The invention is a method applicable to oil and gas exploration and exploitation for automatically detecting geological objects belonging to a given type of geological object in a seismic image, on a basis of a priori probabilities of belonging to a type of geological object assigned to each of samples of the image to be interpreted. The image is transformed into seismic attributes applied beforehand, followed by a classification method. For each of the classes, an a posteriori probability of belonging to a type of geological object is determined for each of the samples of the class according to the a priori probabilities, of the class, of belonging, and according to a parameter α describing a confidence in the a priori probabilities of belonging. Based on the class of the sample, the determined a posteriori probability of belonging to a type of geological object is assigned for the samples of the class. The geological objects belonging to the type of geological object are detected based on determined of the a posteriori probabilities of belonging to the type of geological object for each of the samples of the image to be interpreted.

A method for training a backpropagation-enabled segmentation process is used for identifying an occurrence of a sub-surface feature. A multi-dimensional seismic data set with an input dimension of at least two is inputted into a backpropagation-enabled process. A prediction of the occurrence of the subsurface feature has a prediction dimension of at least 1 and is at least 1 dimension less than the input dimension.

Systems and methods for interpreting and visualizing multi-Z horizons from seismic data are disclosed. A two-dimensional (2D) representation of seismic data is displayed via a graphical user interface (GUI). User input is received via the GUI for interpreting a multi-Z horizon within a portion of the displayed 2D representation. The user's input is tracked relative to displayed 2D representation within the GUI. Based on the tracking, each of a plurality of surfaces for the multi-Z horizon is determined. At least one intersection point between the multi-Z horizon surfaces is identified. A depth position for each surface relative to other surfaces is determined. The 2D representation of the seismic data is dynamically updated to include visual indications for the plurality of surfaces and the intersection point(s), based on the depth position of each surface, where the visual indications use different visualization styles to represent the surfaces and intersection point(s).

The present invention relates to a method of prediction of hydrocarbon accumulation in a geological region comprising the following steps of: a. Generation of a geological basin model; b. Generation of a geomechanical model; c. Generation of an integrated model; d. Generation of a strain map based on the information obtained in steps a to c; e. Prediction of hydrocarbon accumulation from the strain maps.

Methods, systems, and computer-readable media for processing seismic data. The method includes receiving a plurality of seismic traces representing a subterranean domain, and receiving an implicit stratigraphic model of at least a portion of the subterranean domain. The method also includes selecting an iso-value in the implicit stratigraphic model, and defining, using a processor, a geologically-consistent interval in the implicit stratigraphic model based at least partially on a position of the iso-value in the implicit stratigraphic model. The method further includes calculating one or more attributes of the plurality of seismic traces in the interval.

A method of analysing seismic data from a geological structure. The method includes determining a set of tiles from a data cube of seismic data and determining which tiles of the set of tiles can be grouped into one or more patches of tiles.

Strata surfaces can be identified in well logs and correlated across the well logs taking into account manual corrections. For example, a computing device can receive well logs. The computing device can determine multiple stratum-surface correlations based on the well logs. Then, the computing device can receive user input indicating a correction to a particular stratum-surface correlation. Based on the correction to the particular stratum-surface correlation, the computing device can update some or all of the other stratum-surface correlations.

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 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.

A method for training a backpropagation-enabled segmentation process is used for identifying an occurrence of a sub-surface feature. A multi-dimensional seismic data set with an input dimension of at least two is inputted into a backpropagation-enabled process. A prediction of the occurrence of the subsurface feature has a prediction dimension of at least 1 and is at least 1 dimension less than the input dimension.