China Petroleum Chemical Corporation

Yequan Chen

Fan Xia

Jianhua Yu

Jianxing Hu

Yi Tao

An approach for calibrating prestack seismic inversion is provided. This method includes selecting various features from inverted elastic properties to generate reservoir properties; fully connected neural network models are used to learn the mapping between the features and ground truth data at well locations; and the prediction is applied to generate one or more final models for the reservoir characterization of the whole survey region.

Method for calibrating prestack seismic inversion using fully connected neural networks

A method and system for generating and displaying a low frequency model for a seismic survey region are provided. The method and system may include defining a seismic survey geometry of the seismic survey region; processing seismic data to generate a stacked seismic data and well log data to obtain elastic attributes; importing stacked seismic data and processed well log data into the defined seismic survey geometry; generating envelope data using the stacked seismic data; generating a low frequency trace for each well; calculating a least-squares optimized coefficient model at each well location based upon the generated envelope data and the low frequency trace for each well; interpolating the coefficient model to the seismic survey geometry using a covariance technique and the imported stacked seismic data; and generating a three-dimensional low frequency model by inversion using the envelope data and the interpolated coefficient model for display.

Method and apparatus for building envelope guided low frequency model for seismic exploration of subsurface formations

A computing program product and method for interpolating wavelets coefficients and estimating spatial varying wavelets using the covariance interpolation method in the data space over a survey region having multiple well locations, are disclosed. The method and computing program product, embodied in a non-transitory computer readable device, that stores instructions for performing by a device are based on interpolating coefficient models in the data space domain using covariance analysis methods to overcome inaccuracy and instability issues commonly observed during wavelet estimation and interpolation.

Computing program product and method that interpolates wavelets coefficients and estimates spatial varying wavelets using the covariance interpolation method in the data space over a survey region having multiple well locations

Growing community of inventors

Houston, TX, United States of America

Yequan Chen