Effective First-Break Picking of Seismic Data Using Geometric Learning Methods
Automatic first-break(FB) picking is a key task in seismic data processing, with numerous applications in the field. Over the past few years, both unsupervised and supervised learning algorithms have been applied to 2D seismic arrival time picking and obtained good picking results. In this paper, we...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/17/2/232 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832587591017299968 |
|---|---|
| author | Zhongyang Wen Jinwen Ma |
| author_facet | Zhongyang Wen Jinwen Ma |
| author_sort | Zhongyang Wen |
| collection | DOAJ |
| description | Automatic first-break(FB) picking is a key task in seismic data processing, with numerous applications in the field. Over the past few years, both unsupervised and supervised learning algorithms have been applied to 2D seismic arrival time picking and obtained good picking results. In this paper, we introduce a strategy of optimizing certain geometric properties of the target curve for first-break picking which can be implemented in both unsupervised and supervised learning modes. Specifically, in the case of unsupervised learning, we design an effective curve evolving algorithm according to the active contour(AC) image segmentation model, in which the length of the target curve and the fitting region energy are minimized together. It is interpretable, and its effectiveness and robustness are demonstrated by the experiments on real world seismic data. We further investigate three schemes of combining it with human interaction, which is shown to be highly useful in assisting data annotation or correcting picking errors. In the case of supervised learning especially for deep learning(DL) models, we add a curve loss term based on the target curve geometry of first-break picking to the typical loss function. It is demonstrated by various experiments that this curve regularized loss function can greatly enhance the picking quality. |
| format | Article |
| id | doaj-art-ae70d3eac5c14aeaa34e615af4fad21d |
| institution | Kabale University |
| issn | 2072-4292 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj-art-ae70d3eac5c14aeaa34e615af4fad21d2025-01-24T13:47:49ZengMDPI AGRemote Sensing2072-42922025-01-0117223210.3390/rs17020232Effective First-Break Picking of Seismic Data Using Geometric Learning MethodsZhongyang Wen0Jinwen Ma1Department of Information and Computational Sciences, School of Mathematical Sciences and LMAM, Peking University, Beijing 100871, ChinaDepartment of Information and Computational Sciences, School of Mathematical Sciences and LMAM, Peking University, Beijing 100871, ChinaAutomatic first-break(FB) picking is a key task in seismic data processing, with numerous applications in the field. Over the past few years, both unsupervised and supervised learning algorithms have been applied to 2D seismic arrival time picking and obtained good picking results. In this paper, we introduce a strategy of optimizing certain geometric properties of the target curve for first-break picking which can be implemented in both unsupervised and supervised learning modes. Specifically, in the case of unsupervised learning, we design an effective curve evolving algorithm according to the active contour(AC) image segmentation model, in which the length of the target curve and the fitting region energy are minimized together. It is interpretable, and its effectiveness and robustness are demonstrated by the experiments on real world seismic data. We further investigate three schemes of combining it with human interaction, which is shown to be highly useful in assisting data annotation or correcting picking errors. In the case of supervised learning especially for deep learning(DL) models, we add a curve loss term based on the target curve geometry of first-break picking to the typical loss function. It is demonstrated by various experiments that this curve regularized loss function can greatly enhance the picking quality.https://www.mdpi.com/2072-4292/17/2/232first-break pickingseismic dataactive contourslevel-setdeep learningsemantic segmentation |
| spellingShingle | Zhongyang Wen Jinwen Ma Effective First-Break Picking of Seismic Data Using Geometric Learning Methods Remote Sensing first-break picking seismic data active contours level-set deep learning semantic segmentation |
| title | Effective First-Break Picking of Seismic Data Using Geometric Learning Methods |
| title_full | Effective First-Break Picking of Seismic Data Using Geometric Learning Methods |
| title_fullStr | Effective First-Break Picking of Seismic Data Using Geometric Learning Methods |
| title_full_unstemmed | Effective First-Break Picking of Seismic Data Using Geometric Learning Methods |
| title_short | Effective First-Break Picking of Seismic Data Using Geometric Learning Methods |
| title_sort | effective first break picking of seismic data using geometric learning methods |
| topic | first-break picking seismic data active contours level-set deep learning semantic segmentation |
| url | https://www.mdpi.com/2072-4292/17/2/232 |
| work_keys_str_mv | AT zhongyangwen effectivefirstbreakpickingofseismicdatausinggeometriclearningmethods AT jinwenma effectivefirstbreakpickingofseismicdatausinggeometriclearningmethods |