, tunnel construction, hydraulic fracturing, and earthquake early warning systems. At present, P-wave FAP detection relies on manual identif...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/1/229 |
| _version_ | 1797358889492021248 |
|---|---|
| author | Sugi Choi Bohee Lee Junkyeong Kim Haiyoung Jung |
| author_facet | Sugi Choi Bohee Lee Junkyeong Kim Haiyoung Jung |
| author_sort | Sugi Choi |
| collection | DOAJ |
| description | The accurate detection of P-wave FAP (First-Arrival Picking) in seismic signals is crucial across various industrial domains, including coal and oil exploration, tunnel construction, hydraulic fracturing, and earthquake early warning systems. At present, P-wave FAP detection relies on manual identification by experts and automated methods using Short-Term Average to Long-Term Average algorithms. However, these approaches encounter significant performance challenges, especially in the presence of real-time background noise. To overcome this limitation, this study proposes a novel P-wave FAP detection method that employs the U-Net model and incorporates spectrogram transformation techniques for seismic signals. Seismic signals, similar to those encountered in South Korea, were generated using the stochastic model simulation program. Synthesized WGN (White Gaussian Noise) was added to replicate background noise. The resulting signals were transformed into 2D spectrogram images and used as input data for the U-Net model, ensuring precise P-wave FAP detection. In the experimental result, it demonstrated strong performance metrics, achieving an MSE of 0.0031 and an MAE of 0.0177, and an RMSE of 0.0195. Additionally, it exhibited precise FAP detection capabilities in image prediction. The developed U-Net-based model exhibited exceptional performance in accurately detecting P-wave FAP in seismic signals with varying amplitudes. Through the developed model, we aim to contribute to the advancement of microseismic monitoring technology used in various industrial fields. |
| first_indexed | 2024-03-08T15:08:45Z |
| format | Article |
| id | doaj.art-b3c161e4328844199ed201a73e5a9a85 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-08T15:08:45Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-b3c161e4328844199ed201a73e5a9a852024-01-10T14:55:19ZengMDPI AGElectronics2079-92922024-01-0113122910.3390/electronics13010229Deep-Learning-Based Seismic-Signal P-Wave First-Arrival Picking Detection Using Spectrogram ImagesSugi Choi0Bohee Lee1Junkyeong Kim2Haiyoung Jung3Department of Fire and Disaster Prevention, Semyung University, 65 Semyung-ro, Jecheon-si 27136, Republic of KoreaDepartment of Electrical Engineering, Semyung University, 65 Semyung-ro, Jecheon-si 27136, Republic of KoreaDepartment of Fire and Disaster Prevention, Semyung University, 65 Semyung-ro, Jecheon-si 27136, Republic of KoreaDepartment of Fire and Disaster Prevention, Semyung University, 65 Semyung-ro, Jecheon-si 27136, Republic of KoreaThe accurate detection of P-wave FAP (First-Arrival Picking) in seismic signals is crucial across various industrial domains, including coal and oil exploration, tunnel construction, hydraulic fracturing, and earthquake early warning systems. At present, P-wave FAP detection relies on manual identification by experts and automated methods using Short-Term Average to Long-Term Average algorithms. However, these approaches encounter significant performance challenges, especially in the presence of real-time background noise. To overcome this limitation, this study proposes a novel P-wave FAP detection method that employs the U-Net model and incorporates spectrogram transformation techniques for seismic signals. Seismic signals, similar to those encountered in South Korea, were generated using the stochastic model simulation program. Synthesized WGN (White Gaussian Noise) was added to replicate background noise. The resulting signals were transformed into 2D spectrogram images and used as input data for the U-Net model, ensuring precise P-wave FAP detection. In the experimental result, it demonstrated strong performance metrics, achieving an MSE of 0.0031 and an MAE of 0.0177, and an RMSE of 0.0195. Additionally, it exhibited precise FAP detection capabilities in image prediction. The developed U-Net-based model exhibited exceptional performance in accurately detecting P-wave FAP in seismic signals with varying amplitudes. Through the developed model, we aim to contribute to the advancement of microseismic monitoring technology used in various industrial fields.https://www.mdpi.com/2079-9292/13/1/229deep learningFAP (First-Arrival Picking) detectionseismic signalspectrogram imagesU-Net modelWGN (white Gaussian noise) |
| spellingShingle | Sugi Choi Bohee Lee Junkyeong Kim Haiyoung Jung Deep-Learning-Based Seismic-Signal P-Wave First-Arrival Picking Detection Using Spectrogram Images Electronics deep learning FAP (First-Arrival Picking) detection seismic signal spectrogram images U-Net model WGN (white Gaussian noise) |
| title | Deep-Learning-Based Seismic-Signal P-Wave First-Arrival Picking Detection Using Spectrogram Images |
| title_full | Deep-Learning-Based Seismic-Signal P-Wave First-Arrival Picking Detection Using Spectrogram Images |
| title_fullStr | Deep-Learning-Based Seismic-Signal P-Wave First-Arrival Picking Detection Using Spectrogram Images |
| title_full_unstemmed | Deep-Learning-Based Seismic-Signal P-Wave First-Arrival Picking Detection Using Spectrogram Images |
| title_short | Deep-Learning-Based Seismic-Signal P-Wave First-Arrival Picking Detection Using Spectrogram Images |
| title_sort | deep learning based seismic signal p wave first arrival picking detection using spectrogram images |
| topic | deep learning FAP (First-Arrival Picking) detection seismic signal spectrogram images U-Net model WGN (white Gaussian noise) |
| url | https://www.mdpi.com/2079-9292/13/1/229 |
| work_keys_str_mv | AT sugichoi deeplearningbasedseismicsignalpwavefirstarrivalpickingdetectionusingspectrogramimages AT boheelee deeplearningbasedseismicsignalpwavefirstarrivalpickingdetectionusingspectrogramimages AT junkyeongkim deeplearningbasedseismicsignalpwavefirstarrivalpickingdetectionusingspectrogramimages AT haiyoungjung deeplearningbasedseismicsignalpwavefirstarrivalpickingdetectionusingspectrogramimages |