A method and apparatus for machine learning for use with automated seismic interpretation include: obtaining input data; extracting patches from a pre-extraction dataset based on the input data; transforming data of a pre-transformation dataset based on the input data and geologic domain knowledge and/or geophysical domain knowledge; and generating augmented data from the extracted patches and the transformed data. A method and apparatus for machine learning for use with automated seismic interpretation include: a data input module configured to obtain input data; a patch extraction module configured to extract patches from a pre-extraction dataset that is based on the input data; a data transformation module configured to transform data from a pre-transformation dataset that is based on the input data and geologic domain knowledge and/or geophysical domain knowledge; and a data augmentation module configured to augment data from the extracted patches and the transformed data.

A method and apparatus for machine learning for use with automated seismic interpretation include: obtaining input data; extracting patches from a pre-extraction dataset based on the input data; transforming data of a pre-transformation dataset based on the input data and geologic domain knowledge and/or geophysical domain knowledge; and generating augmented data from the extracted patches and the transformed data. A method and apparatus for machine learning for use with automated seismic interpretation include: a data input module configured to obtain input data; a patch extraction module configured to extract patches from a pre-extraction dataset that is based on the input data; a data transformation module configured to transform data from a pre-transformation dataset that is based on the input data and geologic domain knowledge and/or geophysical domain knowledge; and a data augmentation module configured to augment data from the extracted patches and the transformed data.

A method for determining a shear slowness of a subterranean formation includes receiving waveforms data acquired by receivers in an acoustic measurement tool in response to energy emitted by at least one dipole source. The waveforms are processed to extract a formation flexural acoustic mode and a tool flexural acoustic mode. The processing includes transforming the time domain waveforms to frequency domain waveforms, processing the frequency domain waveforms with a Capon algorithm to compute a two-dimensional spectrum over a chosen range of group slowness and phase slowness values; and processing the two-dimensional spectrum to extract the multi-mode slowness dispersion. The method further includes selecting a plurality of slowness-frequency pairs from the formation flexural mode of the extracted multi-mode dispersion wherein each slowness-frequency pair comprises a slowness value at a corresponding frequency and processing the selected slowness frequency pairs to compute the shear slowness of the subterranean formation.

A disclosed method for wellsite operations includes obtaining a spectral decomposition, of a seismic data associated with a geological formation. The spectral decomposition includes a first spectral representation generated using a first operator and a second spectral representation generated using a second operator. The method also includes determining a first characteristic of the first operator and a second characteristic of the second operator. The method further includes determining at least one acceptable operator based on the first characteristic and the second characteristic. The method also includes generating a geological model feature using the at least one acceptable operator.

A disclosed method for wellsite operations includes obtaining a spectral decomposition, of a seismic data associated with a geological formation. The spectral decomposition includes a first spectral representation generated using a first operator and a second spectral representation generated using a second operator. The method also includes determining a first characteristic of the first operator and a second characteristic of the second operator. The method further includes determining at least one acceptable operator based on the first characteristic and the second characteristic. The method also includes generating a geological model feature using the at least one acceptable operator.

A method for generating a seismic image representing a subsurface includes receiving seismic data for the subsurface formation, including receiver wavelet data and source wavelet data. Source wavefield data are generated based on a forward modeling of the source wavelet data. Receiver wavefield data are generated that compensate for distortions in the seismic data by: applying a dispersion-only model to the receiver wavelet data to generate a first reconstructed back-propagated receiver wavefield portion, applying a dissipation-only model to the receiver wavelet data to generate a second reconstructed back-propagated receiver wavefield portion, and combining the first back-propagated receiver wavefield portion and the second back-propagated receiver wavefield portion into the receiver wavefield data. The method includes applying an imaging condition to the receiver wavefield data and the source wavefield data and generating, based on applying the imaging condition, visco-acoustic reverse time migration (VARTM) result data.

Systems and methods are disclosed for associating a standard numerical age to an attribute of geological data from disparate locations. Exemplary implementations may include generating a standardized geological age dataset by standardizing geological data to a global reference age based on a dimension of the geological data, a local geotemporal marker, and a dimension to age function; and storing the standardized geological age dataset.

A computer-implemented method includes the following. A frequency sweep using sweep parameters is emitted from a vibratory seismic source into geological layers. The sweep parameters include frequencies and modulation parameters for seismic waves. Signals are received from one or more sensors. The signals include seismic data acquisition information, including values identifying energy reflected back from boundaries where rock properties change. A determination is made regarding which of the reflected seismic waves are attenuated. The determination uses an integral transform and a thresholding algorithm for image segmentation. Optimum sweep parameters are determined based on the reflected seismic values that are attenuated and updated to compensate for local geology effects. The emitting, receiving, determining attenuation, determining optimum parameters, and updating are repeated until the received signals are determined to be satisfactory.

A simultaneous sources seismic acquisition method is described that introduces notch diversity to improve separating the unknown contributions of one or more sources from a commonly acquired set of wavefield signals while still allowing for optimal reconstruction properties in certain diamond-shaped regions. In particular, notch diversity is obtained by heteroscale encoding.

Systems and methods for generating seismic images of subterranean features including: receiving raw seismic data of a subterranean formation; selecting a portion of the raw seismic data; transforming the selected portion of the raw seismic data from a first domain to a second domain; generating soft constraint data corresponding to the selected portion of the raw seismic data; calculating at least one weight using the generated soft constraint data; generating a weighted transformed data set by applying at least one weight to the transformed selected portion of the raw seismic data; selecting at least one data point of the generated weighted transformed data set; and removing the selected at least one data point from the weighted transformed data set to generate revised seismic data.