With increasingly complex oil and gas exploration targets, seismic exploration faces challenges such as low signal-to-noise ratio (SNR), low resolution, and difficulties in velocity modeling and imaging of seismic data. Conventional seismic data processing and interpretation methods have certain limitations in accuracy or efficiency when applied to massive seismic data. The artificial intelligence (AI)-based seismic data processing and interpretation methods can effectively improve accuracy and efficiency. To this end, this paper provides an overview of supervised, semi-supervised, and unsupervised deep learning techniques, and summarizes the applications of deep learning in data processing such as first break picking, SNR improvement, data reconstruction, velocity spectrum interpretation, migration, and resolution enhancement. Meanwhile, it discusses the applications of deep learning in identifying geological bodies such as faults, seismic facies, river channels, and salt domes, as well as in wave impedance inversion, AVO inversion, full waveform inversion, lithology identification, reservoir parameter prediction, and fluid identification. The production of training sets, optimization of neural networks, training strategies, and large models are discussed, with an outlook on the development trend of AI-based processing and interpretation methods for seismic data provided. It is pointed out that the generalization of networks should be continuously increased and large models suitable for seismic exploration should be studied.

The "stamp-like" acquisition method in complex areas results in fragmented three-dimensional seismic data of a zone, with differences in energy, frequency, phase, and time between datasets. This poses challenges to regional seismic interpretation and comprehensive studies. Conventional pre-stack joint processing helps address boundary splicing problems between 3D blocks but the significant disparities in the quality of original data across different blocks prevent full utilization of high-quality data and ultimately reduce imaging precision. In response to the greatly different seismic data in complex areas, this paper proposes a technical scheme of block and joint seismic data processing based on key parameters of the zone. This method preserves the advantages of native bin processing for individual blocks while possessing the advantages of joint data for facilitating comprehensive studies. Meanwhile, it resolves the problems in conventional joint processing of a large number of existing 3D data, such as "difficult blending of single-block processing" and "insufficient fineness in joint processing". Case studies from the complex mountainous structural belt in Kuche and the Fuman East area of Tarim Basin demonstrate the effectiveness of this technical method. This method constructs joint data volumes by adopting building blocks, which supports the trap well location and basic geological research and provides useful references for the industrial sector.

Intelligent seismic velocity inversion is currently a hot and challenging topic in seismic exploration research. Nevertheless, the complex structure of deep learning networks demands significant computing power from hardware devices, which restricts the application of the model in scenarios with large data volumes and high timeliness requirements. To address these practical issues, in this paper, the U-Net is improved based on the concepts of feature engineering and model lightweighting, and the inversion networks U-Net vG for GPU and U-Net vC for CPU are proposed. Firstly, the characteristics of the velocity inversion network are analyzed to deduce the lightweighting principles of convolutional neural networks. Subsequently, lightweight processing is conducted on the multi-scale module, attention gate module, and feature extraction module to obtain a lightweight convolutional neural network for velocity modeling, which reduces the network volume while maintaining prediction accuracy. Data test results demonstrate that the training process of the proposed network has lower requirements for high-performance hardware resources, and that the network enables efficient velocity inversion, possesses higher seismic velocity inversion accuracy, and exhibits superior noise resistance. It provides a new idea for solving the computing power bottleneck problem in seismic data inversion.

Time Frequency Electromagnetic (TFEM) Method is an emerging electromagnetic exploration method that developed and emerged in the field of oil and gas exploration at the beginning of this century. It combines the advantages of time-domain and frequency-domain electromagnetic methods and can provide higher resolution and more accurate underground structure imaging and multi electromagnetic parameter constraints under complex geological conditions. TFEM has played an important role in oil and gas exploration and has been promoted to geothermal and metal mineral exploration fields. This article systematically reviews the development history of TFEM technology: from the limitations of early CSAMT methods, to achieving high-precision detection through instrument innovation (such as wideband transmission systems, node based receiving equipment) and intelligent upgrades (5G cloud acquisition, OpenHarmony system); For complex targets, acquisition techniques such as multi-directional synchronous excitation and joint well ground observation have been proposed, and time-frequency data fusion processing and induced polarization effect inversion methods have been developed, effectively improving the success rate of oil and gas detection (reaching over 75%). In terms of application, TFEM has completed over 47000 kilometers of profiles in more than 150 exploration targets worldwide, successfully applied to various types of reservoir targets such as clastic rocks and lithological traps. In the future, TFEM will make breakthroughs in intelligent equipment, AI interpretation, and multi-field coupling inversion, and expand to the fields of semi aviation electromagnetic, marine exploration, and geothermal/environmental monitoring, providing more efficient and accurate technical support for deep earth resource development.

Seismic facies identification is a crucial link in seismic data interpretation. Deep learning technology can enhance the efficiency and accuracy of automatic seismic facies identification. However, deep learning methods typically rely on large amounts of labeled data, and in practical applications, the labeling cost of seismic data is high, with great difficulty. Additionally, basic logging data cannot be directly utilized. To this end, this paper proposes a semi-supervised automatic seismic facies identification method based on ultra-sparse logging labels. First, based on the HRNet, a seismic facies identification model that uses one-dimensional logging labels is built for for supervision. Second, to preserve the vertical characteristics of seismic data, this paper develops a sparse label sampling module (SLSM) that conducts samples around the logging labels without slicing the seismic data vertically, thus retaining its vertical depth features and laying a solid foundation for subsequent semi-supervised learning tasks. Third, in terms of the lateral correlation of seismic data, the region growing training strategy (RGTS) is proposed, which expands the information from logging labels to the entire seismic volume through an iterative growing process. Experiments on real-world data show that the proposed model achieves a mean intersection over union (MIoU) of 79.64% by using only 32 one-dimensional logging labels, which account for less than 0.5% of the total data volume. This approach provides references for conducting seismic facies identification in areas with sparse and locally distributed logging data, demonstrating promising application potential.

