Abstract: According to some aspects, machine-learning models can be executed to classify a subsurface rock. Examples include training numerous machine-learning models using training data sets with different probability distributions, and then selecting a model to execute on a test data set. The selection of the model may be based on the similarity of each data point of the test data set and the probability distribution of each training class. Examples include detecting and recommending a pre-trained model to generate outputs predicting a classification, such as a lithology, of a test data set. Recommending the trained model may be based on calculated prior probabilities that measure the similarity between the training and test data sets. The model with a training data set that is most similar to the test data set can be recommended for classifying a physical property of the subsurface rock for hydrocarbon formation.

Abstract: Disclosed herein are embodiments of a method, a non-transitory computer readable medium, and an apparatus for faulted seismic horizon mapping. In one example, a method comprises: obtaining seismic data for a seismic volume that corresponds to a subsurface formation; generating a map of at least one horizon in the subsurface formation based on the seismic volume; identifying at least one fault intersecting the at least one horizon; determining a throw of the at least one fault; and updating the map of the at least one horizon to incorporate the at least one fault based on the throw of the at least one fault.

Abstract: A method for processing seismic data by a seismic data system. The method comprises acquiring a plurality of first traces each corresponding to a respective first trace location. The method comprises expressing the first traces as first vertices in a first graph in which first edges connect the first vertices, wherein the first edges indicate positioning of the first vertices.

Abstract: A least one seismic attribute is determined for each voxel of the seismic volume. A first horizon is selected for mapping and a sparse global grid is generated which includes the horizon, at least one constraint point identifying the horizon, and a number of points having a depth in the seismic volume. A value of at least one seismic attribute is determined for each point and their depths are adjusted based on the value of the seismic attribute. A map of the horizon can be generated based on the adjusted depths. Multiple local grids can be generated based on the sparse global grid, and the depths of the local grid points adjusted to generate a map of the horizon at voxel level resolution. The seismic volume can be mapped into multiple horizons, where previously mapped horizons can function as constraints on the sparse global grid.

Abstract: A least one seismic attribute is determined for each voxel of the seismic volume. A first horizon is selected for mapping and a sparse global grid is generated which includes the horizon, at least one constraint point identifying the horizon, and a number of points having a depth in the seismic volume. A value of at least one seismic attribute is determined for each point and their depths are adjusted based on the value of the seismic attribute. A map of the horizon can be generated based on the adjusted depths. Multiple local grids can be generated based on the sparse global grid, and the depths of the local grid points adjusted to generate a map of the horizon at voxel level resolution. The seismic volume can be mapped into multiple horizons, where previously mapped horizons can function as constraints on the sparse global grid.

Abstract: A method for performing wellbore correlation across multiple wellbores includes predicting a depth alignment across the wellbores based on a geological feature of the wellbores. Predicting a depth alignment includes selecting a reference wellbore, defining a control point in a reference signal of a reference well log for the reference wellbore, and generating an input tile from the reference signal, the control points, and a number of non-reference well logs corresponding to non-reference wellbores. The well logs include changes in a geological feature over a depth of a wellbore. The input tile is input into a machine-learning model to output a corresponding control point for each non-reference well log. The corresponding control point corresponds to the control point of the reference log. Based on the corresponding control points output from the machine-learning model, the non-reference well logs are aligned with the reference well log to correlate the multiple wellbores.

Abstract: A lithology prediction that uses a geological age model as an input to a machine learning model. The geological age model is capable of separating and recoding different seismic packages derived from the horizon interpretation. Once the machine learning model has been trained, a validation may be performed to determine the quality of the machine learning model. The quality may be improved by refining the training of the machine learning model. The lithology prediction generated by the machine learning model that utilizes the geological age model provides an improved lithology prediction that more accurately reflects the subterranean formation of an area of interest.

