Deep-learning techniques appear to be poised to play very important roles in our processing flows for inversion and interpretation of seismic data. The most successful seismic applications of these complex pattern-identifying networks will, presumably, be those that also leverage the deterministic physical models on which we normally base our seismic interpretations. If this is true, algorithms belonging to theory-guided data science, whose aim is roughly this, will have particular applicability in our field. We have developed a theory-designed recurrent neural network (RNN) that allows single- and multidimensional scalar acoustic seismic forward-modeling problems to be set up in terms of its forward propagation. We find that training such a network and updating its weights using measured seismic data then amounts to a solution of the seismic inverse problem and is equivalent to gradient-based seismic full-waveform inversion (FWI). By refining these RNNs in terms of optimization method and learning rate, comparisons are made between standard deep-learning optimization and nonlinear conjugate gradient and limited-memory Broyden-Fletcher-Goldfarb-Shanno (L-BFGS) optimized algorithms. Our numerical analysis indicates that adaptive moment (or Adam) optimization with a learning rate set to match the magnitudes of standard FWI updates appears to produce the most stable and well-behaved waveform inversion results, which is reconfirmed by a multidimensional 2D Marmousi experiment. Future waveform RNNs, with additional degrees of freedom, may allow optimal wave propagation rules to be solved for at the same time as medium properties, reducing modeling errors.

The determination of subsurface elastic property models is crucial in quantitative seismic data processing and interpretation. This problem is commonly solved by deterministic physical methods, such as tomography or full-waveform inversion. However, these methods are entirely local and require accurate initial models. Deep learning represents a plausible class of methods for seismic inversion, which may avoid some of the issues of purely descent-based approaches. However, any generic deep learning network capable of relating each elastic property cell value to each sample in a seismic data set would require a very large number of degrees of freedom. Two approaches might be taken to train such a network: first, by invoking a massive and exhaustive training data set and, second, by working to reduce the degrees of freedom by enforcing physical constraints on the model-data relationship. The second approach is referred to as “physics-guiding.” Based on recent progress in wave theory-designed (i.e., physics-based) networks, we have developed a hybrid network design, involving deterministic, physics-based modeling and data-driven deep learning components. From an optimization standpoint, a data-driven model misfit (i.e., standard deep learning) and now a physics-guided data residual (i.e., a wave propagation network) are simultaneously minimized during the training of the network. An experiment is carried out to analyze the trade-off between two types of losses. Synthetic velocity building is used to examine the potential of hybrid training. Comparisons demonstrate that, given the same training data set, the hybrid-trained network outperforms the traditional fully data-driven network. In addition, we perform a comprehensive error analysis to quantitatively compare the fully data-driven and hybrid physics-guided approaches. The network is applied to the SEG salt model data, and the uncertainty is analyzed, to further examine the benefits of hybrid training.

First arrival time picking is one of the critical processing steps of acoustic emission (AE)/microseismic (MS) monitoring for studying rock fracture processes. Because of massive monitoring data, the automatic arrival time picking technique is particularly desired. Inspired by recent successful applications of machine learning (ML) in earthquake phase identification, we propose a deep learning (DL)-based P-wave first arrival time picking method named AE Network (AEnet) for laboratory AE monitoring data. Our approach consists of two steps: classification and picking. The convolutional neural network (CNN) is used to classify each sample point of acoustic waveforms into either noise or signal. Different from prior DL-based phase picking studies using raw waveforms, we combine the waveform and high-order statistics as the input to enrich the input data features and accelerate the CNN model learning process. Our approach is examined using the laboratory AE monitoring data and the performance of each component of AEnet is also analyzed. The results show that the CNN model can classify the sample points accurately for the picking procedure. With this classification result, we pick the first arrival time of each trace using the curve fitting method and an unsupervised clustering algorithm. To evaluate the performance of AEnet, we apply Akaike Information Criterion-Short Term Averaging/Long Term Averaging Method (AIC-STA/LTA), one of the most popular and traditional picking methods, on the same waveforms and use the manual picks as the reference. Error analysis results show that AEnet outperforms AIC-STA/LTA.

Interferometric Synthetic Aperture Radar (InSAR) provides subcentimetric measurements of surface displacements, which are key for characterizing and monitoring magmatic processes in volcanic regions. The abundant measurements of surface displacements in multitemporal InSAR data routinely acquired by SAR satellites can facilitate near real‐time volcano monitoring on a global basis. However, the presence of atmospheric signals in interferograms complicates the interpretation of those InSAR measurements, which can even lead to a misinterpretation of InSAR signals and volcanic unrest. Given the vast quantities of SAR data available, an automatic InSAR data processing and denoising approach is required to separate volcanic signals that are cause of concern from atmospheric signals and noise. In this study, we employ a deep learning strategy that directly removes atmospheric and other noise signals from time‐consecutive unwrapped surface displacements obtained through an InSAR time series approach using an end‐to‐end convolutional neural network (CNN) with an encoder‐decoder architecture, modified U‐net. The CNN is trained with simulated synthetic unwrapped surface displacement maps and is then applied to real InSAR data. Our proposed architecture is capable of detecting dynamic spatio‐temporal patterns of volcanic surface displacements. We find that an ensemble‐average strategy is recommended to stabilize detected results for varying deformation rates and signal‐to‐noise ratios (SNRs). A case study is also presented where this method is applied to InSAR data covering Masaya volcano, Nicaragua and the results are validated using continuous GPS data. The results confirm that our network can indeed efficiently suppress atmospheric and other noise to reveal the noise‐free surface deformation.