A method for interpreting seismic data includes receiving seismic data that represents a subterranean volume, and generating inline probability values and crossline probability values using a first machine learning technique. The first machine learning technique is trained to identify one or more vertical fault lines in a seismic volume based on the seismic data. The method includes generating a merged data set by combining the inline probability values and the crossline probability values, training a second machine learning technique based on a subset of labeled horizontal planes from the merged data set, the second machine learning technique trained to identify horizontal fault lines from the seismic volume, and generating a representation of the seismic volume based on the second machine learning technique, the representation including an indication of a three-dimensional fault structure within the seismic volume.

Methods of identifying a subterranean tunnel using digital imaging that may include: obtaining data of a propagating wavefield through a propagating volume that includes a portion of the earth's subsurface; obtaining a reference digital image of the propagating volume; selecting a holographic computational method of wavefield imaging; selecting a wavefield based on one or more parameters; calculating a sampling ratio by dividing a number of data samples in the data subset by a number of image samples in the data subset; decimating the data subset; generating a new digital image based on the selected holographic computational method of imaging, the decimated data subset, and parameters corresponding to the data subset; determining a quantitative difference measure between the reference digital image and the new digital image, and image quality; and identifying the subterranean tunnel.

A method is described for assessing subsurface structure uncertainty based on at least one subsurface horizon. The method calculates seismic continuity attributes to determine a mappability of the subsurface horizon(s); determines horizontal uncertainty for each fault in vertical uncertainty for each horizon; generates probabilistic scenarios for a subsurface geometry for at least one conceptual model; and generates a map of geological model uncertainty based on the probabilistic scenarios. In some embodiments, the probabilistic scenarios are stochastic simulations. In some embodiments, generating a map of geological model uncertainty is based on information entropy. The method may be executed by a computer system.

Systems and methods for geochemical sampling grid locations on a seafloor. At least one of the methods includes generating, using received seismic data, an image representing an interpretation of a seafloor horizon surface; extracting, from the image and based on the seismic data, one or more discontinuity attributes of the seafloor horizon surface; extracting, from the image and based on the seismic data, one or more amplitude attributes of a window extending below the seafloor horizon surface; combining the one or more discontinuity attributes and the one or more amplitude attributes; and selecting, using the image and based at least partly on the combining, one or more locations of the seafloor horizon surface for sampling.

A method (1310) for attributing a systems tract to a geological environment, including computing (1314) a shelf break for a geologic environment based at least in part on implicit function values associated with the geologic environment; identifying (1318) sea level variations with respect to geological time for the shelf break; and assigning (1322) at least one systems tract to the geologic environment based at least in part on the sea level variations.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for echo-deblending using coincidence-filtering of offshore seismic data. In one aspect, a method includes receiving an offshore seismic dataset of a surveyed subsurface, the offshore seismic dataset comprising a primary-wave signal and a ghost-wave signal; determining a forward extrapolation and a backward extrapolation for the offshore seismic dataset; determining a coincident signal by applying a coincidence filtering to the forward extrapolation and the backward extrapolation; extrapolating the coincident signal to determine a ghost-wave value for the ghost-wave signal; applying adaptive subtraction to the offshore seismic dataset with the ghost-wave value to determine a computed primary-wave value for the primary-wave signal; generating a model of the surveyed subsurface based on primary-wave data calculated from the offshore seismic dataset based on the computed primary-wave value; and evaluating a productivity of the surveyed subsurface according to the model.

A fracture mapping system for use in hydraulic fracturing operations utilizing non-directionally sensitive fiber optic cable, based on distributed acoustic sensing, deployed in an observation well to detect microseismic events and to determine microseismic event locations in 3D space during the hydraulic fracturing operation. The system may include a weighted probability density function to improve the resolution of the microseismic event on the fiber optic cable.

A subsurface structure identification system includes one or more processors and a memory coupled to the one or more processors. The memory is encoded with instructions that when executed by the one or more processors cause the one or more processors to provide a convolutional neural network trained to identify a subsurface structure in an input migrated seismic volume, and to partition the input migrated seismic volume into multi-dimensional sub-volumes of seismic data. The instructions also cause the one or more processors to process each of the multi-dimensional sub-volumes of seismic data in the convolutional neural network, and identify the subsurface structure in the input migrated seismic volume based on a probability map of the input migrated seismic volume generated by the convolutional neural network.

A system can determine a location for future wells using machine-learning techniques. The system can receive seismic data about a subterranean formation and may determine a set of seismic attributes from the seismic data. The system can block the set of seismic attributes into a set of blocked seismic attributes by distributing the set of seismic attributes onto a geo-cellular grid representative of the subterranean formation. The system can apply a trained machine-learning model to the set of blocked seismic attributes to generate a composite seismic parameter. The system can distribute the composite seismic parameter in the subterranean formation to characterize formation locations based on a predicted presence of hydrocarbons.

A method can include accessing volumetric data from a data store, where the volumetric data correspond to a region; generating structured shape information for the region using at least a portion of the volumetric data; and, in response to a command from a client device, transmitting to the client device, via a network interface, a visualization data stream generated using at least a portion of the structured shape information.