The shear wave velocity and thickness of near-surface strata can be obtained through the inversion of Rayleigh wave dispersion curves. However, traditional nonlinear inversion algorithms often have disadvantages such as poor convergence effect and being prone to fall into local extremity. A new improved beluga whale optimization (DWBWO) algorithm is proposed in this paper and applied to the inversion of the Rayleigh surface wave dispersion curve. Based on the beluga whale optimization (BWO) algorithm, this algorithm introduces the Cubic chaotic initialization strategy to improve the uniformity of the initial population. Meanwhile, the dimensional reverse learning strategy is used to improve the convergence efficiency of the algorithm, and the whirlwind foraging strategy (WFS)is adopted to improve the local optimization ability of the algorithm. The DWBWO algorithm is tested by applying the multi-extremum functions, simulated data and measured data, and compared with the grey wolf optimization (GWO) algorithm, sparrow optimization (SSA) algorithm, whale optimization (WOA) algorithm and BWO algorithm. It was proved that the improved algorithm in this paper has higher stability and accuracy.

To address irregular missing seismic data caused by environmental interference during field acquisition, this paper proposes a local learning-based reconstruction method that integrates particle swarm optimization and grey wolf optimizer (HPSOGWO) algorithm with the XGBoost model. The proposed method establishes a nonlinear mapping relationship between seismic trace spatial coordinates (trace number and sampling number) and amplitude values. By adaptively optimizing feature windows using the HPSOGWO algorithm, this method achieves intelligent selection of adjacent trace data and high-precision prediction of missing values. Compared with the traditional convex-set projection method based on the Curvelet transform (Curvelet-POCS), the proposed approach significantly improves reconstruction accuracy in complex structural areas. In contrast to deep learning methods such as U-Net, it reduces the reliance on large training datasets and lowers computational costs. Tests on a three-layer horizontal layered model with 20% random missing traces show that the proposed method achieves a peak signal-to-noise ratio (PSNR) improvement of 11 dB over Curvelet-POCS and 7 dB over U-Net. F-K spectrum analysis further confirms its effectiveness in preserving seismic wavefield characteristics in the frequency domain. Tests on real onshore 2D seismic data show that the reconstructed profile with 20% missing traces achieves a relative amplitude error of 5.72%, demonstrating high amplitude fidelity and phase consistency. The method thus provides an effective and practical solution for seismic data reconstruction under complex geological conditions.

Geophysical logging plays a crucial role in detecting fluid types in subsurface oil and gas reservoirs and evaluating reservoir parameters. Traditional log interpretation methods face significant challenges. Artificial intelligence (AI) algorithms offer advanced capabilities and high accuracy, which makes them highly advantageous for log interpretation. The integration of "logging + AI" has emerged as a new research direction. However, in intelligent log interpretation, the limited sample size and weak generalization ability of training models hinder the widespread application of purely machine learning-based log interpretation methods. Physical models inherently capture the underlying mechanisms that connect logging data to geological targets. Combining data-driven and mechanism-driven approaches provides an effective way to enhance log interpretation accuracy. However, existing joint data-mechanism driving lacks a well-defined paradigm. In view of this, the study focuses on the prediction of intelligent log interpretation parameters, proposes the concept and methodology of joint data-mechanism driving, and presents two key paradigms: data-guided physical modeling, where physical modeling is the primary framework, with data-driven methods assisting in obtaining key steps or parameters, and physics-guided machine learning, where machine learning is the primary approach, while knowledge models or physical mechanisms provide supervision and constraints on input data, loss functions, and training processes. To implement these paradigms, three hybrid models are proposed: physics-augmented datasets, knowledge-driven sample weighting, and rock physics knowledge transfer. These approaches are applied to predict reservoir parameters and mineral composition in tight sandstone and organic shale reservoirs. Compared with purely data-driven machine learning models, the proposed data-mechanism jointly driving paradigms significantly improve the ability of the log interpretation model to learn from small and low-quality samples and make the model have enhanced robustness, generalization ability, and interpretation accuracy.

The gravity anomaly inversion, which infers the density distribution of subsurface anomalies from surface gravity data, is an essential tool in geophysical exploration and is widely applied in fields such as oilfields, mineral deposits, geological structures, and underground works detection. Traditional gravity inversion methods face challenges of complex computation, low resolution, and dependence on prior information for inversion results. However, deep learning-based gravity anomaly inversion techniques show significant advantages, particularly in terms of improving inversion accuracy and reducing computation time, without the reliance on initial models or prior information. This paper reviews the development and limitations of traditional gravity anomaly forward and inversion methods and summarizes the current research on deep learning-based gravity inversion methods. Meanwhile, it introduces the improvements and innovations of different gravity inversion problems in four respects, including data preparation, network models, network optimization, and network validation. Additionally, the application effect of various gravity inversion methods on the measured data from Vinton Dome in Louisiana, the USA, and the San Nicolás ore deposit in Mexico. The multi-task framework CDUNet yields the most accurate inversion depth values on data of Vinton Dome, while the 3D U-Net++ network obtains clearer and more accurate inversion results on the data of the San Nicolás ore deposit than the U-Net network.

The accurate prediction of tight sandstone reservoir parameters is a key scientific issue and technical challenge in unconventional oil and gas exploration. Traditional prediction methods based on linear or nonlinear regression have limitations in characterizing the complex nonlinear relationship between logging curves and reservoir parameters, leading to insufficient prediction accuracy. This study takes the Chang 6 reservoir in the Tang 157 well area of the Ganguyi Production Plant in Yanchang Oilfield as an example. Based on logging data and core analysis porosity data, multi-source data fusion preprocessing is conducted, and a novel neural network architecture (CNN-Transformer Network) that integrates the core advantages of CNN and Transformer is innovatively proposed. The prediction performance of the CNN-Transformer model is comprehensively compared with that of traditional linear regression (LR), TCN-LSTM, GRU, and ResNet models using RMSE, MAE, and R² metrics. Experimental results show that the prediction accuracy of the CNN-Transformer model reaches 96.7%, significantly outperforming the other comparative models. This model effectively captures the unique complex nonlinear mapping relationship between logging curves and porosity in tight sandstone reservoirs, significantly improving the accuracy of reservoir parameter prediction and providing reliable technical support for the efficient exploration and development decision-making of tight sandstone reservoirs.

