ARAMCO SERVICES COMPANY

In some examples, a system includes a stress field assessment engine, implemented by at least one processor, to determine stress distribution and yield state data based on a geomechanical model, and a natural fracture determination engine, implemented by the at least one processor, to generate a natural fracture network model based on the stress distribution and yield state data. The system may implement a method that includes generating a geomechanical model of a subsurface formation, where the geomechanical model includes a formation model and a wellbore model, simulating the geomechanical model to determine stress distributions and yield states in the subsurface formation, and generating a natural fracture network model using a machine learning technique on the stress distributions and yield states.

A method involves obtaining a measured drainage function for a well and obtaining a set of drainage models, wherein each drainage model includes a reservoir model and a fracture model. The method also includes, for each drainage model, forming a predicted drainage function based, at least in part, on the drainage model, and determining a misfit value based, at least in part, on the predicted drainage function and the measured drainage function. The method further includes determining a set of candidate drainage models based, at least in part, on the misfit value for each drainage model, wherein each candidate drainage model comprises a candidate reservoir model and a candidate fracture model.

Systems and methods for automated first arrival picking are disclosed. The method includes obtaining a seismic dataset composed of a plurality of seismic gathers and determining a pilot for each gather, where the pilot includes a position on an ordinate axis for each seismic trace representing a first arrival. The method continues iteratively until a stopping criterion is met by creating a preconditioned gather using the pilot, determining a differential pilot using global path tracing subject to a constraint and incrementing the pilot using the differential pilot to create a total picked first arrival. Once the stopping criterion has been met, the method further includes determining a final picked first arrival based on the total picked first arrival, determining a seismic velocity model from the final picked first arrival using a tomographic inversion and creating a seismic image using the seismic velocity model and the seismic dataset.

A method and system for determining an uncorrupted NMR response from a sample at a predetermined measurement pressure is provided. The method includes obtaining a sample and a filler fluid with a negligible NMR response, determining a volume of filler fluid based on a dimension of the sample and an interior volume of a pressure cell, injecting the volume of filler fluid at a first temperature into the pressure cell and then changing the temperature of the volume of the filler fluid to a second temperature. The method also includes inserting the sample into the volume of filler fluid within the pressure cell, displacing an upper surface of filler fluid to a predetermined level within the interior volume of the pressure cell. The method still further includes establishing the predetermined measurement pressure within the pressure cell and determining the uncorrupted NMR response from the sample at the predetermined measurement pressure.

A method which includes obtaining an initial velocity model and perturbing the initial velocity model to form a first plurality of velocity models. The method includes using a forward model to simulate seismic data sets from the first plurality of velocity models and transforming the seismic data sets to the wavenumber-time domain. The method includes training a machine-learned model using the first plurality of velocity models and the transformed seismic data sets, wherein the machine-learned model is configured to accept transformed seismic data. The method includes obtaining a second seismic data set for a subsurface region of interest, wherein the second seismic data set is acquired according to a second survey configuration and transforming the second seismic data set to the wavenumber-time domain. The method further includes processing the second transformed data set with the trained machine-learned model to predict a second velocity model for the subsurface region of interest.

A method for mapping fiber optic distributed acoustic sensing (DAS) measurements to particle motion involves obtaining, from a fiber optic DAS system in a wellbore, a first set of DAS data associated with a first seismic wave; obtaining, from a discrete seismic receiver in the wellbore, measured particle motion data associated with the first seismic wave; generating training data from the first set of DAS data and the measured particle motion data; training a machine learning model using the training data; obtaining a second set of DAS data associated with a second seismic wave; and determining a predicted particle motion in response to the second seismic wave using the machine learning model applied to the second set of DAS data.

A method may include obtaining well log data for various wells regarding a geological region of interest. The well log data may correspond to various well logs with different logging types. The method may include assigning, using a grouping algorithm, subsets of the well log data to various groups based on one or more geological attributes. The method may include determining, using the groups and a machine-learning algorithm, various well zones for different portions of a respective well among the wells. The method may include determining interpolated log data using the well log data, the well zones, and an intrawell interpolation process. The method may include generating a formation property volume based on the interpolated log data and the well log data.

A method may include obtaining seismic data for a geological region of interest. The method may further include determining various velocity semblance values for the geological region of interest using a time window and the seismic data. The method may further include determining, automatically by a computer processor, one or more stacking velocities for the geological region of interest using a traced path based on the velocity semblance values and a path tracing algorithm. The path tracing algorithm may recursively determine an accumulated amplitude array based on the velocity semblance values. The path tracing algorithm may further determine the traced path among the velocity semblance values and the accumulated amplitude array, the traced path corresponding to the one or more stacking velocities. The method may further include generating a velocity model of the geological region of interest using the one or more stacking velocities.

A method of predicting three-dimensional fracture geometry in a subterranean region of interest is disclosed. The method includes obtaining a strain tensor for the subterranean region of interest, calculating a set of principal strain components from the strain tensor, and determining a strain cyclide from the set of principal strain components. The method further includes calculating a set of quadrimodal fault normal vectors from the strain cyclide and determining an in-plane shear strain magnitude and a shear strain orientation from the set of quadrimodal fault normal vectors.

A method may include obtaining, using a gamma-ray detector, first acquired gamma-ray data regarding a first core sample. The first acquired gamma-ray data may correspond to various sensor steps. The method may further include determining a sensitivity map based on the first acquired gamma-ray data. The method may further include obtaining, using the gamma-ray detector, second acquired gamma-ray data regarding a second core sample at the sensor steps. The method further includes generating a gamma-ray log using the sensitivity map and a gamma-ray inversion process.