Achieving a proper time-frequency (TF) resolution is the key to extract information from seismic data using TF algorithms and characterize reservoir properties using decomposed frequency components. The generalized S-transform (GST) is one of the most widely used TF algorithms. However, it is difficult to choose an optimized parameter set for the whole seismic data set. In this paper, we propose to set the parameters of the GST adaptively using the instantaneous frequency (IF) of seismic traces. Our workflow begins with building a relationship between the parameter set of the GST and IF using a synthetic wedge model. We use the IF as an indicator for the time thickness of each trace in the wedge model. We then compute the TF spectrum of each trace using the GST with different parameter sets and compare the similarity between the computed TF spectrum and theory TF spectrum. The parameter set with the largest similarity is regarded as the best parameter set for each trace in the wedge model. In this manner, we build a relationship between the parameter set and IF value. We can finally choose the optimum parameter set for the GST according to the IF values of seismic traces. We name the proposed workflow as the self-adaptive GST (SAGST). To demonstrate the validity and effectiveness of the proposed SAGST, we apply it to synthetic seismic traces and field data. Both synthetic and real data examples illustrate that the SAGST can obtain a TF representation with a high TF resolution.

Noise reduction is important for signal analysis. In this paper, we propose a hybrid denoising method based on thresholding and data-driven signal decomposition. The principle of this method is to reconstruct the signal with previously thresholded intrinsic mode functions (IMFs). Empirical mode decomposition (EMD) based methods decompose a signal into a sum of oscillatory components, while variational mode decomposition (VMD) generates an ensemble of modes with their respective centre frequencies, which enables VMD to further decrease redundant modes and keep less residual noise in the modes. To illustrate its superiority, we compare VMD with EMD as well as its derivations, such as ensemble EMD (EEMD), complete EEMD (CEEMD), improved CEEMD (ICEEMD) using synthetic signals and field seismic traces. Compared with EMD and its derivations, VMD has a solid mathematical foundation and is less sensitive to noise, while both make it more suitable for non-stationary seismic signal decomposition. The determination of mode number is key for successful denoising. We develop an empirical equation, which is based on the detrended fluctuation analysis (DFA), to adaptively determine the number of IMFs for signal reconstruction. Then, a scaling exponent obtained by DFA is used as a threshold to distinguish random noise and signal between IMFs and the reconstruction residual. The proposed thresholded VMD denoising method shows excellent performance on both synthetic and field data applications.

The seismic horizon is a critical input for the structure and stratigraphy modeling of reservoirs. It is extremely hard to automatically obtain an accurate horizon interpretation for seismic data in which the lateral continuity of reflections is interrupted by faults and unconformities. The process of seismic horizon interpretation can be viewed as segmenting the seismic traces into different parts and each part is a unique object. Thus, we have considered the horizon interpretation as an object detection problem. We use the encoder-decoder convolutional neural network (CNN) to detect the “objects” contained in the seismic traces. The boundary of the objects is regarded as the horizons. The training data are the seismic traces located on a user-defined coarse grid. We give a unique training label to the time window of seismic traces bounded by two manually picked horizons. To efficiently learn the waveform pattern that is bounded by two adjacent horizons, we use variable sizes for the convolution filters, which is different than current CNN-based image segmentation methods. Two field data examples demonstrate that our method is capable of producing accurate horizons across the fault surface and near the unconformity which is beyond the current capability of horizon picking method.

Microseismic imaging plays an important role in hydraulic fracture detection, and the first-arrival picking of microseismic events is the bedrock of microseismic imaging. Manual picking is the most reliable and also the most time-consuming method for the detection of the first arrival of microseismic events. Accurate and efficient first-arrival picking in a real noisy environment is a challenge for most of the automatic first-arrival picking methods. We have developed a novel workflow to automatically pick the first arrival of microseismics by using a state-of-the art pixel-wise convolutional image segmentation method. We first form the training data by randomly selecting part of the microseismic traces and manually pick the time index of the first arrivals. Next, we segment the selected traces into two parts according to the time index of manual picking and assign each part a label accordingly. Then, we build an encoder-decoder convolutional neural network architecture and use the training data and training label as the input. Next, we obtain the trained network hierarchy by learning the segmented training data and labels. Finally, we predict the first arrivals of microseismic events by applying the trained network hierarchy to the rest of the microseismic traces. The synthetic and field data examples demonstrate that our method successfully identifies the first arrivals. The predicted first-arrival result obtained by using our method is superior to the result obtained by using the traditional method of short-term average and long-term average.

Interpreters face two main challenges in seismic facies analysis. The first challenge is to define, or “label,” the facies of interest. The second challenge is to select a suite of attributes that can differentiate a target facies from the background reflectivity. Our key objective is to determine which seismic attributes can best differentiate one class of chaotic seismic facies from another using modern machine-learning technology. Although simple 1D histograms provide a list of candidate attributes, they do not provide insight into the optimum number or combination of attributes. To address this limitation, we have conducted an exhaustive search whereby we represent the target and background training facies by high-dimensional Gaussian mixture models (GMMs) for each potential attribute combination. The first step is to choose candidate attributes that may be able to differentiate chaotic mass-transport deposits and salt diapirs from the more conformal, coherent background reflectors. The second step is to draw polygons around the target and background facies to provide the labeled data to be represented by GMMs. Maximizing the distance between all GMM facies pairs provides the optimum number and combination of attributes. We use generative topographic mapping to represent the high-dimensional attribute data by a lower dimensional 2D manifold. Each labeled facies provides a probability density function on the manifold that can be compared to the probability density function of each voxel, providing the likelihood that a given voxel is a member of each of the facies. Our first example maps chaotic seismic facies associated with the development of salt diapirs and minibasins. Our second example successfully delineates karst collapse underlying a shale resource play from north Texas.

Seismic noise attenuation is an important step in seismic data processing. Most noise attenuation algorithms are based on the analysis of time-frequency characteristics of the seismic data and noise. We have aimed to attenuate white noise of seismic data using the convolutional neural network (CNN). Traditional CNN-based noise attenuation algorithms need prior information (the “clean” seismic data or the noise contained in the seismic) in the training process. However, it is difficult to obtain such prior information in practice. We assume that the white noise contained in the seismic data can be simulated by a sufficient number of user-generated white noise realizations. We then attenuate the seismic white noise using the modified denoising CNN (MDnCNN). The MDnCNN does not need prior clean seismic data nor pure noise in the training procedure. To accurately and efficiently learn the features of seismic data and band-limited noise at different frequency bandwidths, we first decomposed the seismic data into several intrinsic mode functions (IMFs) using variational mode decomposition and then apply our denoising process to the IMFs. We use synthetic and field data examples to illustrate the robustness and superiority of our method over the traditional methods. The experiments demonstrate that our method can not only attenuate most of the white noise but it also rejects the migration artifacts.