Abstract: A computer-implemented method for generating a three-dimensional (3D) digital model from one or more two-dimensional images is described. The method includes: obtaining, though an application programming interface (API), a series of two-dimensional (2D) images of a scene taken by an image capturing device; extracting, by a processing device, key images from the series of 2D images, wherein each of the key images depicts one or more components of a building structure in the scene; determining, by the processing device, and based on the extracted key images, a respective position and a respective direction of the image capturing device relative to each of the one or more components of the building structure; and processing, using a 3D image generation neural network, the extracted key images and the positions and directions of the image capturing device to generate metadata comprising a three-dimensional (3D) digital model of the building structure.

Abstract: Neural network systems and related machine learning methods for geological modeling are provided that employ an improved generative adversarial network including a generator neural network and a discriminator neural network. The generator neural network is trained to map a combination of a noise vector and a category code vector as input to a simulated image of geological facies. The discriminator neural network is trained to map at least one image of geological facies provided as input to corresponding probability that the at least one image of geological facies provided as input is a training image of geological facies or a simulated image of geological facies produced by the generator neural network.

Abstract: Neural network systems and related machine learning methods for geological modeling are provided that employ an improved generative adversarial network including a generator neural network and a discriminator neural network. The generator neural network is trained to map a combination of a noise vector and a category code vector as input to a simulated image of geological facies. The discriminator neural network is trained to map at least one image of geological facies provided as input to corresponding probability that the at least one image of geological facies provided as input is a training image of geological facies or a simulated image of geological facies produced by the generator neural network.

Abstract: A method (and corresponding system) that characterizes a porous rock sample is provided, which involves subjecting the porous rock sample to an applied experimental pressure where a first fluid that saturates the porous rock sample is displaced by a second fluid, and subsequently applying an NMR pulse sequence to the rock sample, detecting resulting NMR signals, and generating and storing NMR data representative of the detected NMR signals. The application of experimental pressure and NMR measurements can be repeated over varying applied experimental pressure to obtain NMR data associated with varying applied experimental pressure values. The NMR data can be processed using inversion to obtain a probability distribution function of capillary pressure values as a function of NMR property values. The probability distribution function of capillary pressure values as a function of NMR property values can be processed to determine at least one parameter indicative of the porous rock sample.

Abstract: Neural network systems and related machine learning methods for geological modeling are provided that employ an improved generative adversarial network including a generator neural network and a discriminator neural network. The generator neural network is trained to map a combination of a noise vector and a category code vector as input to a simulated image of geological facies. The discriminator neural network is trained to map at least one image of geological facies provided as input to corresponding probability that the at least one image of geological facies provided as input is a training image of geological facies or a simulated image of geological facies produced by the generator neural network.

Abstract: A method (and corresponding system) that characterizes a porous rock sample is provided, which involves subjecting the porous rock sample to an applied experimental pressure where a first fluid that saturates the porous rock sample is displaced by a second fluid, and subsequently applying an NMR pulse sequence to the rock sample, detecting resulting NMR signals, and generating and storing NMR data representative of the detected NMR signals. The application of experimental pressure and NMR measurements can be repeated over varying applied experimental pressure to obtain NMR data associated with varying applied experimental pressure values. The NMR data can be processed using inversion to obtain a probability distribution function of capillary pressure values as a function of NMR property values. The probability distribution function of capillary pressure values as a function of NMR property values can be processed to determine at least one parameter indicative of the porous rock sample.

Abstract: Methods may include normalizing two or more wellbore logs obtained from the output of two or more wellbore tool surveys of a wellbore in a formation of interest; inputting two or more wellbore logs into a correlation matrix; assigning each of the two or more wellbore logs a positive or negative value based on the impact on a selected wellbore quality; performing a principal component analysis of the two or more wellbore logs to obtain one or more loading vectors; computing weighting factors for each of the two or more wellbore logs from the one or more loading vectors; and generating a quality index by linearly combining the two or more wellbore logs using the computed weighting factors.

Abstract: A method, computer program product, and computing system are provided for defining one or more injector completions and one or more producer completions in one or more reservoir models. One or more edges between the one or more injector completions and the one or more producer completions in the one or more reservoir models may be defined. The one or more edges between the one or more injector completions and the one or more producer completions may define a graph network representative of the one or more reservoir models. The one or more reservoir models may be simulated along the one or more edges between the one or more injector completions and the one or more producer completions.

Abstract: Methods may include normalizing two or more wellbore logs obtained from the output of two or more wellbore tool surveys of a wellbore in a formation of interest; inputting two or more wellbore logs into a correlation matrix; assigning each of the two or more wellbore logs a positive or negative value based on the impact on a selected wellbore quality; performing a principal component analysis of the two or more wellbore logs to obtain one or more loading vectors; computing weighting factors for each of the two or more wellbore logs from the one or more loading vectors; and generating a quality index by linearly combining the two or more wellbore logs using the computed weighting factors.

Abstract: Methods of generating structural models of highly deviated or horizontal wells may be generated from the measurement of true stratigraphic thickness in three dimensions (TST3D). In one aspect, methods may include generating a structural model from one or more deviation surveys of a horizontal well, one or more single channel log measurements, and a three-dimensional reference surface.

