The interpretability and reliability of pre-stack seismic waveform classification are often hindered by the entanglement of various geological factors in pre-stack seismic waveforms, along with their intrinsic uncertainties. To address the problem, we propose a physical knowledge-guided disentangled representation network for a specific interpretation task of pre-stack seismic waveform classification. Unlike physics-driven deep learning methods that incorporate physical laws directly into network structures or loss functions, our approach uses a physical knowledge constraint network to guide deep feature learning based on physical attributes. This enables the model to capture more interpretable and separable features. First the concept of group supervision and disentangled representation theory is applied to separate specific physical attributes within the pre-stack seismic waveform. Then, physical knowledge about the seismic data is incorporated to impose additional constraints during the disentangling of deep features. Finally, a clustering technique is used to cluster disentangled deep features and generate the clustering result, which can assist geological experts in inferring sedimentary environments and the distribution of reservoir. Testing on synthetic data demonstrates that our method effectively separates and reconstructs geological elements within seismic data, accurately classifies different types of reflection patterns, and shows strong robustness against noise. Furthermore, the application of actual data shows that the classification results of pre-stack seismic waveform using the proposed method have better interpretability.

Residual moveout (RMO) provides critical information for depth-domain tomography. The current industry-standard method for fitting RMO involves scanning high-order polynomial equations. However, this analytical approach does not accurately capture abrupt variation of the RMO, leading to low iteration efficiency in tomographic inversion. Supervised learning-based image segmentation methods for picking can effectively capture local variations; however, they encounter challenges such as a scarcity of reliable training samples and the high complexity of post-processing. To address these issues, this study proposes a deep learning-based cascade picking method. It distinguishes accurate and robust RMOs using a segmentation network and a post-processing technique based on trend regression. Additionally, a data synthesis method is introduced, enabling the segmentation network to be trained on synthetic datasets for effective picking in field data. Furthermore, a set of metrics is proposed to quantify the quality of automatically picked RMOs. Experimental results based on both model and real data demonstrate that, compared to semblance-based methods, our approach achieves greater picking density and accuracy.

The application of artificial intelligence in seismic impedance inversion makes the prediction of stratigraphic information more efficient. Semi-supervised framework for impedance inversion is the latest breakthrough method in this field. However, the 1-D semi-supervised methods now in use are unable to extract the spatiotemporal properties of the data solely through the network itself. Moreover, the initial model, a critical input for this method, is typically derived through extrapolation and interpolation of well log data. This can lead to significant errors, especially when the well data are sparse and the subsurface structures are complex. Well data only provide information for a limited section of the reservoir, thereby making it challenging to capture the overall behavior accurately. As a result, the creation of an accurate initial model is often fraught with errors. A more desirable approach is to use seismic attribute-guided methods, such as neural networks, which incorporate both seismic and well log data, leading to a more accurate low-frequency model with lateral variations. In this article, we develop a semi-supervised domain adversarial and spatial fusion (DASF) inversion framework. This method uses a 1-D convolutional neural network (CNN)-based global spatiotemporal analysis module and a 2-D CNN-based local spatiotemporal analysis module to complete the inversion and forward task simultaneously. Multiple spatiotemporal characteristics from two submodules can be successfully fused using an adaptive fusion approach. In this network, the step of extracting the initial model is incorporated into the learning process. Moreover, we adopt adversarial learning in the impedance domain to guide the training process, thereby reducing the network’s dependence on labels. The experiments on the synthetic and field dataset show that the proposed method can efficiently improve the prediction accuracy of the inversion results compared with conventional methods. Meanwhile, the local spatiotemporal analysis module can be used to create a more trustworthy initial model that incorporates the characteristic of seismic and well-logging data.

It is crucial to retain as many signal components as possible, while noise is eliminated for wavelet packet noise reduction algorithms. Conventional thresholding functions take coefficients smaller than a given threshold as the noise component and get them removed in many ways. In this letter, considering the potential probability of being the signal-related component of coefficients whose value is smaller than the given threshold and the nonnegligible fact that microseismic (MS) event is sparse compared with the noise, we proposed a new wavelet packet-based denoising method via fuzzy partition. First, instead of a hard partition from a given threshold, wavelet packet coefficients get reduced by a fuzzy partition to retain more potential signal elements and suppress the noise. Second, we employ fuzzy c-means (FCM) clustering to identify the interval period of the MS event further to remove the residual noise and additional resonance in processed time series. We tested our method on synthetic datasets and real-field data from an MS monitoring experiment in a coal mine in Sichuan Basin, China. We utilize Pearson correlation coefficient and root-mean-square error between ideal signal and denoised data as performance indicators in synthetic tests, while sample entropy and kurtosis of denoised data are involved in the real field dataset. Test results from synthetic datasets and the real field dataset demonstrate that the proposed noise reduction method is superior to traditional hard-, soft-, and garrote-thresholding and is more applicable and effective in MS data processing.

