A method of fluid substitution, wherein an initial data set is provided, wherein a substituted data set is provided, wherein a rock physics model is provided, wherein the initial data set includes initial data of a geophysical parameter and initial fluid data, and wherein the substituted data set includes substituted fluid data. The method includes using the model and the initial data set to calculate first calculated data of the geophysical parameter, using the model and the substituted data set to calculate second calculated data of the geophysical parameter, calculating the difference between the first calculated data of the geophysical parameter and the second calculated data of the geophysical parameter, and applying the difference to the initial data of the geophysical parameter to produce substituted data of the geophysical parameter.

A system, method and program product for processing borehole images to delineate between natural fractures and induced fractures. A system is disclosed that includes: an image analysis platform that inputs a noisy image from a borehole, processes the image using a set of filtering strategies, and renders a set of suggested filtered images via a user interface, the user interface including a mechanism for allowing a user to choose a selected filtered image from the set of suggested filtered images that best delineates between natural fractures and induced fractures, and wherein the image analysis platform further includes a feedback system for packaging and outputting the noisy image and selected filtered image as feedback; and a learning platform having a knowledge registration system that collects and stores training data and the feedback and in a knowledgebase, and a machine learning system that generates filtering strategies.

An exemplary method of analyzing a well log includes imaging a well log to form a well log image, performing pattern recognition on the well log image to determine pattern data, and determining stratigraphic structure data based on the pattern data. Another exemplary method of improving production from a stratigraphic structure includes performing pattern recognition on a well log image stored in an image format to determine pattern data, determining stratigraphic structure data using a computer-based structure analyzer based on the pattern data, and projecting well parameters based on the stratigraphic structure data. An exemplary system includes a scanner to scan a raster image of a printed well log and a computational system in communication with the scanner to receive the raster image. The computational system includes a pattern recognition analyzer to determine pattern data from the raster image and a structure analyzer to determine stratigraphic structure based on the pattern data.

A method and apparatus for generating an image of a subsurface region including obtaining geophysical data/properties for the subsurface region; resampling the geophysical data/properties to generate a resampled data set; iteratively (a) inverting the resampled data set with an initial prior model to generate a new model; and (b) updating the new model based on learned information to generate an updated prior model; substituting the initial prior model in each iteration with the updated prior model from an immediately-preceding iteration; and determining an end point for the iteration. A final updated model may thereby be obtained, which may be used in managing hydrocarbons. Inversion may be based upon linear physics for the first one or more iterations, while subsequent iterations may be based upon non-linear physics.

A method and apparatus for generating a fluid saturation model for a subsurface region. One example method generally includes obtaining a model of the subsurface region; for each of a plurality of fluid types: flooding the subsurface region model with the fluid type to generate a flood model; and running a trial petrophysical inversion with the flood model to generate a trial petrophysical model; identifying potential fluid contact regions in the trial petrophysical models; partitioning the subsurface region model at the identified potential fluid contact regions; and constructing the fluid saturation model from the partitioned subsurface region model.

A method and apparatus for hydrocarbon management, including generating a fluid saturation model for a subsurface region. Generating such a model may include: performing a brine flood petrophysical inversion to generate inversion results; iteratively repeating: classifying rock types (including at least one artificial rock type) based on the inversion results; generating a trial fluid saturation model based on the classified rock types; performing a trial petrophysical inversion with the trial fluid saturation model to generate trial results; and updating the inversion results with the trial results; and generating the fluid saturation model for the subsurface region based on the inversion results. The petrophysical inversion may include a facies-based inversion and/or may invert for water saturation. Generating such a model may include: performing a brine flood petrophysical inversion, performing a hydrocarbon flood petrophysical inversion; identifying misfits in the inversion results, and generating a trial fluid saturation model based on the misfits.

A method of performing quality control on a subsurface model of a subterranean region includes providing a plurality of types of data relating to subsurface characteristics in the subsurface model outside of one or more wellbores in the region, the plurality of types of data including wellbore data obtained from one or more measurement instruments located within at least one of the one or more wellbores, performing an analysis on the data to determine if there is an error or errors in the data; if an error is detected, searching for the cause of the error; if the cause of the error is detected, correcting the error; if the cause of the error is not detected, either ignoring the data containing the error or including in the model the data containing the error and allocating to the data containing the error an increased prior uncertainty thus reducing the influence on the model of the data containing the error.

A method can include selecting a type of geophysical data; selecting a type of algorithm; generating synthetic geophysical data based at least in part on the algorithm; training a deep learning framework based at least in part on the synthetic geophysical data to generate a trained deep learning framework; receiving acquired geophysical data for a geologic environment; implementing the trained deep learning framework to generate interpretation results for the acquired geophysical data; and outputting the interpretation results.

A system and method for performing a test procedure on a system under test are provided. An actuation unit operatively coupled to the system under test is configured to perform at least one operation thereon. A visual recognition unit is configured to capture at least one image of the system under test in real-time. A test unit remotely interfaced with the system under test is configured to perform the test procedure. Using the test unit, the test procedure is retrieved from the memory, at least one control signal is output to the actuation unit for causing the at least one operation to be performed in real-time for testing the system under test in accordance with the one or more test instructions, and the at least one image of the system under test is monitored as the at least one operation is performed for validating the test procedure in real-time.

A process for the determining of sweet spot intervals based on a combination of rock quality, an in-situ stress regime, natural fractures, and the identification of fluid flow paths from the interaction of hydraulic fracturing and formation attributes. The process may include determining geological components, determining mechanical earth model outputs, and determining sweet spot intervals using additional data from fracture calibration tests. Systems and computer-readable media for the determining of sweet spot intervals are also provided.