Deep-learning-based seismic impedance inversion methods have received wide attention due to their ability to handle nonlinear mapping problems. The conventional deep-learning-based seismic impedance inversion methods have the problem of an overwhelming dependence on labeled data, which results in a decrease in the model's ability to extract local features and poor precision of inversion results when training data is insufficient. To address these issues, a new atrous spatial pyramid pooling and U-Net (ASPP-UNet) based seismic impedance inversion method is proposed. The multi-scale feature extraction ability of U-Net is enhanced by the atrous spatial pyramid pooling operation. Based on this, the training datasets were constructed using seismic data and a small amount of logging data. To verify the effectiveness of the proposed method, we conducted two simulation experiments on the Marmousi2 and SEAM public datasets and compared the results with those of CNN, U-Net, and Attention-UNet under the same experimental conditions. The experimental results show that, under the same experimental conditions, the single-trace impedance inversion produced by the proposed method contains richer high-frequency details, and the inverted impedance profile displays smooth vertical continuity between layers and at fault locations. The inversion results also depend less on labeled data and exhibit the least information loss at positions far from the training wells, which is reflected in the strong lateral continuity between traces in the inverted impedance profile. Compared with the comparison methods, the ASPP-UNet inversion results show the best statistical indicators. To further validate the applicability of the ASPP-UNet method, it was applied to real seismic impedance inversion data from East Sichuan Province. The impedance profile obtained by ASPP-UNet is consistent with the actual geological structure. Compared with the three deep-learning methods mentioned above, the inversion results have the highest accuracy, and the impedance profile error is the smallest.

Conventional post-stack seismic data are usually affected by absorption attenuation, resulting ina lower peak frequency, narrower frequency band, low resolution, and poor inversion prediction effect. Therefore, an improved Q estimation and inverse Q-filtering method is proposed to improve the resolution of seismic data and obtain the fidelity and amplitude-preserving seismic data. Firstly, in Q estimation, given the problem that the extracted wavelet amplitude spectrum deviates from the actual situation due to the thin-layer tuning effect that affects the Q estimation accuracy, the complete ensemble empirical model decomposition with adaptive noise (CEEMDAN) method is introduced, which eliminates the interference of reflection coefficients by decomposing and reconstructing the log amplitude spectrum and thus obtains the wavelet amplitude spectrum that removes the tuning effect. Combined with the centroid frequency shift of the energy spectrum, higher-accuracy Q values are obtained. Then, in terms of inverse Q filtering, the amplitude compensation function of the time-varying gain stabilization factor method is optimized to overcome the density dependence and obtain more stable inverse Q-filtering results. The actual data processing results show that the proposed method can obtain fidelity and amplitude-preserving high-resolution post-stack seismic data, which lays a reliable data foundation for subsequent exploration and development of the study area.

In ocean bottom node (OBN) seismic exploration, significant discrepancies often exist between the actual node positions and the initial surveyed locations due to factors such as ocean currents, tides, topographic variations, and fishing vessel dragging, necessitating secondary positioning. To address this, a high-precision secondary positioning method based on four-quadrant stacking is proposed. Specifically, within a relative coordinate system, shot points are divided into four quadrants according to their azimuth. Linear moveout correction and common receiver point stacking are performed separately for shot points in each quadrant. Subsequently, the displacement of the node from the surveyed position to the actual position is decomposed into two mutually perpendicular components. These two components are determined by analyzing the first arrival time differences from the common receiver points in each quadrant, which thereby enables precise estimation of the node's actual coordinates. Application to field data demonstrates that this method achieves high-precision secondary positioning of nodes. Moreover, the four-quadrant stacking strategy significantly improves the reliability of first arrival picking. Compared with traditional methods, this approach offers higher positioning accuracy and efficiency, showing excellent engineering applicability and promising potential for broader adoption.

Full waveform inversion (FWI) is currently the most accurate velocity field inversion technique. FWI employs gradient-based local optimization algorithms to minimize the error between the forward data and the original data, thereby obtaining an accurate subsurface velocity field. The success of FWI on real data relies on the careful processing of original data and the prudent selection of inversion strategies. This paper discusses and experiments with the parameter control and implementation strategies of FWI, considering the characteristics of marine data, and proposes practical techniques for full waveform inversion of marine data. Specifically, the technology is as follows. ① The fraction frequency noise suppression technology is used for turning waves, which primarily improves the signal-to-noise ratio of low-frequency turning waves while avoiding damage to the effective signal. ② The wavelet adjustment techniques to enhance the accuracy of the initial wavelet are applied, which allows for more precise calculation of the error between forward data and actual data and leads to a more accurate calculation of the velocity update gradient. ③ The first-arrival tomography inversion velocity models for near-seafloor velocity modeling improve the accuracy of the initial velocity field, better avoid cycle skipping, and ensure that the objective function converges towards a more accurate direction and at a faster rate. ④ The offset increment strategy is adopted during FWI iterations, progressively updating the velocity field from shallow to deep, reducing the solution multiplicity of FWI, and ensuring more accurate convergence of the FWI velocity field. This technology has achieved relatively good results in practical marine data projects, obtaining more accurate velocity fields and better depth migration imaging effects.

