Abstract: A computer-implemented method includes receiving a test seismic dataset associated with a known truth interpretation, receiving one or more hard constraints, training a machine learning system based on the test seismic dataset, the known truth interpretation, and the one or more hard constraints, determining an error value based on the training the machine learning system, adjusting the error value based on one or more soft constraints, updating the training of the machine learning system based on the adjusted error value, receiving a second seismic dataset after the updating the training; applying the second seismic dataset to the machine learning system to generate an interpretation of the second seismic dataset, generating a seismic image representing a subterranean domain based on the interpretation of the second seismic dataset, and outputting the seismic image.

Abstract: A method includes receiving an input dataset representing one or more physical characteristics of a volume, generating an embedding by reducing a dimensionality associated with the input dataset using a trained machine learning model, comparing the embedding with a plurality of other embeddings generated by reducing a dimensionality of other datasets representing one or more physical characteristics of other volumes, selecting one or more of the other embeddings of the one or more other datasets based at least in part on comparing, and estimating one or more attributes of the volume based at least in part on the one or more other datasets corresponding to the selected one or more of the other embeddings.

Abstract: A method for correlating well logs includes receiving a well log as input to a first machine learning model that is configured to predict first markers in the well log based at least in part on a global factor of the well log, receiving the well log as input to a second machine learning model that is configured to predict second markers in the well log based at least in part on local factors of the well log, generating a set of predicted well markers by merging at least some of the first markers and at least some of the second markers, and aligning the well log with respect to one or more other well logs based at least in part on the set of predicted well markers.

Abstract: A method and apparatus for subsurface data processing includes determining a set of clusters based at least in part on measurement vectors associated with different depths or times in subsurface data, defining clusters in a subsurface data by classes associated with a state mode, reducing a quantity of the subsurface data based at least in part on the classes, and storing the reduced quantity of the subsurface data and classes with the state model in a training database for a machine learning process.

Abstract: A method for digitizing image-based data includes receiving an image file including one or more target objects, generating an intermediate image by removing noise from the image file using a denoising machine learning model, identifying the one or more target objects included in the intermediate image using an object segmentation machine learning model, discretizing the one or more target objects that were identified using the trained object segmentation machine learning model, and storing the one or more target objects that were discretized in a data file, visualizing the one or more target objects, or both.

Abstract: A method includes receiving geophysical data representative of a geophysical structure; providing the geophysical data as one or more input data to a neural network; training the neural network to reconstruct the geophysical structure that was received and provide one or more uncertainty metrics for one or more features of the geophysical structure that is reconstructed; reconstructing, using the neural network that has been trained, the geophysical structure; and determining, using the neural network that has been trained, the one or more uncertainty metrics by implementing a second drop out condition on the one or more nodes of the one or more hidden layers of the neural network. The training is performed at least partially by implementing a first drop out condition on one or more nodes of one or more hidden layers of the neural network to randomly set an output of the one or more nodes to zero.

Abstract: A machine-implemented method, at least one non-transitory computer-readable medium storing instructions, and a computing system are provided for attenuating noise. A computing system receives a seismic image and generates a first image using a first neural network configured to identify low-frequency ground roll in a seismic image, and a second image using a second neural network configured to identify reflections in the seismic image. A combined image is generated by combining the first image and the second image. The first neural network and the second neural network are adjusted to reduce a difference between the combined image and the seismic image using frequency constraint to guide separation of the seismic image into the first image and the second image.

Abstract: Methods and systems for augmented geological service characterization are described. An embodiment of a method includes generating a geological service characterization process in response to one or more geological service objectives and a geological service experience information set. Such a method may also include augmenting the geological service characterization process by machine learning in response to a training information set. Additionally, the method may include generating an augmented geological service characterization process in response to the determination information.

Abstract: A method and apparatus for subsurface data processing includes determining a set of clusters based at least in part on measurement vectors associated with different depths or times in subsurface data, defining clusters in a subsurface data by classes associated with a state mode, reducing a quantity of the subsurface data based at least in part on the classes, and storing the reduced quantity of the subsurface data and classes with the state model in a training database for a machine learning process.

