Search

Joint inversion has drawn considerable attention due to the availability of multiple geophysical data sets, ever-increasing computational resources, the development of advanced algorithms, and its ability to reduce inversion uncertainty. A key issue of joint inversion is to develop effective strategies to link different geophysical data in a unified mathematical framework, in which the information obtained from different models can complement each other. We have developed a deep learning-enhanced joint inversion framework to simultaneously reconstruct different physical models by fusing different types of geophysical data. Traditionally, structure similarity constraints are pursued by joint inversion algorithms using manually crafted formulations (e.g., cross gradient). The constraint is constructed by a deep neural network (DNN) during the learning process. The framework is designed to combine the DNN and a traditional independent inversion workflow and improve the joint inversion result iteratively. The network can be easily extended to incorporate multiphysics without structural changes. Numerical experiments on the joint inversion of 2D DC resistivity data and seismic traveltime are used to validate our method. In addition, this learning-based framework demonstrates excellent generalization abilities when tested on data sets using different geologic structures. It also can handle different sensing configurations and nonconforming discretization.

Timely inspection of subsea infrastructure, especially subsea pipelines, is the key to the prevention of oil spills. In this paper, a transformative offshore pipeline inspection technology is presented by using a bio-inspired autonomous robotic system equipped with a processing unit for underwater computer vision processing and edge computing. The goal is to build a time-efficient and cost-effective system for underwater pipeline inspection that can detect oil leakage at early stages and prevent disastrous results. In this paper, we introduced a bio-inspired autonomous underwater vehicle (BAUV) equipped with video cameras and mobile edge computing devices. We deploy a deep neural network (DNN) specially trained for a variety of underwater image/video processing tasks. The intelligent computer vision processing unit allows us to navigate and track objects even when the visibility is poor. This time-efficient and cost-effective solution will detect pipeline leakage and rupture at an early stage and allow operators to make timely and informed decisions to minimize environmental impacts.

In this communication, a trainable theory-guided recurrent neural network (RNN) equivalent to the finite-difference-time-domain (FDTD) method is exploited to formulate electromagnetic propagation, solve Maxwell’s equations and the inverse problem on differentiable programming platform Pytorch. For forward modeling, the computation efficiency is substantially improved compared to conventional FDTD implemented on Matlab. Gradient computation becomes more precise and faster than the traditional finite difference method benefiting from the accurate and efficient automatic differentiation on the differentiable programming platform. Moreover, by setting the trainable weights of RNN as the material-related parameters, an inverse problem can be solved through training the network. Numerical results demonstrate the effectiveness and efficiency of the method for forward and inverse electromagnetic modeling.

The low-frequency seismic data provides crucial information for guiding the full-waveform inversion (FWI), especially when strong reflectors exist in the velocity model. However, hardware limitations make it difficult to acquire low-frequency data. To overcome the non-linearity and ill-posedness caused by the absence of the low-frequency data, we develop an efficient progressive transfer learning algorithm for low-frequency extrapolation. The proposed method combines the FWI, the sparsity-promoted bandwidth extension (BWE) algorithm, and the physics-guided data-driven deep learning approach. Compared with pure data-driven learning-based methods and the original progressive transfer learning method without BWE, our proposed algorithm shows better generalization ability. By integrating the physics constraints and the BWE algorithm, the performance of our method is less dependent on the quality of the initial training velocity model and the corresponding training set. We propose a logarithmic transformation to re-balance the loss function to overcome the challenge of predicting the weak reflection low-frequency data. To accelerate the algorithm, we propose a learning-based BWE method for initializing the training set and a truncated FWI method to reduce the iterative workflow’s computational cost. Experimental results show that our method achieves both high efficiency and high accuracy. The subsurface structures below the strong reflectors are successfully reconstructed with our extrapolated low-frequency data.

Today, the oil and gas industry is in the midst of a digital revolution of reducing cost and gaining efficiency by automating human-intensive processes. Well-log depth matching from multiple wells has been traditionally labor intensive and continues to pose a challenge to efficiently automate and remove human interventions. Multiple attempts and techniques such as cross correlation and dynamic time warping (DTW) produce mixed successes. However, in many complicated scenarios, manual adjustments from domain experts are still inevitable. Recent solutions to the problem include supervised learning algorithms to automate and classify the well logs through a fully connected neural network. In this paper, we present a different approach based on a Deep Q-Network to optimize the reward of the agent within the environment defined at the well-log inputs. The network leverages one-dimensional (1D) convolutional layers and extracts features from input logs. After extensive training, the agent can then learn to take the best actions until it finds a match.

