Abstract: Embodiments of the present disclosure are directed towards systems and methods for automated stratigraphy interpretation from borehole images. Embodiments may include constructing, using at least one processor, a training set of synthetic images corresponding to a borehole, wherein the training set includes one or more of synthetic images, real images, and modified images. Embodiments may further include automatically classifying, using the at least one processor, the training set into one or more individual sedimentary geometries using one or machine learning techniques. Embodiments may also include automatically classifying, using the at least one processor, the training set into one or more priors for depositional environments.

Abstract: Process for interpreting one or more borehole images for use in drilling operations. In some embodiments, the process can include providing an input borehole image obtained from a downhole measurement provided by one or more downhole sensors. The process can also include collecting contextual information relative to the borehole image and the user. The process can also include using the collected contextual information and a mathematical model to infer one or more processing arguments. The mathematical model can be defined by using previously collected arguments and previously collected contextual information. The process can also include processing the input borehole image with the one or more inferred processing arguments to generate one or more interpreted borehole images. The process can also include adjusting one or more drilling operation based, at least in part, on the one or more interpreted borehole images.

Abstract: Embodiments of the present disclosure are directed towards systems and methods for automated stratigraphy interpretation from borehole images. Embodiments may include constructing, using at least one processor, a training set of synthetic images corresponding to a borehole, wherein the training set includes one or more of synthetic images, real images, and modified images. Embodiments may further include automatically classifying, using the at least one processor, the training set into one or more individual sedimentary geometries using one or machine learning techniques. Embodiments may also include automatically classifying, using the at least one processor, the training set into one or more priors for depositional environments.

Abstract: The disclosure relates to methods and systems for analyzing an image of the formation intersected by a borehole. One of the methods determines a local apparent dip of the borehole at least at a measured depth i represented on the image, applies at least a window to the image, wherein each of the windows includes one of the measured depth i and is shaped as a function of the determined local dip at the corresponding measured depth i, compares a texture of at least a first zone of each window and a texture of at least a second zone of said window, wherein each of the first and second zones are adjacent and shaped as a function of the determined dip. Based on the comparison, the method determines at least a location of a texture boundary and derives a property of the formation. The other method includes determine locations of the texture boundaries, segmenting the image as a function of the texture boundaries, and perform clustering of the segments in order to determine a facies of the formation.

Abstract: Systems and methods for estimating surface of fracture per volume of rock are provided. The systems include a logging tool, such as a resistivity tool, for generating a borehole image representative of segments of fractures in one or more planes and a processor for estimating surface of fracture per volume of rock (P32) from the segments without the need for defining the one or more planes bearing the segments. The methods include using a downhole logging tool, such as a resistivity tool, to collect data corresponding to segments of fractures in one or more planes, and estimating surface of fracture per volume of rock (P32) by reconstructing theoretical elliptical fractures from the segment data, calculating length of fracture segment per surface of borehole (P21) for the theoretical elliptical fractures, and deriving P32 from P21.

Abstract: 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.

Abstract: In one embodiment, a method includes obtaining a borehole image deriving from a downhole tool in a wellbore of a geological formation, identifying one or more patches that correspond to sediment particles on the fullbore image, computing one or more characteristics for each of the one or more patches. The one or more characteristics may include long/short axis length, size, roundness, sphericity, orientation, or some combination thereof. The method may also include displaying a visual representation for each of the one or more characteristics.

Abstract: The disclosure relates to methods and systems for analyzing an image of the formation intersected by a borehole. One of the methods determines a local apparent dip of the borehole at least at a measured depth i represented on the image, applies at least a window to the image, wherein each of the windows includes one of the measured depth i and is shaped as a function of the determined local dip at the corresponding measured depth i, compares a texture of at least a first zone of each window and a texture of at least a second zone of said window, wherein each of the first and second zones are adjacent and shaped as a function of the determined dip. Based on the comparison, the method determines at least a location of a texture boundary and derives a property of the formation. The other method includes determine locations of the texture boundaries, segmenting the image as a function of the texture boundaries, and perform clustering of the segments in order to determine a facies of the formation.

Abstract: Generating a virtual core includes obtaining acquired data for a region of interest, determining a rock type of the region of interest, obtaining a selection of modules based on the rock type, and generating, using the acquired data and an interpolator from the modules, a wellbore image of the region of interest. The interpolator generates interpolated data between data points among the acquired data in the wellbore image. Further, using a quantifier from the plurality of modules, a core characterization of the region of interest is determined. The core characterization describes an integration of wellbore data types. Using the core characterization and the wellbore image, a digital core construction of the region of interest is generated. The digital core construction describes subterranean formation properties of the region of interest.

Abstract: Apparatus and methods for use with borehole image data to: delineate a dip and/or a fracture from the borehole image data; create a gap-filled image from the borehole image data; extract a fracture segment from the borehole image data; determine matrix information from the borehole image data; delineate a heterogeneity from the borehole image data; and analyze image porosity. The image porosity analysis is based on: the dip and/or fracture delineated from the borehole image data; the gap-filled image created from the borehole image data; the fracture segment extracted from the borehole image data; the matrix information determined from the borehole image data; and the heterogeneity delineated from the borehole image data.

Abstract: 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.

Abstract: In one embodiment, a method includes obtaining a borehole image deriving from a downhole tool in a wellbore of a geological formation, identifying one or more patches that correspond to sediment particles on the fullbore image, computing one or more characteristics for each of the one or more patches. The one or more characteristics may include long/short axis length, size, roundness, sphericity, orientation, or some combination thereof. The method may also include displaying a visual representation for each of the one or more characteristics.

Abstract: Apparatus and methods for use with borehole image data to: delineate a dip and/or a fracture from the borehole image data; create a gap-filled image from the borehole image data; extract a fracture segment from the borehole image data; determine matrix information from the borehole image data; delineate a heterogeneity from the borehole image data; and analyze image porosity. The image porosity analysis is based on: the dip and/or fracture delineated from the borehole image data; the gap-filled image created from the borehole image data; the fracture segment extracted from the borehole image data; the matrix information determined from the borehole image data; and the heterogeneity delineated from the borehole image data.

Abstract: Systems and methods for estimating surface of fracture per volume of rock are provided. The systems include a logging tool, such as a resistivity tool, for generating a borehole image representative of segments of fractures in one or more planes and a processor for estimating surface of fracture per volume of rock (P32) from the segments without the need for defining the one or more planes bearing the segments. The methods include using a downhole logging tool, such as a resistivity tool, to collect data corresponding to segments of fractures in one or more planes, and estimating surface of fracture per volume of rock (P32) by reconstructing theoretical elliptical fractures from the segment data, calculating length of fracture segment per surface of borehole (P21) for the theoretical elliptical fractures, and deriving P32 from P21.