Abstract: The present disclosure introduces methods and apparatus for acquiring a borehole image corresponding to a sidewall surface of a borehole that penetrates a subterranean formation, wherein the subterranean formation comprises structural elements and a varying geophysical characteristic. The borehole image comprises structure corresponding to the structural elements, texture corresponding to the varying geophysical characteristic, and coverage gaps (605) in which the structure and texture are missing. Trends corresponding to the structure are extracted from the borehole image. Missing structure within the gaps (605) is reconstructed based on the extracted trends. Missing texture within the gaps is simulated based on the borehole image and the reconstructed structure. A fullbore image is constructed based on the borehole image, the reconstructed structure within the gaps, and the simulated texture within the gaps.

Abstract: Methods for characterizing a geological formation, the methods include retrieving measured data provided by a measuring tool along one or more logged borehole length for a borehole, another borehole or both in order to produce a borehole imaging log. Selecting depth-defined intervals of the borehole imaging log as training images for inputting in a multi-point geostatistical model. Determining pattern based simulations for each training image using a pixel-based template of the multi-point geostatistical model so as to obtain training image patterns. Using the pattern based simulation of each training image to assign to each of the training image a corresponding training image pattern. Constructing from the training image patterns one or more fullbore image log of a borehole wall of the borehole. Repeat the second to fourth steps through the one or more logged borehole length in order to construct fullbore images from successive, adjacent training images.

Abstract: The present disclosure introduces methods and apparatus for acquiring a borehole image corresponding to a sidewall surface of a borehole that penetrates a subterranean formation, wherein the subterranean formation comprises structural elements and a varying geophysical characteristic. The borehole image comprises structure corresponding to the structural elements, texture corresponding to the varying geophysical characteristic, and coverage gaps (605) in which the structure and texture are missing. Trends corresponding to the structure are extracted from the borehole image. Missing structure within the gaps (605) is reconstructed based on the extracted trends. Missing texture within the gaps is simulated based on the borehole image and the reconstructed structure. A fullbore image is constructed based on the borehole image, the reconstructed structure within the gaps, and the simulated texture within the gaps.

Abstract: Methods for upscaling digital rock modeling data are described. Core-plug samples for pore-scale modeling are chosen using whole-core mini-permeability grids and conventional CT scans. Pore models or pore-network models are used for flow modeling. Borehole-scale models use MPS (Multi-Point Statistics) to combine mini-permeability grids and conventional CTscans of whole core with electrical borehole images to create 3D numerical pseudocores for each RRT (Reservoir Rock Type). Effective SCAL properties computed from various MPS borehole-scale realizations or models are used to populate interwell-scale models for each RRT. Effective properties computed from flow simulations for interwell volumes are used to populate full-field scale models. At the full-field scale, outcrop analogs, sequence stratigraphy, forward stratigraphic models, diagenetic models, and basin-scale models are combined using MPS to improve flow simulations.

Abstract: Methods of generating structural models of highly deviated or horizontal wells may be generated from the measurement of true stratigraphic thickness in three dimensions (TST3D). In one aspect, methods may include generating a structural model from one or more deviation surveys of a horizontal well, one or more single channel log measurements, and a three-dimensional reference surface.

Abstract: This subject disclosure describes methods to build and/or enhance 3D digital models of porous media by combining high- and low-resolution data to capture large and small pores in single models. High-resolution data includes laser scanning fluorescence microscopy (LSFM), nano computed tomography (CT) scans, and focused ion beam-scanning electron microscopy (FIB-SEM). Low-resolution data includes conventional CT scans, micro computed tomography scans, and synchrotron computed tomography scans.

Abstract: A method for generating one or more geological models for oil field exploration. The method includes receiving one or more well facies logs, a vertical facies proportion curve, a lateral proportion map, a variogram model and a global target histogram. The method then includes generating a facies probability cube using a modified Sequential Gaussian Simulation (SGSIM) algorithm, the well facies logs, the vertical facies proportion curve, the lateral proportion map and the variogram model. After generating the facies probability cube, the method includes matching the facies probability cube to the global histogram and generating the geological models based on the matched facies probability cube.

Abstract: Methods and systems for creating a numerical pseudocore model, comprising: a) obtaining logging data from a reservoir having depth-defined intervals of the reservoir, and processing the logging data into interpretable borehole image data having unidentified borehole image data; b) examining one of the interpretable borehole image data, other processed logging data or both to generate the unidentified borehole image data, processing the generated unidentified borehole image data into the interpretable borehole image data to generate warped fullbore image data; c) collecting one of a core from the reservoir, the logging data or both and generating a digital core data from one of the collected core, the logging data or both such that generated digital core data represents features of one or more depth-defined interval of the reservoir; and d) processing generated digital core data, interpretable borehole image data or the logging data to generate realizations of the numerical pseudocore model.

Abstract: A method for generating one or more geological models for oil field exploration. The method includes receiving one or more well facies logs, a vertical facies proportion curve, a lateral proportion map, a variogram model and a global target histogram. The method then includes generating a facies probability cube using a modified Sequential Gaussian Simulation (SGSIM) algorithm, the well facies logs, the vertical facies proportion curve, the lateral proportion map and the variogram model. After generating the facies probability cube, the method includes matching the facies probability cube to the global histogram and generating the geological models based on the matched facies probability cube.

Abstract: A multipoint geostatistics computer-implemented method for modeling of discrete properties, comprising acquiring by a computer software program a training image made from at least one dimensional array of discrete property values, the values depicting the spatial relationship and variability considered to be typical of a n-dimensional surface to be modeled; constructing a search tree, the tree representing the probability of occurrence of combinations of values of a discrete property value, the construction being performed by counting these occurrences in the training image. The non-branching sequences of the search tree are compressed to what essentially amounts to a single node, by keeping only the relevant information the sequences contain.