Accurate first arrival picking plays a crucial role in microseismic data processing. However, it is challenging to guarantee satisfactory accuracy with conventional approaches when the signal-to-noise ratio (SNR) of data is low. This article proposes an automatic first arrival time picking method based on fuzzy$C$means clustering (FCM) and Akaike information criterion (AIC). The proposed method consists of three steps: clustering, rough picking, and adjusting. First, we employ FCM to divide each data point into the signal cluster and the noise cluster according to a fuzzy partition. Second, unlike conventional FCM-based picking approaches, we utilize Otsu’s method to determine a data-dependent threshold, instead of an artificially predefined one, to obtain a coarse result of the microseismic event interval from clustering partition. Finally, note that the microseismic event data points are concentrated in amplitude and also correlated in time. Therefore, we employ the AIC of the clustering partition to seek time-varying information to adjust the coarse result. Besides, we investigated several commonly used characteristic factors to introduce a supervised guideline for feature selection in first arrival picking with FCM. At last, we carried out simulations and real field data tests to verify the reliability of the proposed method. The experimental results demonstrate that the proposed method outperforms the short-and long-time average ratio (SLTA) method, the AIC method, and the conventional FCM-based picking method.

Seismic attributes comprise an effective method for oil and gas reservoir characterization and prediction. Hundreds of seismic attributes have been introduced in the last 30 years. Among the seismic attributes targeting different reservoir features, the autoencoder (AE) receives a significant amount of attention, as it extracts deep attributes of seismic data, providing more details of seismic lateral features than other seismic waveform data and seismic attributes. However, data-driven deep attributes bring new challenges to interpretation as they lack the support of intrinsic physical mechanisms. Hence, a shared AE (S-AE) method is proposed in this article, which can extract seismic deep attributes and fuse traditional seismic attributes simultaneously. An S-AE is a revised version of an AE, which consists of an encoder and decoder. An S-AE takes the seismic waveform as the input of the encoder and obtains the deep attribute, and the decoder then transforms the deep attribute to reconstruct the seismic waveforms and attributes. In an S-AE, the network in front of the decoder is shared, while the networks after the decoder consist of independent layers. Such a network structure ensures the effect of reconstruction and associates seismic attributes with the extracted deep attribute, so as to achieve the purpose of attribute fusion and deep attribute extraction. The proposed S-AE method is compared with conventional seismic data fusion methods, such as RGB and principal component analysis, and the superiority of the S-AE is demonstrated in both synthetic and field applications.

Accurate picking of first arrival time plays a critical role in event localization and further data processing in microseismic(MS) monitoring. A large amount of data from receivers make effective automatic time picking method an urgent issue. In this letter, we proposed an adaptive automated time picking approach based on fuzzy c-means (FCM) clustering algorithm. First, by applying FCM, data points are assigned to two clusters with certain membership degrees: signal cluster and noise cluster. Then the vector describing data points to signal cluster center is extracted from the membership degree matrix. Second, considering the shortcoming of a preset threshold, correlation coefficient based adaptive selection algorithm is performed to obtain an optimal threshold for MS event picking. Finally, tests on the synthesis and real data illustrate that our approach outperforms the short-term and long-term average ratio (SLTA) and Akaike information criterion (AIC), and it is more robust than the traditional FCM-based picking method.

Joint monitoring is more potent than conventional micro-seismic(MS) monitoring in understanding underground processes. With simultaneous observations from the surface and downhole, joint monitoring has shown its advantages in disaster early-warning in tunneling and mining, station deployment. However, in Sichuan Basin, China, due to the complex environment, it is intuitively more difficult to transport, install, and maintain stations on the surface. Thus, we have developed a new joint monitoring system for real-time and long-term MS observations based on novel self-developed stations. First, we developed a novel lightweight wireless MS sensor with flexible support of power supply from the battery, solar power, even alternating current for surface monitoring. Second, we also developed a wired station powered by the electricity network in the downhole for underground observation. Finally, a case study in a coal mine located in Sichuan Basin was undertaken. The result illustrates advantages of our joint monitoring system in deployment, real- and long-time joint observation.

The Virtual Reality (VR) user interface style allows natural hand and body motions to manipulate virtual objects in 3D envu-onments using one or more 3D input devices.This style is best suited to application areas where traditional two-dimensional styles fall short, such as scientific visualization, architectural visualization, and remote manipulation.Currently, the programming effort required to produce a VR application is too large, and many pitfalls must be avoided in the creation of successful VR programs.In this article we describe the Decoupled Simulation Model reality

The Virtual Reality user interface style allows the user to manipulate virtual objects in a 3D environment using 3D input devices. This style is best suited to application areas where traditional two dimensional styles fall short, but the current programming effort required to produce a VR application is somewhat large. We have built a toolkit called MR, which facilitates the development of VR applications. The toolkit provides support for distributed computing, head-mounted displays, room geometry, performance monitoring, hand input devices, and sound feedback. In this paper, the architecture of the toolkit is outlined, the programmer's view is described, and two simple applications are described.

The Polhemus Isotrak is often used as an orientation and position tracking device in virtual reality environments. When it is used to dynamically determine the user's viewpoint and line of sight ( e.g. in the case of a head mounted display) the noise and delay in its measurement data causes temporal-spatial distortion, perceived by the user as jittering of images and lag between head movement and visual feedback. To tackle this problem, we first examined the major cause of the distortion, and found that the lag felt by the user is mainly due to the delay in orientation data, and the jittering of images is caused mostly by the noise in position data. Based on these observations, a predictive Kalman filter was designed to compensate for the delay in orientation data, and an anisotropic low pass filter was devised to reduce the noise in position data. The effectiveness and limitations of both approaches were then studied, and the results shown to be satisfactory. 1 Introduction In recen...