Due to environmental and economic constraints on their acquisition, seismic data are always irregularly sampled and include bad or missing traces, which can cause problems for seismic data processing. Recently, many researchers have attempted to improve seismic data reconstruction using machine learning (ML) techniques, such as convolutional neural networks, which are inspired by computer vision and imaging processing. In this letter, we propose a novel approach for reconstructing missing traces in seismic data using ML techniques, especially recurrent neural network (RNN) algorithms. Instead of processing seismic data as an image, the proposed approach performs seismic trace interpolation using traces that are sequences of time-series data. More specifically, we adopt deep bidirectional long short-term memory (LSTM) for seismic trace interpolation and test models with and without skip connections. Field seismic data are used to demonstrate the effectiveness of the proposed approaches, and the deep bidirectional LSTM (DBiLSTM) with skip connections shows the best performance compared to cubic interpolation, minimum weighted norm interpolation (MWNI), and DBiLSTM without skip connection.

Clays in fault zones have low electrical resistivity, making electrical resistivity tomography (ERT) effective for fault investigations. However, traditional ERT inversion methods struggle to find a unique solution and produce unstable results owing to the ill-posed nature of the problem. To address this, a workflow integrating deep-learning (DL) technology with traditional ERT inversion is proposed. First, a deep-learning model named DL-ERT inversion that maps apparent resistivity data to subsurface resistivity models is developed. To create target-oriented training data, we use approximately 150 field borehole data acquired from various survey areas in South Korea. The DL-ERT inversion algorithm is based on a U-Net structure and includes an additional network called the borehole mixer to incorporate borehole information when available. The DL-ERT inversion model is trained in three stages: base model training, borehole mixer training, and fine-tuning. Results showed that the fine-tuning model provided the highest prediction accuracy for all test datasets. Next, the prediction of the trained model is used as the initial model for the deterministic inversion method to predict the final subsurface model. The efficiency and accuracy of the proposed workflow are demonstrated in fault detection using a field data example compared with traditional deterministic inversion.

The mainstream approach to the interpretation of towed streamer electromagnetic (EM) data is based on 2.5-D and/or 3-D inversions of the observed data into the resistivity models of the subsurface formations. However, the rigorous 3-D and even 2.5-D inversions require large amounts of computational power and time. The synthetic aperture (SA) method is one of the key techniques in remote sensing using radio frequency signals. During recent years, this method was also applied to low-frequency EM fields used for geophysical exploration. This letter demonstrates that the concept of the SA EM method can be extended for rapid imaging of the large volumes of towed streamer EM data. We introduce a notion of virtual receivers, which complement the actual receivers in the construction of the SA for the towed streamer data. A numerical study demonstrates that this method increases the EM response from potential subsurface targets and opens a possibility for on-board real-time imaging of EM data during a survey. The method is illustrated by the imaging of towed streamer EM data acquired over the Troll oil and gas fields in the North Sea. Remarkably, the imaging of the entire towed streamer EM survey requires just a few seconds of computation time on a desktop PC. This result is significant, because it opens a possibility for real-time imaging of the towed streamer EM survey data.

In seismic data acquisition, data loss can occur, particularly with the use of streamer systems in marine seismic exploration. These systems often cause spatial aliasing problems by having close inline intervals and wide crossline intervals to maximize the exploration range. To improve the resolution of seismic data in the crossline direction, various machine learning techniques have been employed for crossline data reconstruction. In this study, we introduce a 3D cWGAN (conditional Wasserstein generative adversarial network) for interpolating 3D seismic data. We evaluate the model’s performance by comparing it with 2D cWGAN and 3D U-Net. In this study, two interpolation strategies are employed to reconstruct missing data in the crossline direction. The first strategy uses a 2D network, which trains a model using inline data and applies the trained model to the crossline direction via 2D cWGAN. The second strategy employs a 3D network, which uses the 3D volume of the seismic data directly via 3D cWGAN and 3D U-Net. We demonstrate the effectiveness of the proposed method using the Sleipner CO2 4D seismic survey dataset. Our results show that the 3D cWGAN is more efficient in enhancing resolution and computation compared to the 2D cWGAN or 3D U-Net.