Velocity-model building is a key step in hydrocarbon exploration. The main product of velocity-model building is an initial model of the subsurface that is subsequently used in seismic imaging and interpretation workflows. Reflection or refraction tomography and full-waveform inversion (FWI) are the most commonly used techniques in velocity-model building. On one hand, tomography is a time-consuming activity that relies on successive updates of highly human-curated analysis of gathers. On the other hand, FWI is very computationally demanding with no guarantees of global convergence. We propose and implement a novel concept that bypasses these demanding steps, directly producing an accurate gridding or layered velocity model from shot gathers. Our approach relies on training deep neural networks. The resulting predictive model maps relationships between the data space and the final output (particularly the presence of high-velocity segments that might indicate salt formations). The training task takes a few hours for 2D data, but the inference step (predicting a model from previously unseen data) takes only seconds. The promising results shown here for synthetic 2D data demonstrate a new way of using seismic data and suggest fast turnaround of workflows that now make use of machine-learning approaches to identify key structures in the subsurface.

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.

No abstract

Seismic inversion is a fundamental tool in geophysical analysis, providing a window into the Earth. In particular, it enables the reconstruction of large scale subsurface earth models for hydrocarbon exploration, mining, earthquakes analysis, shallow hazard assessment and other geophysical tasks. This article provides a comprehensive and timely overview of emerging datadriven Deep Learning (DL) solutions to seismic inverse problems, including velocity, impedance, reflectivity model building and seismic bandwidth extension. The article reviews seismic wave propagation and signal acquisition principles using large scale sensor arrays in offshore and inland exploration. In addition, the relations between the seismic forward and inverse problems are established, and prominent model-based solutions including seismic tomography, Full-Waveform Inversion (FWI) and multiscale FWI are explained. A primer to DL principles is presented, including empirical risk minimization, stochastic gradient-based learning, Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN) and regularization. The article then presents DL-based solutions addressing full seismic inversion as well as DL-assisted FWI solutions including Encoder-Decoder architectures, CNN-based networks and RNN-based networks with Long Short Term Memory and Gated Recurrent Units. Seismic signals features extraction methods such as semblance velocity analysis and seismic spectrograms are discussed, as well as batch vs. sequential data processing architectures. The article further presents advanced solutions based on Generative Adversarial Networks , and Physics-guided DL architectures that incorporate numerical geophysical modeling into the DL training loop, enabling unsupervised and semi-supervised learning.

No abstract