A method for adequate selection of training data sets to reconstruct seismic field data using a convolutional U-Net

Deep learning (DL) methods are recently introduced for seismic signal processing. Using DL methods, many researchers have adopted these novel techniques in an attempt to construct a DL model for seismic data reconstruction. The performance of DL-based methods depends heavily on what is learned from the training data. We focus on constructing the DL model that well reflect the features of target data sets. The main goal is to integrate DL with an intuitive data analysis approach that compares similar patterns prior to the DL training stage. We have developed a two-sequential method consisting of two stage: (i) analyzing training and target data sets simultaneously for determining target-informed training set and (ii) training the DL model with this training data set to effectively interpolate the seismic data. Here, we introduce the convolutional autoencoder t-distributed stochastic neighbor embedding (CAE t-SNE) analysis that can provide the insight into the results of interpolation through the analysis of both the training and target data sets prior to DL model training. The proposed method were tested with synthetic and field data. Dense seismic gathers (e.g. common-shot gathers; CSGs) were used as a labeled training data set, and relatively sparse seismic gather (e.g. common-receiver gathers; CRGs) were reconstructed in both cases. The reconstructed results and SNRs demonstrated that the training data can be efficiently selected using CAE t-SNE analysis and the spatial aliasing of CRGs was successfully alleviated by the trained DL model with this training data, which contain target features. These results imply that the data analysis for selecting target-informed training set is very important for successful DL interpolation. Additionally, the proposed analysis method can also be applied to investigate the similarities between training and target data sets for another DL-based seismic data reconstruction tasks.

Time-lapse seismic data reconstruction using compressive sensing

The time-lapse seismic method plays a critical role in the reservoir monitoring and characterization. However, time-lapse data acquisitions are costly. Sparse acquisitions combined with post-acquisition data reconstruction could reduce the cost and facilitate more frequent applications of the time-lapse seismic monitoring. We present a sparse time-lapse seismic data reconstruction methodology based on compressive sensing. The method works with a hybrid of repeated and non-repeated sample locations. To make use of the additional information from non-repeated locations, we present a view that non-repeated samples in space are equivalent to irregular samples in calendar time. Therefore, we use these irregular samples in time coming from non-repeated samples in space to improve the performance of compressive sensing reconstruction. The tests on synthetic and field datasets indicate that our method can achieve a sufficiently accurate reconstruction by using as few as 10% of the receivers or traces. The method not only works with spatially irregular sampling for dealing with the land accessibility problem and for reducing the number of nodal sensors, but also utilizes the non-repeated measurements to improve the reconstruction accuracy.