To effectively overcome the cycle-skipping issue in full-waveform inversion (FWI), we have developed a deep neural network (DNN) approach to predict the absent low-frequency (LF) components by exploiting the hidden physical relation connecting the LF and high-frequency (HF) data. To efficiently solve this challenging nonlinear regression problem, two novel strategies are proposed to design the DNN architecture and to optimize the learning process: (1) the dual data feed structure and (2) progressive transfer learning. With the dual data feed structure, not only the HF data, but also the corresponding beat tone data, are fed into the DNN to relieve the burden of feature extraction. The second strategy, progressive transfer learning, enables us to train the DNN using a single evolving training data set. Within the framework of progressive transfer learning, the training data set continuously evolves in an iterative manner by gradually retrieving the subsurface information through the physics-based inversion module, progressively enhancing the prediction accuracy of the DNN and propelling the inversion process out of the local minima. The synthetic numerical experiments suggest that, without any a priori geologic information, the LF data predicted by the progressive transfer learning are sufficiently accurate for an FWI engine to produce reliable subsurface velocity models free of cycle-skipping artifacts.

The simultaneous-source technology for high-density seismic acquisition is a key solution to efficient seismic surveying. It is a cost-effective method when blended subsurface responses are recorded within a short time interval using multiple seismic sources. A following deblending process, however, is needed to separate signals contributed by individual sources. Recent advances in deep learning and its data-driven approach toward feature engineering have led to many new applications for a variety of seismic processing problems. It is still a challenge, though, to collect enough labeled data and avoid model overfitting and poor generalization performance over different datasets with a low resemblance from each other. In this article, we propose a novel self-supervised learning method to solve the deblending problem without labeled training datasets. Using a blind-trace deep neural network and a carefully crafted blending loss function, we demonstrate that the individual source-response pairs can be accurately separated under three different blended-acquisition designs.

In this paper, we discuss an unsupervised deep learning (DL) method for solving time domain electromagnetic simulations. Compared to the conventional approach, our method encodes initial conditions, boundary conditions as well as Maxwell's equations as the constraints when training the network, turning an electromagnetic simulation problem into an optimization process. High prediction accuracy of the electromagnetic fields, without discretization or interpolation in space or in time, can be achieved with limited number of layers and neurons in each layer of the neural network. We study several numerical examples to demonstrate the effectiveness of this method for simulating time-domain electromagnetic fields. First, the accuracy of this method is validated by comparing with the analytical solution of a 1D cavity model filled with homogeneous media. Then, we combine the continuity condition to modify the loss function for handling medium discontinuities. Further, the computational efficiency of finite-difference and DL methods in conductive and nonlinear media is compared. Finally, we prove the effectiveness of this method in high-dimensional and multi-scale simulations.

In this article, a new scheme based on the supervised descent method (SDM) for solving directional electromagnetic logging-while-drilling (LWD) inverse problems is proposed. The SDM provides us a new perspective to combine the classical gradient-based inversion and machine-learning-based inversion schemes. It iteratively learns a set of descent directions in the offline training process, where the training model set is generated in advance according to the prior information, and then updates the models with the learned descent directions as well as data residuals in the prediction stage, resulting in great flexibility to incorporate prior information, the capability of skipping local minima, and accelerated convergence. The generalization ability of the SDM to interrogate new models that are not contained in the training model set is also explored. By utilizing real-time information obtained from the logging process, the learned descent directions can be slightly revised with a higher efficiency to get closer to the true model. In addition, we probe the sensitivity of the SDM by adding different levels of random noise to the measurements. Numerical examples demonstrate that SDM-based inversion can achieve a higher resolution, faster convergence, and higher robustness than conventional schemes such as Occam’s inversion.

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.

Depth matching of multiple logging curves is essential to any well evaluation or reservoir characterization. Depth matching can be applied to various measurements of a single well or multiple log curves from multiple wells within the same field. Because many drilling advisory projects have been launched to digitalize the well-log analysis, accurate depth matching becomes an important factor in improving well evaluation, production, and recovery. It is a challenge, though, to align the log curves from multiple wells due to the unpredictable structure of the geologic formations. We have conducted a study on the alignment of multiple gamma-ray well logs by using the state-of-the-art machine-learning techniques. Our objective is to automate the depth-matching task with minimum human intervention. We have developed a novel multitask learning approach by using a deep neural network to optimize the depth-matching strategy that correlates multiple gamma-ray logs in the same field. Our approach can be extended to other applications as well, such as automatic formation top labeling for an ongoing well given a reference well.