Abstract: A method for detecting an unknown fault in a target seismic volume. The method includes generating a number of patches from a training seismic volume that is separate from the target seismic volume, where a patch includes a set of training areas, generating a label for assigning to the patch, where the label represents a subset, of the set of training areas, intersected by an known fault specified by a user in the training seismic volume, training, during a training phase and based at least on the label and the training seismic volume, a machine learning model, and generating, by applying the machine learning model to the target seismic volume during a prediction phase subsequent to the training phase, a result to identify the unknown fault in the target seismic volume.

Abstract: A method can include receiving seismic image data of a geologic region and interpretation information of the seismic image data for a geologic feature in the geologic region, where the seismic image data include a geologic feature class imbalance; shifting the geologic feature class imbalance toward a class of the geologic feature by increasing the spatial presence of the geologic feature in the seismic image data to generate training data; and training a neural network using the training data to generate a trained neural network.

Abstract: A method can include receiving seismic image data of a geologic region and interpretation information of the seismic image data for a geologic feature in the geologic region, where the seismic image data include a geologic feature class imbalance; shifting the geologic feature class imbalance toward a class of the geologic feature by increasing the spatial presence of the geologic feature in the seismic image data to generate training data; and training a neural network using the training data to generate a trained neural network.

Abstract: A method for detecting an unknown fault in a target seismic volume. The method includes generating a number of patches from a training seismic volume that is separate from the target seismic volume, where a patch includes a set of training areas, generating a label for assigning to the patch, where the label represents a subset, of the set of training areas, intersected by an known fault specified by a user in the training seismic volume, training, during a training phase and based at least on the label and the training seismic volume, a machine learning model, and generating, by applying the machine learning model to the target seismic volume during a prediction phase subsequent to the training phase, a result to identify the unknown fault in the target seismic volume.