Abstract: A method can include receiving data for a body where the data include energy consumption data and weight change data; generating an efficiency parameter value using the received data, where the efficiency parameter depends on a difference of an amount of water in two different types of body tissues of the body; and generating an output using the efficiency parameter, where such a method can be performed via circuitry of a system or a device, which may include a weight scale, a wearable computing device or a smart phone.

Abstract: A method can include selecting a type of geophysical data; selecting a type of algorithm; generating synthetic geophysical data based at least in part on the algorithm; training a deep learning framework based at least in part on the synthetic geophysical data to generate a trained deep learning framework; receiving acquired geophysical data for a geologic environment; implementing the trained deep learning framework to generate interpretation results for the acquired geophysical data; and outputting the interpretation results.

Abstract: A method for processing an image includes receiving an input image including a signal and noise, and generating a filtered image based on the input image by removing at least a portion of the noise from the input image. A portion of the signal is also removed from the input image. The method further includes generating a residual image based on the input image. The residual image comprises the at least a portion of the noise and the portion of the signal that are removed from the input image to generate the filtered image. The method also includes identifying at least some of the portion of the signal that is in the residual image, and inserting the at least some of the portion of the signal identified in the residual image into the filtered image.

Abstract: A method can include receiving n-dimensional data where n is equal at least three; analyzing a plurality of two-dimensional slices of the n-dimensional data to determine characteristic information with respect to a plurality of feature indexes for a feature in the n-dimensional data; and, based at least in part on the characteristic information, associating the feature with one of the feature indexes.

Abstract: A method, apparatus, and program product analyze time-series data such as seismic data collected from a subsurface formation by splitting a time-series data set such as an individual seismic trace into a plurality of spectral components, each having an associated frequency, determining an instantaneous frequency for each spectral component, determining a frequency difference for each spectral component based at least in part on the associated and instantaneous frequencies therefor, and determining a tuning parameter based at least in part on the determined frequency difference of each spectral component. Doing so enables, for example, thin-bed structures in the subsurface formation to be identified, and in some instances, thicknesses of such structures to be determined.

Abstract: A method includes receiving imagery data; fitting a multidimensional polynomial function to at least a portion of the imagery data to generate one or more values for one or more corresponding parameters of the function; and generating curvature attribute data based at least in part on the fitting.

Abstract: Systems, methods, and non-transitory computer-readable media for processing geological data, of which the method includes receiving a geological data processing tool at a client system. The geological data processing tool includes artificial intelligence, and the geological data processing tool is generated by a geological processing tool provider. The method also includes obtaining training data for the geological data processing tool. The training data includes a plurality of labels. The method also includes training the geological data processing tool based on the training data, receiving data representing a physical, subterranean volume, identifying one or more geological features in the subterranean volume by using the geological data processing tool after training the geological data processing tool, and modifying, using the client system, one or more parameters of the geological data processing tool, or one or more labels of the plurality of labels.

Abstract: A method can include selecting a type of geophysical data; selecting a type of algorithm; generating synthetic geophysical data based at least in part on the algorithm; training a deep learning framework based at least in part on the synthetic geophysical data to generate a trained deep learning framework; receiving acquired geophysical data for a geologic environment; implementing the trained deep learning framework to generate interpretation results for the acquired geophysical data; and outputting the interpretation results.

Abstract: A method can include receiving data sets where each of the data sets corresponds to one of a plurality of individual emitter-detector arrangements; calculating a multi-dimensional similarity metric for one of the data sets; and, based at least in part on the multi-dimensional similarity metric, assessing the one data set.

Abstract: One or more computer-readable media include computer-executable instructions to instruct a computing system to, for a given time, solve the elastic wave equation in tensorial form for a geological reservoir model subject to stated conditions; and adjust a grid associated with the geological reservoir model based on solution of the elastic wave equation in tensorial form for the given time. Various other apparatuses, systems, methods, etc., are also disclosed.

