Disclosed are a method and apparatus for estimating S-wave velocities by learning well logs, whereby the method includes a model formation step of forming an S-wave estimation model to output S-wave velocities corresponding to measured depth when the well logs are input based on train data sets including train data having values of multiple factors included in the well logs, the values being arranged corresponding to measured depth, and label data having S-wave velocities corresponding to measured depth as answers, and an S-wave velocity estimation step of inputting unseen data having values of multiple factors included in well logs acquired from a well at which S-wave velocities are to be estimated, the values being arranged corresponding to measured depth, to the S-wave estimation model to estimate S-wave velocities corresponding to measured depth.

A method, including: generating a velocity model for a subsurface region of the Earth by using a full wavefield inversion process; generating an impedance model for the subsurface region of the Earth by using a full wavefield inversion process; and estimating pore pressure at a prediction site in the subsurface region by integrating the velocity model and the impedance model with a velocity-based pore pressure estimation process.

A method and system for modeling a subsurface region include applying a trained machine learning network to an initial petrophysical parameter estimate to predict a geologic prior model; and performing a petrophysical inversion with the geologic prior model, geophysical data, and geophysical parameters to generate a rock type probability model and an updated petrophysical parameter estimate. Embodiments include managing hydrocarbons with the rock type probability model. Embodiments include checking for convergence of the updated petrophysical parameter estimate; and iteratively: applying the trained machine learning network to the updated petrophysical parameter estimate of a preceding iteration to predict an updated rock type probability model and another geologic prior model; performing a petrophysical inversion with the updated geologic prior model, geophysical seismic data, and geophysical elastic parameters to generate another rock type probability model and another updated petrophysical parameter estimate; and checking for convergence of the updated petrophysical parameter estimate.

In an example method, one or more processors receive a plurality of rock fragment images. Each of the rock fragment images represents respective rock fragments obtained from a subsurface formation during well bore drilling. The one or more processors select one or more portions of the rock fragment images, and generate a geological formation image based on the one or more selected portions of the rock fragment images. The geological formation image is indicative of one or more geological characteristics of the subsurface formation along the well bore.

A system for estimating a rock property away from a well may include one or more hardware processors configured to access acquired three-dimensional (3D) seismic data that includes seismic traces from a 3D seismic survey of an area of interest. The system may also include a multi-head Convolutional Neural Network (CNN) model. The multi-head CNN model may include a plurality of kernels of various sizes for determining spatial and temporal relationships of the captured 3D seismic data at different resolutions. The multi-head CNN model may be trained to generate an estimated rock property value of a formation zone included in the area of interest, away from the well. The one or more hardware processors are further configured to update a drilling program for a production system based on the estimated rock property value. The drilling program may be executed on a computing device of the production system.

Systems, methods, and devices for wireless communication that support mechanisms for identifying hyper frame number (HFN) desynchronization conditions and/or for triggering HFN resynchronization in a wireless communication system. In aspects, an HFN desynchronization condition is identified based on Ethernet frame validation. For example, aspects of the present disclosure provide mechanisms for validating and Ethernet frame. An HFN desynchronization condition is identified or detected when an Ethernet frame is determined to be corrupt based on the Ethernet frame validation in accordance with aspects herein. In some aspects, such as in Ethernet header compression (EHC) protocol implementations, an HFN desynchronization condition may be identified based on a determination that a deciphered context identification (CID) is not a valid CID (e.g., is not a CID in a set of valid CIDs).

Systems and methods are disclosed that include generating reservoir property profiles corresponding to reservoir properties for pseudo wells based on reservoir data, generating seismic attributes for the pseudo wells, and training a machine learning model by comparing the reservoir property profiles against the seismic attributes. In this manner, the machine learning model may be used to predict reservoir properties for use with seismic exploration above a region of a subsurface that contains structural or stratigraphic features conducive to a presence, migration, or accumulation of hydrocarbons.

A method of low-frequency seismic data enhancement for improving the characterization precision of a deep carbonate reservoir includes: first performing inversions on an input seismic data set to obtain the corresponding reflection coefficients and average seismic wavelet; then constructing a seismic wavelet with rich low-frequency information; and finally, performing convolution on the seismic wavelet with rich low-frequency information and the reflection coefficients to obtain seismic data with rich low-frequency information and enhanced low-frequency energy. In the present invention, changes of the seismic data in a work area in transverse and longitudinal directions are taken into consideration, and processing parameters can be quickly determined according to actual conditions of the work area to obtain an optimal processing effect. In this way, the characterization quality of geological anomalies, such as a fault, a fracture system, or the like, in a deep carbonate reservoir can be improved significantly.

A method, including performing, with a computer, up/down separation of geophysical data, which produces an approximate up-going wavefield and an approximate down-going wavefield; creating an areal source based at least in part on the down-going wavefield; and performing, with a computer, a full wavefield inversion process with the areal source, and an objective function measuring a misfit between modeled up-going wavefields and recorded up-going wavefields, wherein the full wavefield inversion process generates a final subsurface physical property model.

The present invention relates to a one-way wave equation prestack depth migration method using an elastic generalized-screen (EGS) wave propagator capable of efficiently expressing the movement of an elastic wave passing through a mutual mode conversion between a P-wave and an S-wave while propagating boundary surfaces of an underground medium, by expanding, to an elastic wave equation, a conventional scalar generalized-screen (SGS) technique capable of quickly calculating the propagation of a wave in a medium in which there is a horizontal speed change, and according to the present invention, provided is a prestack EGS migration method for seismic wave multi-component data, which: can calculate a wave field with higher accuracy in a medium having a complex structure by expanding up to a second term of a Taylor series expansion of a vertical slowness term of a propagator; includes a mode separation operator in the propagator so as to directly use a shot gather as a migration input, without the need to separate multi-component data into a P-wave and an S-wave, enabling P-wave and S-wave image sections to be generated; and is configured to improve the quality of an S-wave migration image by correcting a polarity conversion in a wave number-frequency domain prior to S-wave imaging.