The typical 3D numerical model and seismic simulation are of great significance for the study of seismic processing and interpretation methods, as they can test and validate the effectiveness of various new technologies and approaches. In the double-complex exploration areas in western China, where both neasurface and subsurface structures present significant complex, there have long been challenges of difficult seismic migration imaging and delineation of structures, making it urgent to build a typical 3D model and forward modeling data that represent the double-complex characteristics of China's foreland basins. By taking the representative double-complex area of the Keshen block in the Kelasu area in western China as an example, this paper combines the typical surface and subsurface geological and geophysical features of foothill areas in the western foreland basins and fully utilizes data of seismic depth migration velocity, acoustic logging, VSP logging, and uphole survey to construct typical numerical models for double-complex exploration zones in western China(BGP-DC²GModels). The BGP-DC²GModels include an acoustic velocity model, an isotropic elastic medium model, TTI/TORT models, and a viscoelastic medium model, typically featuring complex near-surface conditions, complex subsurface structures, a high-speed conglomerate fan body, salt-gypsum formations, detachment layers (coal seams), a Q anomaly, and anisotropy. Based on the BGP-DC²GModels, five sets of high-quality forward modeling data for surface and borehole 3D observation are generated by adopting the spectral-element method, including the isotropic acoustic wave, isotropic elastic wave, isotropic viscoelastic wave, TTI viscoelastic wave, and TORT viscoelastic wave. Additionally, the acoustic reverse time migration and anisotropic reverse time migration results of the data are compared and analyzed, further demonstrating that typical models and numerical simulation data can test and validate the effectiveness of new acquisition, processing, and interpretation methods.

To address the problem of limited generalization ability in traditional models for logging prediction of total organic carbon (TOC) content in the Longmaxi Formation shale reservoirs of the Sichuan Basin, this study systematically evaluates the performance of various deep learning models in both single-well and cross-well prediction tasks and identifies practical models suitable for different scenarios. Based on the acoustic time difference, density, and natural gamma-ray logging data from three wells (well1, well2, and well3) in the Longmaxi Formation, multiple models are constructed, including multiple linear regression (MLR), support vector regression (SVR), convolutional neural network (CNN), bidirectional long short-term memory network (BiLSTM), and hybrid CNN-BiLSTM and CNN-BiLSTM-Attention models. In the single-well prediction experiment, a random split strategy is applied to well1 for modeling and validation. The results show that the CNN model achieves the best performance, with the coefficient of determination (R²) reaching 0.9519 on the prediction set, demonstrating excellent local feature extraction capability and strong resistance to overfitting. To further evaluate model generalization ability, a leave-one-well-out (LOWO) cross-validation strategy is designed for cross-well prediction. The results indicate that the CNN-BiLSTM-Attention model exhibits the strongest generalization performance, achieving the highest R² of 0.9653 on the prediction set, with mean absolute error (MAE) and root mean square error (RMSE) as low as 0.131% and 0.170%, respectively, which significantly outperforms other models. The attention mechanism effectively integrates the local features extracted by CNN with the long-term sequential dependencies captured by BiLSTM, enhancing the model's ability to focus on key information and adapt to inter-well variations. This study verifies the effectiveness and robustness of deep learning models integrated with an attention mechanism for TOC prediction under complex geological conditions, emphasizes the importance of cross-well validation in practical applications, and provides a reliable methodological foundation for shale gas sweet-spot prediction.

Shale gas has become an important strategic alternative field for China's oil and gas resources. Shale is characterized by low porosity and low permeability, and only after going through large-scale volume fracturing can industrial production capacity be obtained. The fine characterization and quantitative characterization of fracture parameters after shale fracturing are the key to fracturing effect evaluation and development parameter optimization. By taking the three-dimensional CT images of shale cores after fracturing as the research object, this paper conducts intelligent fracture extraction based on the deep learning semantic segmentation model. Firstly, a U-Net deep learning model integrating the pyramid convolution and attention mechanism is built to alleviate the influence of image category imbalance and improve fracture extraction accuracy. Secondly, a digital core model is built based on the semantic segmentation results, and quantitative characterization of the spatial distribution of fractures is realized by combining parameters such as the porosity and tilt index. Finally, the complexity of the fracture network is characterized by the peak and width of the multi-fractal spectrum. The research results show that compared with the traditional image segmentation model, the sensitivity of the improved model is increased by 6.69%, and the intersection over union grows by 0.48%. This study systematically characterizes the three-dimensional fracture features by image segmentation algorithm optimization, digital core modeling, and multi-fractal analysis, which is applicable to the characterization of fracture networks in unconventional reservoirs such as shale and can provide a reference for the evaluation of reservoir stimulation effects after hydraulic fracturing.

The reservoir space of the Lower Paleozoic carbonate rocks in the Jiyang Depression is mainly composed of fractures and dissolution pores. The reservoirs are highly heterogeneous both vertically and horizontally, which makes the prediction of the buried hill reservoirs quite challenging. Therefore, based on the development characteristics of the reservoir space and the correlation of seismic reflections, this paper proposes a seismic forward modeling method for the buried hill interior based on the dual-porosity medium model, which characterizes the seismic response features of the Lower Paleozoic buried hill interior. Meanwhile, a buried hill reservoir prediction method based on structure-oriented filtering is developed, achieving effective prediction of the favorable reservoir development zones in the Lower Paleozoic buried hill. The research results show that the development of the Lower Paleozoic carbonate reservoirs in the Jiyang Depression is the main factor causing seismic reflection anomalies, and the effective reservoir sections exhibit obvious seismic response anomalies. By comparing the data residuals before and after structure-oriented filtering, the development positions of the main inner reservoirs can be indicated. This method has achieved good results in the Pingnan buried hill and Dawangzhuang buried hill in the Dongying Sag.