Abstract: A method can include receiving seismic data that has an associated bandwidth; for a number of frequency bands, for a number of frequency bands, iteratively filtering and adjusting the seismic data by applying band-pass filters to extract information associated with each of the frequency bands where the adjusting the seismic data includes, after each iteration, subtracting extracted information from the seismic data prior to a subsequent iteration; balancing the extracted information to generate spectrally balanced seismic data; and outputting the spectrally balanced seismic data.

Abstract: A method can include receiving n-dimensional data where n is equal at least three; analyzing a plurality of two-dimensional slices of the n-dimensional data to determine characteristic information with respect to a plurality of feature indexes for a feature in the n-dimensional data; and, based at least in part on the characteristic information, associating the feature with one of the feature indexes.

Abstract: A method, apparatus, and program product analyze time-series data such as seismic data collected from a subsurface formation by splitting a time-series data set such as an individual seismic trace into a plurality of spectral components, each having an associated frequency, determining an instantaneous frequency for each spectral component, determining a frequency difference for each spectral component based at least in part on the associated and instantaneous frequencies therefor, and determining a tuning parameter based at least in part on the determined frequency difference of each spectral component. Doing so enables, for example, thin-bed structures in the subsurface formation to be identified, and in some instances, thicknesses of such structures to be determined.

Abstract: A method can include receiving seismic data that has an associated bandwidth; for a number of frequency bands, for a number of frequency bands, iteratively filtering and adjusting the seismic data by applying band-pass filters to extract information associated with each of the frequency bands where the adjusting the seismic data includes, after each iteration, subtracting extracted information from the seismic data prior to a subsequent iteration; balancing the extracted information to generate spectrally balanced seismic data; and outputting the spectrally balanced seismic data.

Abstract: A method can include receiving data that includes signal data and coherent noise data where the signal data includes signal data that corresponds to a multidimensional physical structure; generating filtered data by filtering at least a portion of the data to attenuate at least a portion of the coherent noise data by applying a multidimensional geometric coherent noise model defined by at least one geometric parameter; and assessing a portion of the signal data in the generated filtered data to characterize the multidimensional physical structure.

Abstract: A method can include providing seismic data values for a subsurface region that includes a reflector; determining a gradient magnitude value based on at least a portion of the seismic data values; normalizing the gradient magnitude value using a nonlinear normalization equation that includes a gradient magnitude variable divided by a normalization variable raised to a power that depends on an adjustable parameter; and outputting the normalized gradient magnitude value. Various other apparatuses, systems, methods, etc., are also disclosed.

Abstract: A method can include receiving a request for a dip value for a location within a sub-surface volume; responsive to the request, locating complementary dip values for locations within the sub-surface volume where the location for the requested dip value lies within bounds defined by the locations for the complementary dips values; and interpolating a value for the requested dip value based on the complementary dip values. Various other apparatuses, systems, methods, etc., are also disclosed.

Abstract: A method for decomposing a signal includes receiving sampled data. A wavelet is built using the sampled data that includes a plurality of samples. The wavelet includes a number of oscillations per sampling unit, and a length of the wavelet corresponds to the number of oscillations. The wavelet is time-shifted. The wavelet is then scaled such that the samples proximate to one or both ends of the wavelet decay toward zero. The wavelet is also scaled such that an amplitude at a peak frequency of the wavelet, when transformed into a Fourier domain, is substantially unity.

Abstract: A method can include receiving data that includes signal data and coherent noise data where the signal data includes signal data that corresponds to a multidimensional physical structure; generating filtered data by filtering at least a portion of the data to attenuate at least a portion of the coherent noise data by applying a multidimensional geometric coherent noise model defined by at least one geometric parameter; and assessing a portion of the signal data in the generated filtered data to characterize the multidimensional physical structure.

Abstract: A method can include providing seismic data for a subsurface region that includes a reflector; processing at least a portion of the seismic data to generate at least one path that extends orthogonally to the reflector; and outputting output data representing the at least one path. Various other apparatuses, systems, methods, etc., are also disclosed.