A method for generating an image of a subsurface based on blended seismic data includes receiving the blended seismic data, which is recorded so that plural traces have uncontaminated parts with different uncontaminated recording time lengths, selecting plural subgroups (SG1, SG2) of traces so that each subgroup (SG1) includes only uncontaminated parts that have a same uncontaminated recording time length, processing the traces from each subgroup to generate processed traces, mapping the processed traces to a same sampling, combining the processed traces from the plural subgroups (SG1, SG2) to generate combined processed traces, and generating an image of a structure of the subsurface based on the combined processed traces.

A method may include obtaining fracture image data regarding a geological region of interest. The method may further include determining various fractures in the fracture image data using a first artificial neural network and a pixel-searching process. The method may further include determining a fracture model using the fractures, a second artificial neural network, and borehole image data. The method may further include determining various fracture permeability values using the fracture model and a third artificial neural network. The method may further include determining various matrix permeability values for the geological region of interest using core sample data. The method may further include generating a coarsened grid model for the geological region of interest using a fourth artificial neural network, the matrix permeability values, and the fracture permeability values.

A full probability-based seismic risk analysis method for a tunnel under fault dislocation comprises: evaluating a magnitude-frequency relationship of a fault; obtaining a probabilistic seismic risk curve of a fault dislocation; calculating a series of bending moments of a tunnel lining under different fault dislocations; obtaining a series of damage index values R.sub.M of the tunnel; obtaining a vulnerability model of the tunnel damaged by fault dislocation; calculating a probabilistic risk that the tunnel crossing the fault is damaged due to the dislocation of the active fault; obtaining a probability P that the damage state is equal to or higher than a certain damage state within a specified period; and using the results to guide the assessment of the seismic risk of the tunnel crossing the fault. Modeling and analysis can be performed according to the actual situation of the tunnel crossing the fault with different factors.

Methods and systems described herein are directed to determining properties of a subterranean formation using an acoustic wave-equation with a novel formulation in terms of a velocity model and a reflectivity model of the subterranean formation. The acoustic wave equation may be used with full-waveform inversion to build high-resolution velocity and reflectivity models of a subterranean formation. The acoustic wave equation may be also used with least-squares reverse time migration in the image and space domains, to build a reflectivity model of the subterranean formation with enhanced resolution and amplitude fidelity. The velocity and reflectivity models of materials that form the subterranean formation reveal the structure and lithology of features of the subterranean formation and may reveal the presence of oil and natural gas reservoirs.

The present disclosure provides a method and a system for high-resolution seismic fault detection by means of an adversarial neural network, including following steps of: training a target adversarial neural network based on a preset training sample set, so as to obtain a trained target adversarial neural network, wherein the preset training sample set includes seismic data and fault labels, the target adversarial neural network includes: a segmentation module, a feature fusion module, and a discriminator module, the segmentation module is a module configured for obtaining a fault feature based on the preset training sample set, and the feature fusion module is a module configured for fusing the fault feature and the seismic data into a global feature map; and performing seismic fault detection on a target seismic image based on the trained target adversarial neural network.

The present disclosure relates to the field of geophysical processing methods for oil and gas exploration, and more particularly, to a method for gas detection using multiple quantum neural networks. A plurality of stratigraphic and structural seismic attributes are extracted from the seismic data of a target horizon, and input seismic characteristic parameters are divided into different classes by using an unsupervised learning and supervised learning combined quantum self-organizing feature map network. Gas detection is then performed using a particle swarm optimization based quantum gate node neural network with clustering results of various seismic characteristic parameters output by the quantum self-organizing feature map network as inputs. The present method uses the unsupervised learning and supervised learning combined quantum self-organizing feature map network for a plurality of stratigraphic and structural seismic attributes of the seismic data and thus has improved accuracy and uniqueness of clustering.

Disclosed are a multi-scale photoacoustic detection method of geological structure around a borehole and related devices. The method includes: obtaining depth information and direction information of the borehole; generating trajectory data of the borehole according to the depth information and direction information; obtaining an optical image of the geological structure around the borehole; generating a first velocity model according to the optical image and the trajectory data; obtaining low-frequency acoustic wave data and high-frequency acoustic wave data of the geological structure around the borehole; performing a full waveform inversion on the first velocity model according to the low-frequency acoustic wave data and the high-frequency acoustic wave data to obtain a second velocity model; and determining the geological structure around the borehole according to the second velocity model.

The disclosed technology is generally directed to carbon capture and storage. In one example of the technology, a first neural network is trained with synthetic data that is associated with seismic images of synthetic simulated subsurfaces. The first neural network extracts features from multiple resolutions of the seismic images of the synthetic simulated subsurfaces. The ground truth includes synthetic labels that indicate probabilities of potential carbon dioxide leakage pathways of the synthetic simulated subsurfaces. A seismic image of a first subsurface is received. At least the trained first neutral network is used to generate output labels that indicate probabilities of potential leakage pathways of carbon dioxide storage of the first subsurface.

Systems and methods are discussed to image lithological data within the strata beneath the earth surface, including a subterranean object detection system. The system may further comprise a pipeline operable to conduct a working fluid and an instrumented pig operable to travel within the pipeline and operable to image lithological strata and voids within the strata beneath and around the pipeline. The instrumented pig may comprise an outer case, a battery coupled to the outer case, a ground imaging unit operable to send a signal to image the lithological strata and voids within the strata beneath and around the pipeline and may be operable to receive a reflected signal indicating lithology data, wherein the ground imaging unit may be operably coupled to the battery.

A method for generating a geophysical image of a subsurface region includes defining a computational sub-volume for the geophysical image including a predetermined number of seismic traces of a plurality of seismic traces and a predetermined number of samples per each one of the plurality of seismic traces, generating a data matrix corresponding to a first sub-volume of the subsurface region based on the defined computational sub-volume, the data matrix comprising the predetermined number of samples for the predetermined number of traces of a portion of a seismic dataset corresponding to the first sub-volume. The method also includes estimating a coherence between the predetermined number of traces of the data matrix by performing a sum of a variance of the predetermined number of samples of the data matrix, and assigning the estimated coherence to a location in the geophysical image.