Accurate estimation of coalbed methane (CBM) content plays a crucial role in assessing and efficiently exploiting CBM resources. Deep CBM is influenced by multiple controlling factors and complex genetic mechanisms. Currently, machine-learning approaches for CBM content prediction typically rely on either seismic or logging data. As a result, the complex geological conditions of deep coal seam are not fully accounted for. This study proposes an intelligent prediction method for CBM content, which achieves multi-source data fusion through a multi-scale modeling and deep integration strategy. The approach first extracts multi-scale sensitive attributes or features relevant to CBM content from geological, logging, and seismic sources. For each dataset of the same scale, adaptive modeling is performed using a Bayesian hyperparameter-optimized random forest (RF) algorithm, which enhances model robustness and prevents overfitting. The prediction results from individual scales are subsequently integrated through the least squares method to construct a multi-scale RF composite model. The proposed method is validated using a field dataset and compare its performance with that of conventional approaches, including single-scale RF and linear regression. The results show that, compared with these baseline methods, the proposed method reduces the mean relative error of CBM content prediction on test wells by 3.01% and 4.94%, respectively. This demonstrates that the proposed approach achieves higher accuracy and stronger generalization capability, enabling precise characterization of the spatial distribution of CBM content.

The transparency of geological condition detection and precise exploration are critical challenges hindering safe and efficient coal mining operations. Coalfield seismic exploration technology plays a vital role as a means to address hidden, potentially hazardous geological issues during the mining process. This technology provides high-precision regional geological structures and coal formation patterns, offering reliable geological basis for coalfield development. The evolution of coalfield seismic exploration technology in China can be divided into three distinct phases: the early stage from the 1950s to the early 1970s marked by technological inception; the digital development era spanning the late 1970s through the 1980 s; and the current phase since the 1990 s, characterized by extensive promotion and practical application. Over the course of more than seventy years, this technology has made significant advancements in coalfield geological surveys and the precise detection of hidden factors contributing to geological hazards. It stands as an indispensable geological support for ensuring safe and efficient coal development. By integrating in-depth research on coalfield exploration techniques with typical engineering practices, the text systematically outlines its technical features and current status across the stages of data acquisition, processing, and interpretation. In response to the urgent need for transparent and intelligent mine construction, future developments in coalfield exploration technology will focus on advancing dense distributed data collection, intelligent data processing and interpretation, and the innovative application and development of multi-attribute integration techniques.

Electromagnetic methods are naturally superior in identifying whether deep targets contain fluids. It is of great significance for oil and gas field exploration and development to study high-precision electromagnetic detection technology for reservoir fluids. Based on the capillary model and electrochemical theory, we consider that the polarized electric field is closely related to fluid concentration, microscopic charge migration, and accumulation, and has time and frequency dependencies. The essence of polarization effects can be explained through the electric diffusion hypothesis and thin film polarization theory. Based on Maxwell's equations and the equivalent complex resistivity model, we derive the basic formula for electromagnetic hydrocarbon detection. The accurate characterization of electrical anomalies in oil and gas reservoirs by relevant parameters is further analyzed, especially the performance of induced polarization effects related to oil and gas content in electromagnetic field amplitude and phase curves. In practice, the induced polarization effect can be effectively extracted and the distribution of oil and gas reservoirs can be identified only by optimizing parameters such as transmission and reception distance and frequency. At last, we analyze the characteristics of the induced polarization effect on electromagnetic field phase and differential curves through numerical simulation, which is consistent with theoretical mathematical characterization. We clarify the effective parameters and critical frequency for data acquisition of the induced polarization effect in reservoirs. Finally, we discuss the applicability of this method in fluid detection and propose a construction method technology based on characteristic curves, providing theoretical support for the practical application of electromagnetic hydrocarbon detection.

In recent years, the Keping fault uplift in Tarim Basin has emerged as a significant breakthrough zone for hydrocarbon exploration, where well-developed high-quality source rocks coexist with complex structural settings, creating a unique exploration environment. The combination of intense surface relief, pronounced velocity contrasts from shallow high-velocity rock masses, and multi-phase superimposed fault systems has led to technical bottlenecks in conventional seismic imaging methods, including substantial static correction errors, low velocity modeling accuracy, and structural distortion. This study systematically investigates key pre-stack depth migration (PSDM) technologies tailored for piedmont zones based on geological characteristics of the 3D seismic survey in the Kepingnan area. Three main innovations are presented: ① Integrated shallow layer modeling technology. To address near-offset data deficiencies caused by complex surface acquisition geometries, this paper develops a constrained tomographic inversion algorithm integrating uphole survey data with wide-azimuth seismic information was developed. This approach effectively enhances shallow velocity model accuracy while overcoming velocity-thickness coupling limitations inherent to conventional methods. ② True surface migration datum construction technology. By optimizing surface-consistent static correction schemes and implementing high-frequency static correction time-difference correction, the paper establishes a dynamic matching mechanism between true surface elevation and migration datum was established. This innovation significantly mitigates topographic effects on wavefield continuation and improves structural fidelity in steeply dipping stratigraphic imaging. ③ Multi-scale velocity iterative inversion technology. The paper develops a multi-azimuth grid tomography method incorporating structural constraints. Through azimuth-dependent hierarchical inversion strategies, this technique achieves synergistic improvements in both vertical and lateral velocity resolution, providing precise velocity models for deep nappe structures and buried fault systems. Field applications demonstrate that this technology system substantially enhances imaging quality of depth-migrated seismic data in Kepingnan area. Target horizons exhibit improved signal-to-noise ratios with clearer fault imaging and more accurate structural configurations. The proposed methodology provides an effective technical solution for hydrocarbon exploration in complex piedmont zones, offering practical value for advancing regional exploration progress.

