A robust first-arrival picking workflow using convolutional and recurrent neural networks
- 1 September 2020
- journal article
- research article
- Published by Society of Exploration Geophysicists in Geophysics
- Vol. 85 (5) , U109-U119
Abstract
A deep-learning-based workflow is proposed in this paper to solve the first-arrival picking problem for near-surface velocity model building. Traditional methods, such as the short-term average/long-term average method, perform poorly when the signal-to-noise ratio is low or near-surface geologic structures are complex. This challenging task is formulated as a segmentation problem accompanied by a novel postprocessing approach to identify pickings along the segmentation boundary. The workflow includes three parts: a deep U-net for segmentation, a recurrent neural network (RNN) for picking, and a weight adaptation approach to be generalized for new data sets. In particular, we have evaluated the importance of selecting a proper loss function for training the network. Instead of taking an end-to-end approach to solve the picking problem, we emphasize the performance gain obtained by using an RNN to optimize the picking. Finally, we adopt a simple transfer learning scheme and test its robustness via a weight adaptation approach to maintain the picking performance on new data sets. Our tests on synthetic data sets reveal the advantage of our workflow compared with existing deep-learning methods that focus only on segmentation performance. Our tests on field data sets illustrate that a good postprocessing picking step is essential for correcting the segmentation errors and that the overall workflow is efficient in minimizing human interventions for the first-arrival picking task.Keywords
Funding Information
- National Science Foundation (1746824)
This publication has 21 references indexed in Scilit:
- Automatic microseismic event picking via unsupervised machine learningGeophysical Journal International, 2017
- Seismic features and automatic discrimination of deep and shallow induced-microearthquakes using neural network and logistic regressionGeophysical Journal International, 2016
- U-Net: Convolutional Networks for Biomedical Image Segmentation2015
- Novel hybrid artificial neural network based autopicking workflow for passive seismic dataGeophysical Prospecting, 2014
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012
- Long Short-Term MemoryNeural Computation, 1997
- First-break refraction event picking and seismic data trace editing using neural networksGeophysics, 1993
- A Learning Algorithm for Continually Running Fully Recurrent Neural NetworksNeural Computation, 1989
- FIRST ARRIVAL PICKING ON COMMON‐OFFSET TRACE COLLECTIONS FOR AUTOMATIC ESTIMATION OF STATIC CORRECTIONS*Geophysical Prospecting, 1985
- DIGITAL PROCESSING OF REFRACTION DATA STUDY OF FIRST ARRIVALS*Geophysical Prospecting, 1972