Abstract: In contrast to existing methods wherein derived horizons are interpreted in isolation, the disclosure provides a process that does not interpret patches themselves but determines the relationships between patches, in order to associate and link patches to derive a holistic geological interpretation. Predefined patches, such as from a pre-interpreted suite, are received as inputs to determine the relationships and derive an interpretation for a complete volume. In one aspect the disclosure provides an automated method of generating a geological age model for a subterranean area. In one example, the automated method includes: (1) abstracting seismic data of a subsurface into a limited number of patches, (2) abstracting the patches by defining patch-links between the patches, and (3) generating a geological age model of the subsurface by solving for the relative geological age of each of the patches using the patch-links.

Abstract: Map projections necessarily distort the Earth's surface in some fashion as a result of the transformation to a coordinate system. However, different map projection systems can preserve some properties of geospatial data (e.g., area) at the expense of other properties (e.g., distance or azimuth). To produce a minimally distorted global raster, a global raster generator creates a number and variety of projections using as input geospatial data. The generator intelligently selects the projection systems based on properties of the input data and desired properties of an output global raster. The generator then applies interpolation algorithms to the projections to produce smooth and continuous projections. The generator then re-projects the interpolated projections to a desired output projection system and filters the projections to identify and remove regions of the projections which exhibit distortion. The generator merges the filtered projections which results in a minimally distorted global raster.

Abstract: An apparatus for processing seismic data variables comprising a tracking module and an interpretation module. The tracking module selects groupings of subsurface data variables from the seismic data variables, selects a subsurface data variable for each grouping, and determines an isochron variable for each subsurface data variable for each grouping. Each grouping of subsurface data variables has spatial coordinates values. The interpretation module predicts a horizon variable for each grouping using the isochron variable and an algorithmic model or trained algorithmic. The interpretation module predicts a horizon variable using the isochron variable for each grouping and a trained algorithmic model. The tracking module selects the subsurface data variable for each grouping based on a peak, trough or zero-crossing identified in the grouping.

Abstract: An apparatus for processing seismic data variables comprising a tracking module and an interpretation module. The tracking module selects groupings of subsurface data variables from the seismic data variables, selects a subsurface data variable for each grouping, and determines an isochron variable for each subsurface data variable for each grouping. Each grouping of subsurface data variables has spatial coordinates values. The interpretation module predicts a horizon variable for each grouping using the isochron variable and an algorithmic model or trained algorithmic. The interpretation module predicts a horizon variable using the isochron variable for each grouping and a trained algorithmic model. The tracking module selects the subsurface data variable for each grouping based on a peak, trough or zero-crossing identified in the grouping.

Abstract: Analysis and display of source-to-sink information according to some aspects includes grouping geochronological data associated with a sediment sample into optimized subpopulations within a reference population and target populations, and producing Gaussian functions for the reference population and the target populations using the subpopulations as a priori constraints. The Gaussian functions describe a distribution of zircons. The subpopulations within the reference population and the target populations are compared based on at least one statistical attribute from the Gaussian functions to identify areas of sediment provenance, and the areas of sediment provenance are displayed in various ways, for example, on a paleographic map as of an age of deposition of the sediment sample. A sink-to-sink analysis can also be performed to identify dissimilarities between samples.

Abstract: The disclosed embodiments include systems and methods to assess geological data. The method includes obtaining data associated with a geological state of a geological entity. The method also includes assessing a nature of a geological age constraint of the geological entity. The method further includes generating a first probability distribution of a geological age of the geological entity based on the nature of the geological age constraint of the geological entity. The method further includes selecting a time of interest for analysis of the geological entity. The method further includes assessing a nature of the geological age constraint during the time of interest. The method further includes generating a second probability distribution for the time of interest. The method further includes determining a likelihood that the geological age constraint of the geological entity coincides with the time of interest.

Abstract: A heat flow modeler preprocesses geological and heat flow data for an earth formation for inputting into a plurality of supervised learning models. The heat flow modeler trains the plurality of supervised learning models on the preprocessed geological data to estimate heat flow throughout the earth formation. The heat flow modeler interpolates the estimated heat flow values to a set of desired locations in the earth formation and cosimulates the preprocessed heat flow values with the interpolated heat flow values as auxiliary variables to generate a cosimulated heat flow map. A final heat flow map is generated by rasterizing the cosimulated heat flow map.

