Abstract: Techniques for creating machine learning models for direct homography regression for image rectification are described. In certain embodiments, a training service trains an algorithm on a source view of a training image and a homography matrix of the training image into a machine learning model that generates a normalized homography matrix for an input of the source view. The normalized homography matrix may then be utilized to generate a target view of an image input into the machine learning model. The target view of the image may be used in a document processing pipeline for document images captured using cameras.

Abstract: A method of identifying bounded hydrocarbon formations of interest in a seismic data set includes obtaining a seismic data set, pre-processing the seismic data set, inputting the plurality of graphical model inputs and one or more rules to a graphical model, wherein the rules define a relationship between a plurality of attributes of a bounded hydrocarbon formation, running a graphical model on the graphical model inputs, post-processing the graphical model outputs, and displaying the ranked clusters in order of rank.

Abstract: A method includes accessing a seismic image comprising a plurality of features of interest. The method also includes defining a plurality of configuration files for a plurality of graphical models. The method further includes applying the plurality of graphical models to the seismic image. The method also includes generating a plurality of scores for each feature of interest, wherein each graphical model generates a score for each feature of interest. The method further includes combining the plurality of scores for each feature of interest into a plurality of combined scores, wherein each feature of interest has a combined score.

Abstract: A method includes retrieving a seismic data set, receiving training data that includes one or more seed points of an identified geobody, determining a geobody trajectory of the identified geobody, based on the one or more seed points of the identified geobody, displaying the geobody trajectory, receiving inputs expanding the geobody trajectory, shrinking the geobody trajectory, confirming the geobody trajectory, or a combination thereof, training a classification algorithm using the geobody trajectory, running the classification algorithm on the seismic data set, receiving an output of one or more sets of voxels from the classification algorithm, skeletonizing the one or more sets of voxels to present the one or more sets of voxels as a set of possible geobody trajectories, and retraining the classification algorithm based on feedback received from a reviewer.

Abstract: A workflow is presented that facilitates defining geocontextual information as a set of rules for multiple seismic attributes. Modeling algorithms may be employed that facilitate analysis of multiple seismic attributes to find candidate regions that are most likely to satisfy the set of rules. These candidates may then be sorted based on how well they represent the geocontextual information.

Abstract: A method of identifying bounded hydrocarbon formations of interest in a seismic data set includes obtaining a seismic data set, pre-processing the seismic data set, inputting the plurality of graphical model inputs and one or more rules to a graphical model, wherein the rules define a relationship between a plurality of attributes of a bounded hydrocarbon formation, running a graphical model on the graphical model inputs, post-processing the graphical model outputs, and displaying the ranked clusters in order of rank.

Abstract: A method includes retrieving a seismic data set, receiving training data that includes one or more seed points of an identified geobody, determining a geobody trajectory of the identified geobody, based on the one or more seed points of the identified geobody, displaying the geobody trajectory, receiving inputs expanding the geobody trajectory, shrinking the geobody trajectory, confirming the geobody trajectory, or a combination thereof, training a classification algorithm using the geobody trajectory, running the classification algorithm on the seismic data set, receiving an output of one or more sets of voxels from the classification algorithm, skeletonizing the one or more sets of voxels to present the one or more sets of voxels as a set of possible geobody trajectories, and retraining the classification algorithm based on feedback received from a reviewer.

Abstract: A method includes accessing a seismic image comprising a plurality of features of interest. The method also includes defining a plurality of configuration files for a plurality of graphical models. The method further includes applying the plurality of graphical models to the seismic image. The method also includes generating a plurality of scores for each feature of interest, wherein each graphical model generates a score for each feature of interest. The method further includes combining the plurality of scores for each feature of interest into a plurality of combined scores, wherein each feature of interest has a combined score.

Abstract: An approach for seismic data analysis is provided. In accordance with embodiments of this approach, parallel regions within a volume of seismic data are modeled. Residual regions within the volumetric data set are identified, where the residual regions comprise those regions not modeled as parallel regions. The residual regions or a graphic derived from the residual regions are displayed for review.

Abstract: A workflow is presented that facilitates defining geocontextual information as a set of rules for multiple seismic attributes. Modeling algorithms may be employed that facilitate analysis of multiple seismic attributes to find candidate regions that are most likely to satisfy the set of rules. These candidates may then be sorted based on how well they represent the geocontextual information.

Abstract: An approach for seismic data analysis is provided. In accordance with embodiments of this approach, parallel regions within a volume of seismic data are modeled. Residual regions within the volumetric data set are identified, where the residual regions comprise those regions not modeled as parallel regions. The residual regions or a graphic derived from the residual regions are displayed for review.