Accurately picking the first arrivals of acoustic logging curves (e.g., P-, S- and Stoneley waves) is crucial for stratigraphic lithology characterization. The conventional interpreter-dominated first arrivals identification methods frequently lead to an interpretation uncertainty and time burden. To reduce these deficiencies, we developed a dual attention PhaseNet (DA-PhaseNet) network to intelligently identify the first arrivals of acoustic logging curves. The field data test demonstrates that the DA-PhaseNet network can dramatically improve the result accuracy and its generality compared to other PhaseNet-based methods. Specifically, the DA-PhaseNet strategy can capture both local and global features of input logging curves simultaneously, resulting in a high identification accuracy of 99.4% and 94.5% for P- and S-wave respectively. Moreover, the proposed DA-PhaseNet network dramatically improves the accuracy of first arrival identification from 72.3% to 87.6% for the noise-contaminated Stoneley wave. Furthermore, it is important to mention that the DA-PhaseNet has a maximum noise tolerance of 0 dB for P- and Stoneley waves to ensure accuracy of first arrival identification, while has a maximum noise tolerance level of 10 dB for S-wave if the result F1 score limit is set at a level of > 0.8.

Accurate classification and characterization of pore-crack structures are substantial to carbonate reservoirs in terms of reservoir exploration and development. Although experience-dominated manually classifying pore-crack structures achieves a milestone, these methods usually encounter significant uncertainties and heavily rely on the interpreter’s experience. Nevertheless, as a classification problem, using the 2D image input dataset, instead of 1D logging data, could achieve a higher accuracy. Consequently, we developed a Swin Transformer-Convolutional Neural Network (SWT-CNN) hybrid network to capture multi-level features of the pore-crack structure simultaneously using 2D resistivity imaging logging images as an input, thereby eliminating the uncertainty of manual interpretation and enabling automatic feature extraction. Furthermore, to fully utilize rare and valuable dataset, the proposed SWT-CNN model incorporates the data augmentation strategy which has been modified to fit the dataset. Also, the idea of transfer learning is introduced to improve the accuracy of pore-crack types classification in carbonate rock and accelerate convergence. Lastly, the field validation data test shows that the proposed SWT-CNN can achieve an accuracy rate of 95.92%. Moreover, the visualization of the feature map indicates the proposed SWT-CNN is more accurate in recognizing the position of pore-crack structures.

Traditional optimization algorithms are usually applied to estimate the elastic parameters of the subsurface by using field seismic data. However, these optimization algorithms highly depend on prior knowledge (e.g., the initial model setup and sparsity), leading to serious inversion uncertainties. Nowadays, with the rapid development of neural networks, convolutional neural networks (CNNs) have been widely imposed on estimating elastic parameters from field data. However, the deficiency of labeled seismic data impedes the CNNs application in seismic inversion. Moreover, both the size and diversity of labeled datasets are also critical factors influencing the accuracy and resolution of predicted parameters when using the CNNs-based inversion techniques. In this work, taking the unconventional tight sandstone formation as an example, we develop a geological and geophysical model driven CNNs (GGCNNs), named as GGCNNs. The proposed GGCNNs allow us to take advantage of both the prior geological information and basic geophysical model from the generated synthetic labeled prestack seismic datasets, representing essential characteristics of the subsurface. Moreover, under the consideration of data diversity, the GGCNNs model enables us to make a tradeoff between the inversion accuracy and labeled data size. Applications on both synthetic and field data clearly demonstrate the effectiveness of the proposed GGCNNs model for predicting elastic parameters by using prestack seismic data, i.e., its predicted results are with high accuracy in the vertical profile and continuity and smooth in the horizon slice.

Accurate estimation of petrophysical properties (e.g., porosity, clay volume) of subsurface rock from seismic data/elastic properties is significant to reservoir characterization. Conventional model-driven inversion strategies for estimating petrophysical parameters confront with the deficiency of prior knowledge. In contrast, machine learning-based approaches are adapted to account for reservoir parameter estimation through developing nonlinear mapping and quantifying uncertainty. However, most of the current researches mainly concentrates on the single parameter prediction with different neural network architectures, which, in turn, conflicts with the truth of coupling multiple reservoir properties. To quantify the sensitivity of input-output parameters and the effects of network architecture on the accuracy of petrophysical parameter inversion, we propose a CNN-based network strategy to estimate multiple reservoir parameters simultaneously. The results from both synthetic labeled data and field data and uncertainty analysis strongly demonstrate that SopenCNN, abbreviated from multiple input and single output openCNN, exhibits the highest prediction accuracy, while the cycleCNN with multiple input and multiple output, referred to as McycleCNN, is superior to the MopenCNN, which means that an openCNN contains multiple input and multiple output. It means that, for similar network architecture, the number of input and output parameters makes a significant impact on prediction accuracy. Moreover, for similar multiple inputs and outputs, the fine-tuning McycleCNN, parallelly updated in each intermediate closed-loop step, behaves much better accordingly. The application of the three workflows with varying architecture on field tight sandstone reservoirs demonstrates that network based inversion strategy could establish a mapping function to characterize spatially varying reservoir parameters.

Lithology classification in well logging plays a significant role in evaluating the quality of oil and gas reservoirs. Conventionally, the manual interpretation method is of much more limited use, partly because it is time-consuming, but mainly because it is subjective. This is due primarily to the massive volume of logging data and the dependence of the experience of geophysical practitioners. By considering the features that logging data are typically sequential and long short-term memory (LSTM) network is well-suited to process a sequential signal, an LSTM-based architecture is proposed to identify rock facies based on borehole data automatically in the study area. The tests based on data from one well of the tight gas sandstone reservoir demonstrate that, when the sample size and the number of hidden layer neurons are appropriately set, the trained LSTM-based Adam optimizer can precisely recognize the rock facies boundaries than that based on Sgdm and Rmsprop optimizers. Additionally, results on another eight wells in the same study area statistically show a good generalization of the trained LSTM. Moreover, another complex reservoir with similar lithology interbedding also demonstrates the usefulness of the LSTM-based network.

To better describe features of nonstationary seismic signals, mode decomposition-based approaches are widely used for seismic processing and analysis, such as empirical mode decomposition (EMD) and empirical wavelet transform (EWT). EWT builds an adaptive filter bank and then decomposes a nonstationary seismic trace into several intrinsic mode functions (IMFs), which has been applied for analyzing the nonstationary seismic signal. In this letter, we propose an enhanced EWT (EEWT) using Hankel transform (HT), which is an integral transform whose kernels are Bessel functions. Compared with sinusoidal functions of Fourier transform (FT), Bessel functions are more effective for describing features of nonstationary signals. Moreover, HT obtains a more compact spectrum than FT for wideband and nonstationary signal analysis, which contributes to the detection of spectral segmentation. To demonstrate the effectiveness of the proposed algorithm, we apply it to both synthetic and field data. Compared with the results provided by EWT, EEWT provides a time-frequency spectrum with higher resolution and offers potentials in precisely highlighting reservoirs.