Abstract: A method for modeling a subterranean volume includes receiving seismic data comprising a signal, generating a semblance in the frequency-wavenumber domain for the seismic data, wherein the semblance represents a coherence of the signal in the frequency-wavenumber domain, extracting one or more wave energy modes in the semblance using a machine learning model trained to identify dispersion curves in the semblance based on a visible characteristic of the dispersion curves, and generating a model representing surface wave propagation based at least in part on the identified one or more wave energy modes.

Abstract: A method for seismic processing includes extracting, using a first machine learning model, one or more seismic features from seismic data representing a subsurface domain, receiving one or more well logs representing one or more subsurface properties in the subsurface domain, and predicting, using a second machine learning model, the one or more subsurface properties in the subsurface domain at a location that does not correspond to an existing well based on the seismic data, the one or more well logs, and the one or more seismic features that were extracted from the seismic data.

Abstract: A method for modeling a subsurface volume includes receiving a plurality of ordered seismic images including representations of objects in the subsurface volume, generating flow fields based on a difference between individual images of the plurality of ordered seismic images, and identifying the objects in the seismic images based on the flow fields and the plurality of ordered seismic images.

Abstract: Methods and systems for augmented geological service characterization are described. An embodiment of a method includes generating a geological service characterization process in response to one or more geological service objectives and a geological service experience information set. Such a method may also include augmenting the geological service characterization process by machine learning in response to a training information set. Additionally, the method may include generating an augmented geological service characterization process in response to the determination information.

Abstract: A method includes receiving well log data comprising a plurality of well logs, identifying one or more sections of one or more well logs of the plurality of well logs that have substantially complete data, training a reconstruction neural network to reconstruct incomplete well logs based on the one or more sections of the one or more well logs that have substantially complete data, and reconstructing one or more incomplete well logs of the plurality of well logs using the reconstruction neural network.

Abstract: A method for drilling includes obtaining formation-measurement pairings, training a machine-learning model using the formation-measurement pairings, receiving measurements obtained by a tool positioned in a well formed in a formation, and generating a formation model of at least a portion of the formation using the machine-learning model and the measurements. The formation model represents one or more physical parameters of the formation, one or more structural parameters of the formation, or both.

Abstract: 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.

Abstract: A computer-implemented method includes receiving a test seismic dataset associated with a known truth interpretation, receiving one or more hard constraints, training a machine learning system based on the test seismic dataset, the known truth interpretation, and the one or more hard constraints, determining an error value based on the training the machine learning system, adjusting the error value based on one or more soft constraints, updating the training of the machine learning system based on the adjusted error value, receiving a second seismic dataset after the updating the training; applying the second seismic dataset to the machine learning system to generate an interpretation of the second seismic dataset, generating a seismic image representing a subterranean domain based on the interpretation of the second seismic dataset, and outputting the seismic image.

Abstract: A method can include receiving a first trained machine model trained via unsupervised learning using unlabeled seismic image data; receiving labeled seismic image data acquired via an interactive interpretation process; and building a second trained machine model, as initialized from the first trained machine model, via supervised learning using the received labels, where the second trained machine model predicts stratigraphy of a geologic region from seismic image data of the geologic region.

Abstract: A method includes receiving information for a subsurface region; based at least in part on the information, identifying sub-regions within the subsurface region; assigning individual identified sub-regions a dimensionality of a plurality of different dimensionalities that correspond to a plurality of different models; via a model-based computational framework, generating at least one result for at least one of the individual identified sub-regions based at least in part on at least one assigned dimensionality; and consolidating the at least one result for multiple sub-regions.

Abstract: A method includes determining a top of salt (TOS) surface in a seismic volume based on a crossline direction of the seismic volume and an inline direction of the seismic volume. The method also includes determining a binary mask based upon the TOS surface. The method also includes sampling seismic data in the seismic volume to obtain a training seismic slice. The method also includes sampling the binary mask to obtain a mask slice. The method also includes selecting a first coordinate in the training seismic slice to produce a first tile. The method also includes selecting a second coordinate in the mask slice to produce a second tile. The method also includes generating or updating a model of the seismic volume based upon the first tile and the second tile.