A robust first-arrival picking workflow using convolutional and recurrent neural networks

Abstract

A deep-learning-based workflow is proposed in this paper to solve the first-arrival picking problem for near-surface velocity model building. The traditional method such as STA/LTA method performs poorly when signal-to-noise ratio (SNR) is low or near-surface geological structures are complex. This challenging task is formulated as a segmentation problem accompanied by a novel post-processing 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 datasets. Particularly, we highlight 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 RNN to optimize the picking. Finally, we adopt a simple transfer learning scheme and demonstrate its robustness via a weight adaptation approach to maintain the picking performance on new datasets. Our tests on synthetic datasets show the advantage of the proposed workflow compared with the existing deep-learning methods that focus only on segmentation performance. Our tests on field datasets illustrate that a good post-processing picking step is essential for correcting the segmentation errors and the overall workflow is efficient in minimizing human interventions for the first-arrival picking task.

Deep Learning for Geophysics: Current and Future Trends

“…This method works well for noisy situations and field datasets. After the segmentation image is obtained, a more advanced picking algorithm, such as an RNN, can be applied to take advantage of the global information (Yuan et al, 2020).…”

A Comparative Analysis of Machine Learning Models for First-break Arrival Picking

“…They deployed seven-layered U-Net architecture with skip connection. In [28], U-Net was used for segmentation of seismic image and Recurrent Neural Network (RNN), for arrival picking. Additionally, the authors proposed a simple weight adaptation method for generalization of the model in unseen data.…”

Iterative Gaussian mixture model and multi‐channel attributes for arrival picking in extremely noisy environments

“…In addition to these popular conventional methods, machine‐learning methods are also important and popular ways to identify the locations of arrivals and have been developed by many researchers in recent years (Glinsky et al ., 2001; Reynen and Audet, 2017; Chen, 2018; Zheng et al ., 2018; Chen et al ., 2019; Dokht et al ., 2019; Wang et al ., 2019; Woollam et al ., 2019; Wu et al ., 2019; Chen, 2020; Duan and Zhang, 2020; Qu et al ., 2020; Yuan et al ., 2020; Saad et al ., 2021). McCormack et al .…”