Automated fault detection without seismic processing

TLDR

Large volumes of seismic data are acquired for hydrocarbon exploration and are traditionally processed through expensive adjoint modeling and interpretation workflows to identify geologic features such as fault networks and salt bodies. This study proposes a novel approach that bypasses these costly steps to directly aid interpretation. The method trains a deep neural network to map raw seismic data to spatial fault points, using a Wasserstein loss that preserves fault surface continuity for accurate predictions. Synthetic data experiments demonstrate that this approach provides a promising, more direct way to identify subsurface elements from seismic data.

Abstract

For hydrocarbon exploration, large volumes of data are acquired and used in physical modeling-based workflows to identify geologic features of interest such as fault networks, salt bodies, or, in general, elements of petroleum systems. The adjoint modeling step, which transforms the data into the model space, and subsequent interpretation can be very expensive, both in terms of computing resources and domain-expert time. We propose and implement a unique approach that bypasses these demanding steps, directly assisting interpretation. We do this by training a deep neural network to learn a mapping relationship between the data space and the final output (particularly, spatial points indicating fault presence). The key to obtaining accurate predictions is the use of the Wasserstein loss function, which properly handles the structured output — in our case, by exploiting fault surface continuity. The promising results shown here for synthetic data demonstrate a new way of using seismic data and suggest more direct methods to identify key elements in the subsurface.