In seismic surveys of complex surfaces such as loess plateau areas, coherent noise greatly reduces the signal-to-noise ratio (SNR) of seismic data, which seriously affects the accuracy of subsequent seismic imaging and physical inversion. To this end, a new coherent noise suppression strategy is proposed in the paper. The method mainly consists of the following core steps. Firstly, anisotropic diffusion filtering is adopted to effectively suppress the incoherent noise components in the data, and initially improve the overall quality of the low SNR data. Next, the dictionary learning method is employed to sparsely characterize the seismic data, and statistical indicators are applied to precisely locate and eliminate the dictionary atoms with a large variance of gradients. These atoms tend to be the main carriers of linear coherent noise and random noise. Then, the dictionary atoms and their corresponding sparse coefficients that can effectively characterize the effective signals are filtered and retained to reconstruct the seismic data. Finally, the effective signals are further extracted from the removed noise through the principle of signal-to-noise local orthogonalization. The simulated data and typical real data tests show that the method ensures the intact preservation of the effective signals while suppressing the coherent and random noises, which further improves the SNR of the data. The method can provide a reference for the treatment of linear coherent noise.

Traditional manual cutting logging faces on-site technical challenges, including inability to quantitatively identify cutting components and accurately name the lithology, thereby hindering the comprehensive and precise acquisition of cutting lithology information. To this end, this paper develops an intelligent lithology identification system based on cutting images collected during the logging-while-drilling process. Firstly, by establishing unified standards for image acquisition and annotation, systematic sample annotation is conducted manually to generate standard samples. Secondly, the deep convolutional neural network algorithm YOLOv5 is adopted for sample training, inference, and post-processing, and an attention mechanism for small target identification is added, with the focus on the influence of Fitness function adjustment on target identification accuracy. Finally, the ONNX(Open Neural Network Exchange) model is adopted for cross-platform support, developing an intelligent lithology identification system based on cutting images. Practical applications show that the system can identify six major lithologies (mudstone, sandstone, limestone, dolomite, coal, and carbonaceous mudstone), with the overall accuracy exceeding 85%. Meanwhile, the system can analyze the component contents of each lithology and characteristics of sandstone cuttings including the roundness, grain size, and sorting, thus enabling the accurate description of cutting component characteristics and developing a new lithology identification technology.

Microseismic monitoring technology is of application significance in fields such as unconventional oil and gas reservoir development and mine disaster monitoring. However, its signals are susceptible to noise interference, which results in a low signal-to-noise ratio (SNR), thus severely compromising the accuracy of subsequent seismic source localization and mechanism inversion. Traditional denoising methods such as the complete ensemble empirical mode decomposition (CEEMD) and wavelet modulus maxima (WMM) have limitations in processing non-stationary microseismic signals. To this end, this paper proposes a microseismic denoising method named SSA-VMD-CC-WT, which combines variational mode decomposition (VMD) optimized by the sparrow search algorithm (SSA) with the adaptive wavelet thresholding (WT). Firstly, SSA is employed to optimize key parameters of the VMD algorithm. Secondly, effective modal components are selected by utilizing the cross-correlation coefficient (CC) to suppress noise. Finally, adaptive WT is applied to perform secondary denoising on the effective components, reducing signal distortion. Simulation tests demonstrate that in strong noise conditions, the SSA-VMD-CC-WT method can separate noise from effective signals more accurately than the CEEMD and WMM methods. The processing of actual microseismic data reveals that the proposed method significantly suppresses both low-frequency and high-frequency noise while maintaining the fidelity of weak seismic sources, thereby improving data interpretability and SNR. Meanwhile, compared with the traditional genetic algorithm (GA), SSA demonstrates higher optimization efficiency.

Sand body are a kind of common reservoir unit, and their accurate identification and tracking are the key to discovering oil and gas fields and supporting the increase in oil and gas reserves and production. Existing methods such as attribute analysis and deep learning still face challenges such as low boundary identification accuracy, complex parameter selection, and poor noise resistance. To this end, this paper proposes a prompt prediction method based on the Segment Anything Model (SAM), a visual image segmentation foundation model. This method requires no model training, and by simply employing the boundary prompt points of target sand bodies, precise identification and tracking results of the boundaries of target sand bodies can be obtained. To address the prediction error of the prompt encoder in SAM when applied to seismic profiles, this paper proposes a KD-tree search method. By calculating the shortest distance from the prompt points to the potential sand body segmentation blocks, the optimal sand body prediction results are determined. After conducting verification with actual target area data and comparison with the customized training of a U-Net model on the target area data, it is demonstrated that the sand body tracking method based on SAM depicts more lateral changes of sand body boundaries and the boundaries are more consistent with seismic amplitude variations.

Seismic wave traveltime information required for geophysical inversion such as source localization and tomographic imaging can be obtained by solving the eikonal equation. Common algorithms for this purpose include the fast marching method (FMM) and the fast sweeping method (FSM). Physics-informed neural network (PINN) is a novel mesh-free method that incorporates the constraints of partial differential equations into the loss function of the neural network, thus embedding physical information into the network. Focusing on optimizing node distribution during training, this study adopts an adaptive sampling strategy based on residual distribution to improve the training performance of PINN and proposes a travel-time calculation method using PINN with adaptive node generation. Application tests on the Marmousi model and an irregular topography model show that, compared with the fixed node-generation method, the proposed approach yields a more stable training process and maintains high accuracy in traveltime calculations.

Shear-wave velocity is a key parameter for pre-stack seismic inversion and reservoir characterization. However, due to the technical and cost constraints of both direct and indirect measurement methods, it is quite difficult to obtain in practice. Therefore, a prediction method is proposed based on the broad learning system (BLS). First, appropriate well-log data are selected and pre-processed through denoising and correlation analysis. Second, a BLS neural network structure comprising mapping nodes and enhancement nodes is constructed to complete the BLS process. Finally, well-log data from the two typical wells Y301 and Y302 in the Y block of the Junggar Basin are used to construct a data set of machine learning. Two contrast experiments are designed and compared with curve fitting and deep learning system to verify the stability and generalization of BLS. The actual results show that the proposed BLS-based shear wave velocity prediction method can reduce training time while achieving prediction accuracy, providing a new neural network option for shear wave velocity, petroleum, and relevant reservoir parameter prediction.

