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:
Systems and methods for modeling subsurface rock formations based on well log data are provided. Systems include a downhole tool for acquiring data from which borehole dips may be picked and a processor including machine-readable instructions for curvature analysis based on inputs generated from the picked borehole dips data and which may be independent of 2D cross section model orientation. Methods (which may be incorporated in the machine-readable instructions corresponding to the systems) include pre-processing borehole dips data to generate inputs such as true stratigraphic thickness index, Local Constant Dips, borehole structural dip, and attributes for structural dip projections which may be used in a curvature analysis process for generating curvature logs such as standard, curvature along axis and curvature normal to axis logs from for smoothed dips, short zone structural dips and/or long zone structural dips.
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:
Systems and methods for modeling subsurface rock formations based on well log data are provided. Systems include a downhole tool for acquiring data from which borehole dips may be picked and a processor including machine-readable instructions for curvature analysis based on inputs generated from the picked borehole dips data and which may be independent of 2D cross section model orientation. Methods (which may be incorporated in the machine-readable instructions corresponding to the systems) include pre-processing borehole dips data to generate inputs such as true stratigraphic thickness index, Local Constant Dips, borehole structural dip, and attributes for structural dip projections which may be used in a curvature analysis process for generating curvature logs such as standard, curvature along axis and curvature normal to axis logs from for smoothed dips, short zone structural dips and/or long zone structural dips.