A method may include obtaining, by a computer processor, seismic data regarding a geological region of interest. The method may further include obtaining, by the computer processor, well log data from a wellbore within the geological region of interest. The method may further include determining, by the computer processor, a formation top depth using the seismic data, the well log data, a stratigraphic column, and a machine-learning model. The stratigraphic column may describe an order of various formations within the geological region of interest. The machine-learning model may assign a feature among the seismic data and the well log data to a formation among the formations in the stratigraphic column to determine the formation top depth.

Methods and apparatus for generating one or more reservoir 3D models are provided. In one or more embodiments, a method can include training a first machine learning model to generate one or more integrated enhanced logs based, at least in part, on an integrated data set, wherein the integrated data set includes seismic data and well log data; generating one or more integrated enhanced logs from the first machine learning model; grouping the one or more integrated enhanced logs into an ensemble of integrated enhanced logs to form a static reservoir 3D model of a subterranean reservoir; inputting additional data to the first machine learning model to produce one or more updated integrated enhanced logs; and grouping the one or more updated integrated enhanced logs into an ensemble of updated integrated enhanced logs to form an updated 3D model.

A method for building a three dimensional (3D) model of a subsurface formation includes selecting, from a set of seismic shots, a plurality of first arrival signals representing the seismic shots. The method includes applying a quality control function to the plurality of first arrival signals to obtain a set of remaining first arrival signals. For each remaining first arrival signals, the method includes applying a velocity inversion function to obtain a depth velocity value at a common-midpoint (CMP) location in a shot gather including the seismic shot associated with that remaining first arrival signal, the CMP location representing a lateral variation of the shot gather including that seismic shot. The method includes, based on the depth velocity value for the seismic shot associated with each remaining first arrival signal, generating a velocity model representing the 3D model of the subsurface formation.

A system and method is provided for restoring a 3D tomographic model of the Earth's subsurface geology from the present-day to a past restoration time. Whereas at the present time all faults represent active discontinuities, at a past restoration time some faults have not yet formed. Accordingly, the restored model divides the fault network into τ-active faults (discontinuous surfaces for faults that intersect the layer deposited at the past restoration time) and τ-inactive faults (continuous surfaces for faults that do not intersect the layer deposited at the past restoration time). A new 3D restoration transformation is also provided that uses linear geological constraints to process the restoration model in less time and generate more accurate geological images.

Systems, methods, and computer-readable medium for generating a three-dimensional fracture network model are provided. The method can include receiving reflected acoustic signal measurements acquired in response to emission of acoustic waves by one or more sensors disposed in a wellbore formed within a target region. Each reflected acoustic signal measurement represents a strength of a reflected acoustic wave as a function of time measured in at least one predetermined direction oriented with respect to an axis of the wellbore. A fracture extension estimate is generated for each of the reflected acoustic signal measurements. A three-dimensional fracture network model is generated corresponding to the fracture extension estimates generated for each of the plurality of reflected acoustic measurements. The generated fracture network model is output for display or use in modeling environments.

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.

Methods for dolomite mapping using multiscale fracture characterization include using a computer system to receive seismic data for a geographical area. The computer system identifies one or more macroscale fractures located within the geographical area based on a three-dimensional (3D) visualization of the seismic data. The computer system identifies one or more mesoscale fractures located within the geographical area based on a curvature map generated from the seismic data. The computer system identifies one or more microscale fractures located within the geographical area based on an amount of chaotic seismic reflections indicated by the seismic data. The computer system identifies a dolomite distribution of the geographical area based on the one or more macroscale fractures, the one or more mesoscale fractures, and the one or more microscale fractures. A display device of the computer system generates a graphical representation of the dolomite distribution.

Methods of oil and gas exploration that may include: obtaining wavefield data representing recordings from a propagating wavefield through a geophysical volume; obtaining at least one reference digital image of a portion or all of the geophysical volume generated from the recorded wavefield data, wherein the reference image may have a reference sampling ratio and a reference image quality value; selecting a holographic computational method of imaging the wavefield data; selecting a data subset from the wavefield data based on one or more parameters selected from the group consisting of field sampling, imaging sampling, and image quality; decimating the data subset, wherein the decimated data subset may represent a sampling ratio less than the reference sampling ratio; and generating a new digital image based on the selected holographic computational method of imaging, the data subset, and parameters corresponding to the data sub set.

A fault indicator calculator, a method for determining a fault indicator, and a fault indicator calculating system are disclosed herein. One embodiment of a fault indicator calculator includes: 1) an interface configured to receive seismic data, and 2) a processor configured to scan a manifold-shaped operator through said seismic data at a range of dips and azimuths and calculate fault throws at various orientations of said dips and azimuths independent of determining other fault indicators.

A method to automatically interpret a subsurface feature within geophysical data, the method including: storing, in a computer memory, geophysical data obtained from a survey of a subsurface region; and extracting, with a computer, a feature probability volume by processing the geophysical data with one or more fully convolutional neural networks, which are trained to relate the geophysical data to at least one subsurface feature, wherein the extracting includes fusing together outputs of the one or more fully convolutional neural networks.