Abstract: According to some aspects, machine-learning models can be executed to classify a subsurface rock. Examples include training numerous machine-learning models using training data sets with different probability distributions, and then selecting a model to execute on a test data set. The selection of the model may be based on the similarity of each data point of the test data set and the probability distribution of each training class. Examples include detecting and recommending a pre-trained model to generate outputs predicting a classification, such as a lithology, of a test data set. Recommending the trained model may be based on calculated prior probabilities that measure the similarity between the training and test data sets. The model with a training data set that is most similar to the test data set can be recommended for classifying a physical property of the subsurface rock for hydrocarbon formation.

Abstract: Analysis and display of source-to-sink information according to some aspects includes grouping target geochronological data and reference geochronological data into distinct population groups representing a reference population and target populations and characterizing subpopulations within the reference population and the target populations according a statistical attribute or statistical attributes. Subpopulations are compared within the reference population and the target populations based on the statistical attribute or attributes to determine correlations between the reference population and the target populations, and the results can be displayed in many different ways. As one example, results can be displayed using a present day geographic map as well as using a geodynamic plate tectonic model to show data points and their paleogeographic locations for the relevant geological time frame of investigation.

Abstract: A system includes a processor and a memory. The memory includes instructions that are executable by the processor to access training data of a modern feature of interest from direct observations, remotely determined data, or a combination thereof. The instructions are also executable to compile parameter data from at least one model simulation that impacts the modern feature of interest. The instructions are executable to train a machine-learning model to generate a predictive model that matches the training data of the modern feature of interest using the compiled parameter data as input. Furthermore, the instructions are executable to predict a feature of interest in a past time period using the predictive model and at least one historical model simulation that impacts the feature of interest. Additionally, the instructions are executable to execute a processing operation for facilitating hydrocarbon exploration based on the predicted feature of interest from the predictive model.

Abstract: Map projections necessarily distort the Earth's surface in some fashion as a result of the transformation to a coordinate system. However, different map projection systems can preserve some properties of geospatial data (e.g., area) at the expense of other properties (e.g., distance or azimuth). To produce a minimally distorted global raster, a global raster generator creates a number and variety of projections using as input geospatial data. The generator intelligently selects the projection systems based on properties of the input data and desired properties of an output global raster. The generator then applies interpolation algorithms to the projections to produce smooth and continuous projections. The generator then re-projects the interpolated projections to a desired output projection system and filters the projections to identify and remove regions of the projections which exhibit distortion. The generator merges the filtered projections which results in a minimally distorted global raster.

Abstract: Analysis and display of source-to-sink information according to some aspects includes grouping target geochronological data and reference geochronological data into distinct population groups representing a reference population and target populations and characterizing subpopulations within the reference population and the target populations according a statistical attribute or statistical attributes. Subpopulations are compared within the reference population and the target populations based on the statistical attribute or attributes to determine correlations between the reference population and the target populations, and the results can be displayed in many different ways. As one example, results can be displayed using a present day geographic map as well as using a geodynamic plate tectonic model to show data points and their paleogeographic locations for the relevant geological time frame of investigation.

Abstract: Analysis and display of source-to-sink information according to some aspects includes grouping geochronological data associated with a sediment sample into optimized subpopulations within a reference population and target populations, and producing Gaussian functions for the reference population and the target populations using the subpopulations as a priori constraints. The Gaussian functions describe a distribution of zircons. The subpopulations within the reference population and the target populations are compared based on at least one statistical attribute from the Gaussian functions to identify areas of sediment provenance, and the areas of sediment provenance are displayed in various ways, for example, on a paleographic map as of an age of deposition of the sediment sample. A sink-to-sink analysis can also be performed to identify dissimilarities between samples.