Physical and/or economic constraints cause acquired seismic data to be incomplete; however, complete data are required for many subsequent seismic processing procedures. Data reconstruction is a crucial and long-standing topic in the exploration seismology field. We extended our previous works on deep learning (DL)-based irregularly and regularly missing 2-D data reconstruction to 3-D data. A key motivation is that the 3-D convolutional neural network (CNN) can take full advantage of the 3-D nature of the data, and the additional dimension allows more information to contribute to the data reconstruction. DL also avoids many assumptions (e.g., linearity, sparsity, and low-rank) limiting conventional nonintelligent reconstruction methods. We built an artificial neural network (ANN) based on an end-to-end U-Net encoder-decoder-style 3-D CNN. The ANN was trained on large quantities of various synthetic and field 3-D seismic data using a mean-squared-error (MSE) loss function and an Adam optimizer. We demonstrated that the developed 3-D CNN reconstruction method appears to outperform the 2-D CNN for 3-D restoration. We benchmarked the ANN's generalization capacity for recovery of irregularly and regularly sampled 3-D data on several typical seismic data sets, particularly those with high missing percentages or large gaps. An ANN trained with irregularly sampled data can be partly applied to regularly sampled cases. We investigated how a key parameter, i.e., the learning rate, can be experimentally determined. In the context of the presented examples, our methodology provided a substantial improvement over an open-source state-of-the-art rank-reduction-based approach in terms of data fidelity and efficiency.

Inspired by image-to-image translation, we applied deep learning (DL) to regularly missing data reconstruction, aimed at translating incomplete data into their corresponding complete data. With this purpose in mind, we first construct a network architecture based on an end-to-end U-Net convolutional network, which is a generic DL solution for various tasks. We then meticulously prepare the training data with both synthetic and field seismic data. This article is implemented in Python based on Keras (a high-level DL library). We described the network architecture, the training data, and the training settings in detail. For training the network, we employed a mean-squared-error loss function and an Adam optimization algorithm. Next, we tested the trained network with several typical data sets, achieving good performances (even in the presence of big gaps) and validating the feasibility, effectiveness, and generalization capability of the assessed framework. The feature maps for a sample going through the well-trained network are uncovered. Compared with the f-x prediction interpolation method, DL performs better and is capable of avoiding several assumptions (e.g., linearity, sparsity, etc.) associated with conventional interpolation methods. We demonstrated the influences of the network depth, the kernel size of the convolution window, and the pooling function on the DL results. We applied the trained network to dense data reconstruction successfully. The proposed method can overcome noise to some extent. We finally discussed some practical aspects and extensions of the evaluated framework.

In transient electromagnetic (TEM) methods, the full transmitting-current waveform, not just the abrupt turn-off, can have effects on the measured responses. A 3D finite-element time-domain forward-modeling solver was used to investigate these effects. This was motivated by an attempt to match, via forward-modeling, real data from the Albany graphite deposit in northern Ontario, Canada. Initial modeling results for homogeneous half-spaces illustrate the effects that a full waveform can have on TEM responses, especially the durations of the steady stage and turn-off time. For the Albany data set, a geophysical conductivity model was developed from a geologic model that itself had been constructed predominantly from drillhole information. The conductivities of the various geologic units in the model were first estimated based on typical conductivity values for the respective rock types, then adjusted to fit the measured TEM data as closely as possible. We found that the TEM responses differed significantly from the pure step-off response and that incorporating the effects of the full waveform (particularly the linear ramp turn-off) greatly improved the match between observed and computed responses, especially for the early measurement times. In addition, this Albany example illustrates the presence of sign changes in TEM data caused primarily by localized conductivity targets.