The seismic data of the Lower Cambrian Qiongzhusi Formation in the Sichuan Basin has weak reflected energy without distinct characteristics of interlayer wave groups and clear description of faults, which makes it difficult to meet the requirements for fine prediction of high-quality shale reservoirs and the accurate design of horizontal well trajectories. In response, taking the 3D seismic project for shale gas in Well Z201 as an example, this paper proposes a high-precision seismic acquisition technology of deep shale gas in Qiongzhusi Formation of Sichuan Basin. First, the observation system parameter optimization technology for pre-stack inversion of reservoirs is applied to design the observation system. Then, the intelligent layout of physical points in the obstacle area based on the contribution degree is conducted to improve the uniformity of coverage times in the target zone. Finally, the surface velocity and lithology constrained modeling technology is used to characterize the near-surface structure and spatial distribution of lithology within the survey area. The application results of the proposed method in seismic acquisition of shale gas in Qiongzhusi Formation demonstrate that high-resolution, broadband seismic data can be obtained using the technology, which provides a data basis for the subsequent high-resolution processing and fine reservoir description.

Accurately segmenting pores in scanning electron microscope (SEM) images can provide a scientific basis for oil and gas exploration and development, and more. At present, pore segmentation methods mainly rely on data-driven approaches, requiring a large amount of manual annotation of data, which is time-consuming and costly. To this end, this paper proposes the semi-supervised pore segmentation network PoreSeg for SEM images. Firstly, a semi-supervised framework is constructed based on consistency regularization and pseudo labeling. Secondly, a high-intensity combined perturbation strategy is introduced to enhance data diversity. Finally, combined with the pore aware fusion (Pore-CutMix) method, the sparse pore information is fully utilized to improve the segmentation ability of the model for pores. Experimental results show that under the condition of equal labeled samples, PoreSeg improves the pore intersection over union (IoU) by 15.10% compared with the fully supervised network. At the same time, compared with existing semi-supervised methods, PoreSeg is more sensitive to pores and has higher segmentation accuracy. PoreSeg significantly reduces dependence on annotated data while maintaining high accuracy, and has huge application potential.

Current data transmission technologies face challenges such as high coding complexity, low encryption efficiency, and limited data compression, thus restricting the development of efficient and safe communications. To resolve these problems, this paper proposes an innovative ultra-low-traffic data transmission scheme, the Temporal-base data pulse transmission method. The core of this method is the combination of high-accuracy time synchronization and subdivision technology, and the establishment of the "Temporal-base" theoretical framework. By adopting the accurate time datum as the data coding basis, the information is mapped to the specific pulse time sequence or phase via super large binary representation to achieve pulse transmission of data. This mechanism notably simplifies the traditional coding process and improves the confidentiality (due to accurate synchronization requirements of time pulses) and compression potential (due to efficient pulse coding of information in the time dimension) of data. By carrying out case analysis, this study verifies the advantages of the proposed data transmission method in improving the transmission rate, significantly saving communication bandwidth, and strengthening data confidentiality, thus fully proving the huge application potential and value of this method in future efficient and safe data transmission scenarios.

In seismic exploration, multiples pose a significant issue, particularly in marine exploration. This study developed a method for suppressing interbed multiples based on the inverse scattering series method in the curvelet domain. The curvelet transform (CT), as a multi-scale and multi-directional transformation method, can sparsely represent seismic data, facilitating the capture of the main features of seismic data. By combining CT with the inverse scattering series method, the seismic data was first converted to the curvelet domain using CT. Then, the interbed multiples were predicted in the curvelet domain through the inverse scattering series method. This approach did not require building a model of the subsurface medium, offering high applicability and practicality. Furthermore, CT can sparsely represent seismic data, reducing the computational load of the inverse scattering series method. By performing an inverse CT on the predicted multiples, they were reconstructed in the time-space domain and subtracted from the original seismic data, ultimately obtaining the effective signal with suppressed multiples. The numerical experiments demonstrate that this method not only significantly improves computational efficiency but also reduces memory consumption while ensuring accuracy. This study provides an innovative approach for suppressing multiples in seismic data processing and is expected to play an important role in practical seismic exploration.

In gas-water two-phase flow, phase stratification and the non-uniform distribution of gas and water within the wellbore often lead to significant measurement errors when using conventional instruments under varying flow regimes and phase separation conditions. To overcome these limitations, a modular combination of multiphase flow sensors, such as the Capacitance Array Tool (CAT), Resistance Array Tool (RAT), Spinner Array Tool (SAT), and Gas Array Tool (GAT), can be flexibly configured to enhance the adaptability and efficiency of well logging systems. In particular, the GAT employs optical sensors to perform repeated measurements under various flow conditions, effectively improving measurement robustness and resolution. This study evaluates the gas holdup measurement performance of GAT and RAT under different flow rates and water cut conditions. An inverse distance weighting (IDW) algorithm is applied to interpolate the measured gas holdup distribution for visualization. Experimental results demonstrate that GAT outperforms RAT regarding imaging quality, measurement accuracy, and adaptability under low-to-moderate water cut and high flow rate conditions, providing valuable insights for interpreting gas-water two-phase production profiles in horizontal wells.

