A process for seismic imaging of a subterranean geological formation includes generating a source wavefield from seismic data representing a subterranean formation. The process includes generating a receiver wavefield from the seismic data representing the subterranean formation. The process includes decomposing the source wavefield to extract a source depth component and decomposing the receiver wavefield to extract a receiver depth component. The process includes applying a transform to each of the source depth component and the receiver depth component. The process includes combining the source depth component and the receiver depth component to generate an imaging condition. The process includes extracting a low-frequency term from the imaging condition to generate a wave-path tracking data, generating a wave path from the wave-path tracking data, and rendering a seismic image of at least a portion of the subterranean geological formation from the generated wave path.

Systems and methods develop a three-dimensional model of a subterranean formation based on vertical seismic profiles at a plurality of well locations. This approach can include receiving seismic data for the subterranean formation including the vertical seismic profiles; for each vertical seismic profile, injecting a ground force into the vertical seismic profile to provide a reference trace at depth zero to estimate energy loss in each receiver providing data in the vertical seismic profile and estimating time and depth variant quality factors for the well location associated with the vertical seismic profile based on the seismic profile; estimating quality factors for points within a three-dimensional volume representing the subterranean formation by interpolating between the time and depth variant quality factors for the location associated with each vertical seismic profile; and combining estimated quality factors to generate a three-dimensional quality factor model of the three-dimensional volume representing the subterranean formation.

Tops of geological layers can be automatically identified using machine-learning techniques as described herein. In one example, a system can receive well log records associated with wellbores drilled through geological layers. The system can generate well clusters by applying a clustering process to the well log records. The system can then obtain a respective set of training data associated with a well cluster, train a machine-learning model based on the respective set of training data, select a target well-log record associated with a target wellbore of the well cluster, and provide the target well-log record as input to the trained machine-learning model. Based on an output from the trained machine-learning model, the system can determine the geological tops of the geological layers in a region surrounding the target wellbore. The system may then transmit an electronic signal indicating the geological tops of the geological layers associated with the target wellbore.

A method including obtaining, by a computer processor, at least one key log in each of a set of training wells located, at least partially, within a hydrocarbon reservoir, identifying a target formation bounding surface in each of the set of training wells, and generating an initial depth surface for the target formation bounding surface from the target formation bounding surface in each of the set of training wells. The method further including, determining from the initial depth surface an initial depth estimate of the target formation bounding surface at a location of a current well, forming an objective function based, at least in part on a correlation between each key log in each of the set of training wells, and each corresponding key log in the current well, and optimizing the objective function by varying a depth shift between each of the set of training wells and the current well, to determine an optimum depth shift that produces an extremum of the objective function. The method still further including combining the initial depth estimate of the target formation bounding surface at the location of the current well with the optimum depth shift to produce a final depth estimate of the target formation bounding surface at the location of the current well.

A method for estimating a thickness of a deep reservoir may include obtaining seismic data relating to the deep reservoir. The method may include performing spectral decomposition to obtain one or more frequency components from the seismic data. The method may include identifying a number of mono-frequency horizons corresponding to high frequencies in the seismic data, determining whether the deep reservoir is a thin reservoir based on the number of mono-frequency horizons, and estimating the thickness of the deep reservoir when the deep reservoir is determined to be the thin reservoir.

Systems and methods for automatically tracking multi-Z horizons within seismic volumes are provided. Seed data for each of a plurality of surfaces of a multi-Z horizon within a seismic volume are obtained. A data hull for each surface is generated based on the obtained seed data. A tracking region within the seismic volume is determined, based on the generated data hull. Each surface of the multi-Z horizon is automatically tracked through the tracking region. Upon determining that one or more of the plurality of surfaces violate at least one geological boundary rule associated with the plurality of surfaces, truncating the one or more surfaces such that each surface of the multi-Z horizon honors the geological boundary rule within the seismic volume.

A method can include receiving a first trained machine model trained via unsupervised learning using unlabeled seismic image data; receiving labeled seismic image data acquired via an interactive interpretation process; and building a second trained machine model, as initialized from the first trained machine model, via supervised learning using the received labels, where the second trained machine model predicts stratigraphy of a geologic region from seismic image data of the geologic region.

A method includes receiving a training selection of a first set of faults located in a first subset of a seismic dataset for a subsurface geologic formation, detecting a second set of faults in the seismic dataset based on fault interpretation operations using a first set of interpretation parameters, and determining a difference between the first set of faults and the second set of faults. The method also includes generating a second set of interpretation parameters for the fault interpretation operations based on the difference between the first set of faults and the second set of faults, and determining a feature of the subsurface geologic formation based on fault interpretation operations using the second set of interpretation parameters.

A method for includes obtaining a well log comprising a sequence of measurements of a wellbore in a field, and generating change points in the well log based on the sequence of measurements. Each of the change points corresponds to a depth along the wellbore where a probability distribution of the well log changes. The method further includes generating a statistic for each of multiple intervals in the well log, where the intervals are defined by the plurality of change points, categorizing the intervals based on the statistic for each of the intervals to generate categorized intervals, and performing the operation based on the categorized intervals.

The present disclosure describes methods and systems for interpreting geological features in a seismic volume based on mono-frequency filtering of the seismic volume. One computer-implemented method includes receiving a seismic data volume, decomposing the seismic data volume into multiple sub-volumes, generating one or more seismic horizons on each sub-volume, analyzing the generated seismic horizons for the multiple sub-volumes including determining a first sub-volume and a second sub-volume from the multiple sub-volumes, and subtracting the generated one or more seismic horizons for the first sub-volume from the generated one or more seismic horizons for the second sub-volume.