A method for generating one or more reservoir models using machine learning is provided. Generating reservoir models is typically a time-intensive idiosyncratic process. However, machine learning may be used to generate one or more reservoir models that characterize the subsurface. The machine learning may use geological data, geological concepts, reservoir stratigraphic configurations, and one or more input geological models in order to generate the one or more reservoir models. As one example, a generative adversarial network (GAN) may be used as the machine learning methodology. The GAN includes two neural networks, including a generative network (which generates candidate reservoir models) and a discriminative network (which evaluates the candidate reservoir models), contest with each other in order to generate the reservoir models.

A method and apparatus for machine learning for use with automated seismic interpretation include: obtaining input data; extracting patches from a pre-extraction dataset based on the input data; transforming data of a pre-transformation dataset based on the input data and geologic domain knowledge and/or geophysical domain knowledge; and generating augmented data from the extracted patches and the transformed data. A method and apparatus for machine learning for use with automated seismic interpretation include: a data input module configured to obtain input data; a patch extraction module configured to extract patches from a pre-extraction dataset that is based on the input data; a data transformation module configured to transform data from a pre-transformation dataset that is based on the input data and geologic domain knowledge and/or geophysical domain knowledge; and a data augmentation module configured to augment data from the extracted patches and the transformed data.

A method and apparatus for automated seismic interpretation (ASI), including: obtaining trained models comprising a geologic scenario from a model repository, wherein the trained models comprise executable code; obtaining test data comprising geophysical data for a subsurface region; and performing an inference on the test data with the trained models to generate a feature probability map representative of subsurface features. A method and apparatus for machine learning, including: an ASI model; a training dataset comprising seismic images and a plurality of data portions; a plurality of memory locations, each comprising a replication of the ASI model and a different data portion of the training dataset; a plurality of data augmentation modules, each identified with one of the plurality of memory locations; a training module configured to receive output from the plurality of data augmentation modules; and a model repository configured to receive updated models from the training module.

A method and apparatus for seismic interpretation including machine learning (ML). A method of training a ML system for seismic interpretation includes: preparing a collection of seismic images as training data; training an interpreter ML model to learn to interpret the training data, wherein: the interpreter ML model comprises a geologic objective function, and the learning is regularized by one or more geologic priors; and training a discriminator ML model to learn the one or more geologic priors from the training data. A method of hydrocarbon management includes: training the ML system for seismic interpretation; obtaining test data comprising a second collection of seismic images; applying the trained ML system to the test data to generate output; and managing hydrocarbons based on the output. A method includes performing an inference on test data with the interpreter and discriminator ML models to generate a feature probability map representative of subsurface features.

A method and system of machine learning-augmented geophysical inversion includes obtaining measured data; obtaining prior subsurface data; (a) partially training a data autoencoder with the measured data to learn a fraction of data space representations and generate a data space encoder; (b) partially training a model autoencoder with the prior subsurface data to learn a fraction of model space representations and generate a model space decoder; (c) forming an augmented forward model with the model space decoder, the data space encoder, and a physics-based forward model; (d) solving an inversion problem with the augmented forward model to generate an inversion solution; and iteratively repeating (a)-(d) until convergence of the inversion solution, wherein, for each iteration: partially training the data and model autoencoders starts with learned weights from an immediately-previous iteration; and solving the inversion problem starts with super parameters from the previous iteration.

Techniques related to improving performance of an automated control system for drilling with a drilling system, comprising directing drilling tools on a drilling rig to drill, a borehole using the automated control system, obtaining, from one or more surface sensors disposed at a surface of the drilling site, surface sensor data relating to surface drilling activity of the drilling system, determining, based on a comparison between the surface sensor data and a set of historical data, a set of drilling parameters associated with a drilling state, applying the set of drilling parameters to a physics model of the drilling site to determine a set of downhole parameters for the drilling site, wherein the physics model comprises a simulation of current conditions of the borehole and a drill string of the drilling rig, and adjusting operation of at least one of the drilling tools based on the set of downhole parameters.

Systems and methods for simulating subterranean regions having multi-scale fracture geometries. Non-intrusive embedded discrete fracture modeling formulations are applied to two-dimensional and three-dimensional unstructured grids, with mixed elements, using an element-based finite-volume method in conjunction with commercial simulators to model subsurface characteristics in regions having complex hydraulic fractures, complex natural fractures, or a combination of both.

A method and apparatus for modeling a subsurface region, including: obtaining a training set of geologically plausible models for the subsurface region; training an autoencoder with the training set; extracting a decoder from the trained autoencoder, wherein the decoder comprises a geologic-model-generating function; using the decoder within a data-fitting objective function to replace output-space variables of the decoder with latent-space variables, wherein a dimensionality of the output-space variables is greater than a dimensionality of the latent-space variables; and performing an inversion by identifying one or more minima of the data-fitting objective function to generate a set of prospective latent-space models for the subsurface region; and using the decoder to convert each of the prospective latent-space models to a respective output-space model. A method and apparatus for making one or more hydrocarbon management decisions based on the estimated uncertainty.

A technique is provided for modeling flow simulations at downhole reservoir conditions and rock formations after performing wellbore perforations. By utilizing these flow simulations, a user may be able to simulate and compare different scenarios, thereby facilitating a more effective, profitable, and realistic choice of perforating systems and operating conditions.

Unstructured grids are automatically constructed in a domain containing complex internal boundaries. Simulation grids are constructed for reservoirs or fields which contain complex fault planes. Reconciling among generated fault grid-points and other reservoir/field grid-points is performed, enabling the use of unconstrained Delaunay triangulation. High-quality orthogonal unstructured grids are provided with good convergence properties for reservoir simulation.