Sparse-spike deconvolution (SSD) is an important method for seismic resolution enhancement. With the wavelet given, many trace-by-trace SSD methods have been proposed for extracting an estimate of the reflection-coefficient series from stacked traces. The main drawbacks of trace-by-trace methods are that they neither use the information from the adjacent seismograms nor do they take full advantage of the inherent spatial continuity of the seismic data. Although several multitrace methods have been consequently proposed, these methods generally rely on different assumptions and theories and require different parameter settings for different data applications. Therefore, traditional methods demand intensive human-computer interaction. This requirement undoubtedly does not fit the current dominant trend of intelligent seismic exploration. Therefore, we have developed a deep learning (DL)-based multitrace SSD approach. The approach transforms the input 2D/3D seismic data into the corresponding SSD result by training end-to-end encoder-decoder-style 2D/3D convolutional neural networks (CNN). Our key motivations are that DL is effective for mining complicated relations from data, the 2D/3D CNN can take multitrace information into account naturally, the additional information contributes to the SSD result with better spatial continuity, and parameter tuning is not necessary for CNN predictions. We determine the significance of the learning rate for the training process’s convergence. Benchmarking tests on the field 2D/3D seismic data confirm that the approach yields accurate high-resolution results that are mostly in agreement with the well logs, the DL-based multitrace SSD results generated by the 2D/3D CNNs are better than the trace-by-trace SSD results, and the 3D CNN outperforms the 2D CNN for 3D data application.

Geothermal systems are usually characterized by distinct electrical resistivity structures due to their close relationship with the distribution of the temperature, geothermal fluids and clay minerals. Geophysical electromagnetic (EM) methods have been routinely used for geothermal exploration. However, inversion models independently derived from different EM datasets often exhibit ambiguous resistivity features, causing difficulty for reliable interpretation. This work employs a 3D Gauss-Newton approach to jointly invert collocated magnetotelluric (MT) and controlled-source electromagnetic (CSEM) data to better characterize subsurface resistivity structures. To effectively integrate complementary information in different datasets, we have developed a data gradient weighting adaptive joint inversion algorithm based on the norms of individual data residuals to balance contributions from each dataset during the joint inversion process. We first demonstrate the effectiveness of the developed approach on synthetic MT and CSEM data generated from a simplified geothermal model. Then, we apply the 3D joint inversion approach to the MT and CSEM field datasets from the Yanggao region in Shanxi Province, China to image a potential high-temperature geothermal system. Compared to results from single inversions, the joint inversion results demonstrate improved model characterization for both conductive and resistive structures, which is consistent with the results from the seismic surveys. From the joint inversion results, we can clearly delineate the important components of the geothermal system in the region, including thermal reservoirs, hydrothermal alteration layers, as well as conduction channels connecting them. Finally, we propose a conceptual model of the geothermal system in the region, which will be helpful for future drilling purposes.

High-precision vector magnetic field detection has been widely used in the fields of celestial magnetic field detection, aeromagnetic detection, marine magnetic field detection and geomagnetic navigation. Due to the large amount of data, the 3D inversion of high-precision magnetic gradient vector data often involves a large number of computational requirements and is very time-consuming. In this paper, a 3D magnetic gradient tensor (MGT) inversion method is developed, based on using a convolutional neural network (CNN) to automatically predict physical parameters from the 2D images of MGT. The information of geometry, depth and parameters such as magnetic inclination (I), magnetic declination (D) and magnetization susceptibility of magnetic anomalies is extracted, and a 3D model is obtained by comprehensive analysis. The method first obtains sufficient MGT data samples by forward modeling of different magnetic anomalies. Then, we use an improved CNN with shear layers to achieve the prediction of each magnetic parameter. The reliability of the algorithm is verified by numerical simulations of synthetic models of multiple magnetic anomalies. MGT data of the Tallawang magnetite diorite deposit in Australia are also predicted by using this method to obtain a slab model that matches the known geological information. The effects of sample size and noise level on the prediction accuracy are discussed. Compared with single-component prediction, the results of multi-component joint prediction are more reliable. From the numerical model study and the field data validation, we demonstrate the capability of using CNNs for inversing MGT data.