A method, apparatus, and program product utilize a disentangled factor learning framework to analyze petro-technical image data such as seismic image data to infer properties of a subsurface volume and/or to generate image data for use in training machine learning algorithms for use in petro-technical applications.

Methods, computing systems, and computer-readable media for interpreting seismic data, of which the method includes receiving seismic data representing a subterranean volume, and determining a feature-likelihood attribute of at least a portion of a section of the seismic data. The feature-likelihood attribute comprises a value for elements of the section, the value being based on a likelihood that the element represents part of a subterranean feature. The method also includes identifying contours of the subterranean feature based in part on the feature-likelihood attribute of the section, and determining a polygonal line that approximates the subterranean feature.

Embodiments of the disclosure involve a method comprising a method comprising inputting borehole dip data; determining characteristics of a plurality of dips based on the borehole dip data; applying one or more geological models to the characteristics; and generating one or more geological cross-sections based on geological modeling.

The disclosure provides methods and systems for characterizing depositional features. The methods and systems include accessing data encoding seismic waves as seismic traces reflected from cells at various locations within a particular stratum in response to a seismic source. The cells are classified into multiple non-overlapping groups according to the amplitude values or other seismic attributes of the seismic waves reflected from the various locations within the particular stratum. One or more subgroups of adjacent cells are identified. A subgroup area metric is calculated for each subgroup of cells by combining individual area metrics from adjacent cells in a given subgroup and subsequently assigning the calculated subgroup area metric to each cell of the given subgroup. One or more depositional features within the stratum are characterized based at least in part on the variation map based on the subgroup area metric of each cell.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, to identify geobodies for exploration and production activities. In one aspect, a method includes receiving seismic volume data regarding a geobody, generating an interpretation object by applying a multi-Z interpretation at representative intervals of edge-detected attributes through the seismic volume data, converting Z-value surfaces to points at each of the representative intervals, the Z-value surfaces generated by gridding polygons having been infilled and converted from the interpretation object, applying a mathematical addition or subtraction to generate a body of points representing the geobody by replicating the points at successive intervals, forming a blended 3D property model of the geobody by combining the seismic volume data resampled into a three-dimensional (3D) cellular grid, and enabling exploration activities by employing the seismic attribute analysis of the geobody identified based on the blended 3D property model.

Methods for dolomite mapping using multiscale fracture characterization include using a computer system to receive seismic data for a geographical area. The computer system identifies one or more macroscale fractures located within the geographical area based on a three-dimensional (3D) visualization of the seismic data. The computer system identifies one or more mesoscale fractures located within the geographical area based on a curvature map generated from the seismic data. The computer system identifies one or more microscale fractures located within the geographical area based on an amount of chaotic seismic reflections indicated by the seismic data. The computer system identifies a dolomite distribution of the geographical area based on the one or more macroscale fractures, the one or more mesoscale fractures, and the one or more microscale fractures. A display device of the computer system generates a graphical representation of the dolomite distribution.

A method for determining a favorable time window of an infill well of an unconventional oil and gas reservoir, which comprises the following steps: S1, establishing a three-dimensional geological model with physical properties and geomechanical parameters; S2, establishing a natural fracture network model in combination with indoor core-logging-seismic monitoring; S3, calculating complex fractures in hydraulic fracturing of parent wells; S4, establishing an unconventional oil and gas reservoir model and calculating a current pore pressure field; S5, establishing a dynamic geomechanical model and calculating a dynamic geostress field; S6, calculating complex fractures in horizontal fractures of the infill well in different production times of the parent wells based on pre-stage complex fractures and the current geostress field; S7, analyzing a microseismic event barrier region and its dynamic changes in infill well fracturing; and S8, analyzing the productivity in different infill times, and determining an infill time window.

A computer-implemented method is described for automated seismic interpretation that includes receiving, at one or more processors, a pre-stack seismic dataset representative of the subsurface volume of interest; performing, via the one or more processors, a machine learning algorithm on the pre-stack seismic dataset to identify seismic facies based on AVA clusters, wherein the identified seismic facies include cluster sequences in depth for a plurality of spatial x-y locations in the subsurface volume; performing, via the one or more processors, seismic interpretation of the seismic dataset based on the identified seismic facies to generate a digital image of the seismic interpretation; and displaying the digital image of the seismic interpretation on a user interface.

The present disclosure describes methods and systems, including computer-implemented methods, computer program products, and computer systems, for generating a velocity model for a subsurface structure. One computer-implemented method for determining velocity model for a subsurface structure includes generating, by at least one hardware processor, a first velocity model for the subsurface structure by performing a refraction traveltime tomography procedure based on an initial velocity model; and generating, by the at least one hardware processor, a first refined velocity model based on the first velocity model and a structure skeleton model, wherein the structure skeleton model is determined based on reflection seismic data of the subsurface structure.

A method is described for seismic imaging including image enhancement using a trained neural network. The neural network may receive training pairs of low signal-to-noise ratio 3D seismic images and high signal-to-noise ratio 3D seismic images; train a neural network on the training pairs wherein the training uses atrous convolution; receive a seismic image representative of a subsurface volume of interest; apply the neural network to the seismic image to generate a second seismic image; and display the second seismic image on a graphical user interface. The method is executed by a computer system.