Accurate prediction of geological sweet spots is a core component for the efficient exploration and development of shale oil and gas. Intelligent prediction of sweet spots of shale oil and gas based on logging data holds significant importance for hydrocarbon development. Within the field of sweet spot prediction, traditional model-based prediction methods suffer from limitations such as weak generalization, insufficient feature representation, and cumulative error propagation. This study integrates novel deep learning frameworks with the aim of achieving accurate prediction of geological sweet spots using logging data. Porosity (POR) and total organic carbon (TOC) are key parameters defining geological sweet spots. This study establishes deep learning models between logging curves and these two critical parameters to achieve intelligent prediction of geological sweet spot parameters. Firstly, a convolutional neural network (CNN) model is constructed. By analyzing and comparing different combinations of input logging curves and varying CNN layer architectures, the model achieves high-precision predictions for both POR and TOC on the test set, with correlation coefficients exceeding 0.96. Secondly, innovatively fusing CNN with an attention mechanism, a composite Transformer architecture termed the CNN-Transformer compound (CTNet) model is proposed. This model possesses the dual capability of capturing local lithological features and global inter-layer dependencies. After validation and testing on the dataset, the CTNet model achieves a correlation coefficient above 0.91 on the test set. Experimental results indicate that the CNN model demonstrates higher overall prediction accuracy than the CTNet model. However, the CTNet model exhibits significantly superior prediction accuracy within limestone intervals compared to the CNN model (e.g., in the limestone section of well GY6-1, the correlation coefficient of the CTNet model and the CNN model is 0.848 and 0.300, respectively), showcasing its unique potential for addressing prediction challenges in complex heterogeneous reservoirs. The findings demonstrate that both the proposed CNN and CTNet deep learning mo-dels can effectively achieve high-precision prediction of key geological sweet spot parameters in shale oil and gas, offering new methodologies for intelligent exploration.

Accurate underground velocity information is crucial for seismic imaging in complex area. While existing seismic waveform inversion techniques are highly accurate, they have shortcomings such as high computational amount and reliance on initial models. Currently, deep learning technology experiences rapid advancements in various fields and has successfully been applied to nonlinear seismic inversion. However, conventional end-to-end deep learning networks struggle to establish a multi-scale physical coupling relationship between velocity parameters and seismic records. To this end, this paper proposes a hybrid network AER-UNet, which reorganizes the encode and decoder structures and adds an attention mechanism-based jumping connection module on this basis. This approach effectively obtains key spatial information from seismic records and enhances the representation of the subtle structures in velocity fields, thus accurately capturing the characteristics of underground medium velocity parameters. An appropriate number of random velocity models should be built in the network training phase to simulate the true structure of the underground medium and thus obtain the accurate mapping relationship between velocity models and seismic records. Additionally, developing new loss functions can help improve the computational accuracy of velocity modeling. By carrying out numerical experiments using the SEG/EAGE thrust model, the effectiveness of the hybrid network for velocity modeling is evaluated. Compared to FWI and other deep learning networks, this method can more efficiently and accurately rebuild underground velocity models.

Due to the high and steep underground structure in the limestone outcropping area of the eastern Sichuan Basin, the conventional geometry has some problems, such as uneven illumination and insufficient partial illumination energy.For the high and steep structure of the eastern Sichuan Basin with high-precision seismic ima-ging, seismic illumination analysis is an important method to guide the optimized design of seismic acquisition geometry in the region. By combining the surface and underground geological conditions in limestone outcropping areas of the eastern Sichuan Basin, this paper establishes the demonstration technology and process of geometry encryption based on seismic illumination analysis.By conducting the design and demonstration of geometry encryption of the underlying structure in the limestone outcropping areas, the seismic illumination energy of the local shadow area of the geological target is effectively improved. Firstly, the surface encryption range is determined by adopting the 2D forward model for reverse illumination analysis, and then by employing the 3D geological model for forward illumination modeling analysis combined with the actual seismic data analysis, the acquisition geometry encryption scheme suitable for the limestone outcropping area in eastern Sichuan Basin is obtained. The technological implementation and application show that adding receiving lines at the top of the structure can effectively improve the seismic imaging effect of the high and steep complex structure area in the east Sichuan Basin, and a technically effective and economically feasible encryption scheme for the geometry can be obtained.

Diffraction imaging is an important method to improve the imaging accuracy of underground small-scale geologic bodies. However, conventional seismic surveys are mainly based on reflection imaging, with weak-energy diffraction suppressed, as a result of which diffraction need to be separated and imaged separately. At present, the localized damped rank-reduction with adaptively chosen ranks (LDRRA) method widely used improves the separation accuracy of diffraction by damping the adaptively chosen singular value matrix with a damping operator, but its damping factor is mainly given manually, and all local window data use the same given damping factor. Different local windows contain different seismic data, and using the same damping factor will reduce the separation accuracy of diffraction. Therefore, a localized adaptive damped rank-reduction (LADRR) method for diffraction separation is proposed. First, based on the LDRRA framework, the Hankel matrix undergoes singular value decomposition (SVD) to truncate singular values. Second, a squared ratio of singular value is introduced to adaptively compute a damping factor for each localized data window, through which the optimal damping factor is selected to apply damping effects to the truncated singular values, thereby preserving the reflection components. Finally, the damped localized window data is subjected to inverse Hankelization and inverse Fourier transform, and then subtracted from the original wavefield to yield the separated diffraction. Theoretical simulation and field data test results demonstrate that the proposed method can separate diffraction with high accuracy, and the imaging results of the separated diffraction can get more accurate location of the underground small-scale geologic body.

In response to high-resolution imaging in complex geological structures, surface imaging and vertical seismic profile (VSP) imaging mitigate illumination limitations inherent to either method alone, but are still subject to unbalanced image amplitude and structural distortion due to uneven illumination. To address this issue, a joint VSP-surface Gaussian beam depth migration method is proposed. First, a dynamic complementary mechanism is established for the surface and borehole wavefields, where illumination-based weighting factors are applied to balance their respective contributions and integrate their advantages. Second, to constrain the Gaussian beam propagation paths, a structural dip field is introduced, enabling dynamic adjustment of the initial beam direction for adaptive alignment with the local formation dip. Third, a dip-dependent weighting function is employed during the imaging stack to suppress scattering energy from non-geological directions, thereby enhancing the signal-to-noise ratio of the joint VSP-surface image. Applications to both synthetic and field data demonstrate that the joint VSP-surface Gaussian beam depth migration method produces superior images compared to those obtained using surface data alone and improves the imaging accuracy of complex structure.