Multiresolution neural networks for tracking seismic horizons from few training images

Abstract

Detecting a specific horizon in seismic images is a valuable tool for geological interpretation. Because hand-picking the locations of the horizon is a time-consuming process, automated computational methods were developed starting three decades ago. Older techniques for such picking include interpolation of control points however, in recent years neural networks have been used for this task. Until now, most networks trained on small patches from larger images. This limits the networks ability to learn from large-scale geologic structures. Moreover, currently available networks and training strategies require label patches that have full and continuous annotations, which are also time-consuming to generate.We propose a projected loss-function for training convolutional networks with a multi-resolution structure, including variants of the U-net. Our networks learn from a small number of large seismic images without creating patches. The projected loss-function enables training on labels with just a few annotated pixels and has no issue with the other unknown label pixels. Training uses all data without reserving some for validation. Only the labels are split into training/testing. Contrary to other work on horizon tracking, we train the network to perform non-linear regression, and not classification. As such, we propose labels as the convolution of a Gaussian kernel and the known horizon locations that indicate uncertainty in the labels. The network output is the probability of the horizon location. We demonstrate the proposed computational ingredients on two different datasets, for horizon extrapolation and interpolation. We show that the predictions of our methodology are accurate even in areas far from known horizon locations because our learning strategy exploits all data in large seismic images.

Semi-supervised Segmentation of Salt Bodies in Seismic Images Using an Ensemble of Convolutional Neural Networks

“…Another work related to ours is [36]. Authors try to mitigate the high cost of manual annotations of seismic images by introducing an approach which can utilize sparse annotations instead of the commonly used dense segmentation masks.…”

Neural networks for geophysicists and their application to seismic data interpretation

“…It was shown previously [Peters et al, 2018] that it is possible to track a single horizon using the Unet based networks and loss-functions that compute losses and gradients based on the sparse labels only. Therefore, there was no need to work in small patches around labeled points or manually generate fully annotated label images.…”

“…are the labeled features that need to be recovered. Using deep convolution networks is therefore a straight forward extension of existing neural network technology and have been studied recently by many authors (see for example [Peters et al, 2018, 2019, Wu and Zhang, 2018, Waldeland et al, 2018, Poulton, 2002, Leggett et al, 2003, Lowell and Paton, 2018, Zhao, 2018 and references within). However, while it seems straight forward to use such algorithms, there are some fundamental differences between vision-related applications to seismic processing.…”

Does shallow geological knowledge help neural-networks to predict deep units?

“…During the last few years, new neural network designs have shown that they can provide high-quality interpretations. In particular, U-nets were used for the interpretation of geological units [Peters et al, 2019a,b], horizons [Peters et al, 2018], salt [Zeng et al, 2018], and faults [Wu et al, 2019, Zhang et al, 2019.…”

“…Recently, Peters et al [2018Peters et al [ , 2019a introduced partial loss-functions for non-linear regression and classification for seismic interpretation. These type of loss functions measure misfit at the known and sparsely distributed annotated label pixels only.…”