A computer system manages model information for defining a U-Net configured to execute, on the input time-series data, an encoding operation for extracting a feature map relating to the target wave by using downsampling blocks and a decoding operation for outputting data for predicting the first motion time of the target wave by using upsampling blocks, executes the encoding operation and the decoding operation on the input time-series data by using the model information. The downsampling blocks and the upsampling blocks each includes a residual block. The residual block includes a time attention block calculates a time attention for emphasizing a specific time domain in the feature map. The time attention block includes an arithmetic operation for calculating attentions different in time width, and calculates a feature map to which the time attention is added by using the attentions.

A method is described for full waveform inversion using a b-spline projection that produces an earth model that can be used for seismic imaging. The method may be executed by a computer system.

In acoustic well logging, for each inversion depths of a well at which logging of data occurs, acoustic log signals representative of waveforms received at acoustic receivers are processed in a frequency domain to derive field dispersion curve(s). A neural net is operated to generate formation shear slowness value(s) from the curve(s), and resulting signal(s) indicative of shear slowness values are saved, transmitted, plotted, printed or processed. An apparatus for carrying out the method includes a logging tool having at least one activatable acoustic wave source; spaced and acoustically isolated therefrom in the logging tool an array of acoustic detectors that on the detection of acoustic wave energy generate electrical or electronic log signal(s) characteristic of acoustic energy waves detected by the acoustic detector(s); and at least one processing device associated with or forming part of the logging tool for processing the log signal(s).

Acoustic waves are obtained from an acoustic logging tool within a borehole passing through a formation. Signal properties in a time domain, frequency domain, or both are determined based on the obtained acoustic waves. A machine learning analysis is used to determine formation slowness based on the determined signal properties and a downhole operational parameter is adjusted based on the determined formation slowness.

A system and method for forming a seismic image of a subterranean region of interest are provided. The method includes obtaining an observed seismic dataset for the subterranean region of interest and determining a plurality of common-offset sections from the observed seismic dataset. The method further includes determining stochastically migrated common-offset sections for each of the common-offset sections and forming a stochastic image gathers from the plurality of stochastically migrated common-offset sections. The method still further includes forming the seismic image by stacking each of the plurality of stochastically migrated common-offset sections.

A method includes receiving seismic data for a geologic region of the Earth; building a velocity model of the geologic region of the Earth; selecting at least one mode of multiple and corresponding travel time data from a data storage where the travel time data correspond to at least one complex ray signature in the geologic region of the Earth and are based at least in part on the velocity model; performing migration on the seismic data using at least the selected travel time data to generate processed seismic data; and rendering an image of the geologic region of the Earth to a display where the image includes at least a multiple image.

Systems and methods are provided to correct seismic data for the undesired effects caused by near surface velocity variations. In one embodiment, a method includes receiving travel time data for a near surface region and estimating an initial velocity model for the near surface region using the travel time data. The method can include updating the velocity model by performing an inversion iteration of including inversion of travel times to estimate slowness. The process can also include calculating at least one long-wavelength static for the near surface region. The long-wavelength statics may be used to correct for undesired effects caused by near surface velocity variations.

A computer-implemented method can include the following. Seismic vibratory waves through the Earth along a selected vector path are received. An initial value is selected for a first arrival for each of the seismic vibratory waves. Initial values are determined for travel times and velocities of the seismic vibratory waves. Reversed signs of amplitudes of the seismic vibratory waves are determined and corrected. Time intervals are determined based on the initial values of the travel times. Time windowing and filtering in a frequency domain are performed. Final values are determined for first arrivals and travel times for each of the seismic vibratory waves based on the time windowing and filtering. Final values are determined for velocities of the seismic vibratory waves.

A method of predicting parameters of an earthquake uses an array of ionosondes to scan an observed volume of an ionosphere located above a seismically active zone. The method includes monitoring ionograms provided by the array of ionosondes; detecting the presence of at least one seismic-induced irregularity (SII); determining a first predicted parameter corresponding to an epicenter location; and determining one or more predicted parameters selected from a group consisting of a magnitude, a time of occurrence, and a hypocenter depth. Algorithms for calculating the predicted parameters are presented in detail.

A method and system for measuring a compressional and a shear slowness. The method may comprise disposing a downhole tool into a wellbore. The downhole tool may comprise a transmitter, wherein the transmitter is a monopole, and a receiver, wherein the receiver is a monopole receiver. The method may further comprise broadcasting the sonic waveform into the formation penetrated by the wellbore, recording a reflected wave on one or more receivers, wherein the reflected wave is a compressional wave or a shear wave, processing the reflected wave into at least one measurement, and applying a validation scheme to the at least one measurement. The system may be a downhole tool comprising a transmitter configured to transmit a sonic waveform into a formation, wherein the transmitter is a monopole, and a receiver configured to record a reflected wave, wherein the receiver is a monopole receiver.