Accurate forward modeling is essential for solving inverse problems in exploration seismology. Unfortunately, it is often not possible to afford being physically or numerically accurate. To overcome this conundrum, we make use of raw and processed data from nearby surveys. We have used these data, consisting of shot records or velocity models, to pretrain a neural network to correct for the effects of, for instance, the free surface or numerical dispersion, both of which can be considered as proxies for incomplete or inaccurate physics. Given this pretrained neural network, we apply transfer learning to fine-tune this pretrained neural network so it performs well on its task of mapping low-cost, but low-fidelity, solutions to high-fidelity solutions for the current survey. As long as we can limit ourselves during fine-tuning to using only a small fraction of high-fidelity data, we gain processing the current survey while using information from nearby surveys. We examined this principle by removing surface-related multiples and ghosts from shot records and the effects of numerical dispersion from migrated images and wave simulations.
Bayesian inference for high-dimensional inverse problems is computationally costly and requires selecting a suitable prior distribution. Amortized variational inference addresses these challenges by pretraining a neural network that acts as a surrogate conditional distribution that approximates the posterior distribution not only for one instance of the observed data but also for the distribution of the data pertaining to a specific inverse problem. When fed previously unseen data, the neural network — in our case, a conditional normalizing flow — provides the posterior samples at virtually no cost. However, the accuracy of amortized variational inference relies on the availability of high-fidelity training data, which seldom exist in geophysical inverse problems because of the earth’s heterogeneous subsurface. In addition, the network is prone to errors if evaluated over data that are not drawn from the training data distribution. As such, we have aimed to increase the resilience of amortized variational inference in the presence of moderate data distribution shifts. We achieve this via a correction to the conditional normalizing flow’s latent distribution that improves the approximation to the posterior distribution for the data at hand. The correction involves relaxing the standard Gaussian assumption on the latent distribution and parameterizing it via a Gaussian distribution with an unknown mean and (diagonal) covariance. These unknowns are then estimated by minimizing the Kullback-Leibler divergence between the corrected and the (physics-based) true posterior distributions. Although generic and applicable to other inverse problems by means of a linearized seismic imaging example, we find that our correction step improves the robustness of amortized variational inference with respect to changes in the number of seismic sources, noise variance, and shifts in the prior distribution. This approach, given noisy seismic data simulated via the linearized Born modeling, provides a seismic image with limited artifacts and an assessment of its uncertainty at approximately the same cost as five reverse time migrations.
We use techniques from Bayesian inference and deep neural networks to translate uncertainty in seismic imaging to uncertainty in tasks performed on the image, such as horizon tracking. Seismic imaging is an ill-posed inverse problem because of bandwidth and aperture limitations, which are hampered by the presence of noise and linearization errors. Many regularization methods, such as transform-domain sparsity promotion, have been designed to deal with the adverse effects of these errors; however, these methods run the risk of biasing the solution and do not provide information on uncertainty in the image space and how this uncertainty impacts certain tasks on the image. A systematic approach is developed to translate uncertainty due to noise in the data to the confidence intervals of automatically tracked horizons in the image. The uncertainty in the seismic image is characterized by a convolutional neural network (CNN) that is used to reparameterize the image. To assess these uncertainties, samples are drawn from the posterior distribution of the CNN weights. Compared with traditional priors, it is argued in the literature that these CNNs introduce a flexible inductive bias that is a surprisingly good fit for a diverse set of problems, including medical imaging, compressive sensing, and diffraction tomography. The method of stochastic gradient Langevin dynamics is used to sample from the posterior distribution. This method is designed to handle large-scale Bayesian inference problems with computationally expensive forward operators as in seismic imaging. Aside from offering a robust alternative to the maximum a posteriori estimate that is prone to overfitting, access to these samples allows us to translate uncertainty in the image, due to noise in the data, to uncertainty on the tracked horizons. For instance, it admits estimates for the pointwise standard deviation on the image and for confidence intervals on its automatically tracked horizons.
We present the Seismic Laboratory for Imaging and Modeling/Monitoring open-source software framework for computational geophysics and, more generally, inverse problems involving the wave equation (e.g., seismic and medical ultrasound), regularization with learned priors, and learned neural surrogates for multiphase flow simulations. By integrating multiple layers of abstraction, the software is designed to be both readable and scalable, allowing researchers to easily formulate problems in an abstract fashion while exploiting the latest developments in high-performance computing. The design principles and their benefits are illustrated and demonstrated by means of building a scalable prototype for permeability inversion from time-lapse crosswell seismic data, which, aside from coupling of wave physics and multiphase flow, involves machine learning.
Due to their uncertainty quantification, Bayesian solutions to inverse problems are the framework of choice in applications that are risk averse. These benefits come at the cost of computations that are in general, intractable. New advances in machine learning and variational inference (VI) have lowered this computational barrier by leveraging data-driven learning. Two VI paradigms have emerged that represent different tradeoffs: amortized and non-amortized. Amortized VI can produce fast results but due to generalizing to many observed datasets it produces suboptimal inference results. Non-amortized VI is slower at inference but finds better posterior approximations since it is specialized towards a single observed dataset. Current amortized VI techniques run into a sub-optimality wall that cannot be improved without more expressive neural networks or extra training data. We present a solution that enables iterative improvement of amortized posteriors that uses the same networks architectures and training data. The benefits of our method requires extra computations but these remain frugal since they are based on physics-hybrid methods and summary statistics. Importantly, these computations remain mostly offline thus our method maintains cheap and reusable online evaluation while bridging the optimality gap between these two paradigms. We denote our proposed method ASPIRE - Amortized posteriors with Summaries that are Physics-based and Iteratively REfined. We first validate our method on a stylized problem with a known posterior then demonstrate its practical use on a high-dimensional and nonlinear transcranial medical imaging problem with ultrasound. Compared with the baseline and previous methods in the literature, ASPIRE stands out as an computationally efficient and high-fidelity method for posterior inference.
Modern-day reservoir management and monitoring of geologic carbon storage increasingly call for costly time-lapse seismic data collection. We demonstrate how techniques from graph theory can be used to optimize acquisition geometries for low-cost sparse 4D seismic data. Based on midpoint-offset-domain connectivity arguments, our algorithm automatically produces sparse nonreplicated time-lapse acquisition geometries that favor wavefield recovery.