Chevron U.s.a. Inc.

The Texas A&m University System

Reynaldo Cardona

Prasenjit Roy

Anandaroop Ray

Shuxing Cheng

David C Bartel

Zhao Zhang

Kellen Leigh Gunderson

Yang Zhang

Xinfa Zhu

Michael Gordon Greene

Dileep K Tiwary

Kabilan Krishnamurthy

Mingya Chen

Zhangyang Wang

Ziyu Jiang

Bassel Mouloud Almoughraby

Yong Hua

Kun Fu

Aygul Kostinovsky

Miguel O Ascanio Regalado

Damian O'Grady

James Magill

Jacob G Tesfaye

Mason Edwards

Michael Greene

Ashley Elizabeth Shuler

Jacob Tesfaye

Well data (e.g., well log) may be divided into multiple segments, and different samplings of data in the individual segments may be performed to increase the amount of data that is used to train a seismic inversion model. Synthetic well data may be generated from real well data to increase the amount of well data from which sampling is performed.

Training data for machine learning seismic inversion

Systems and methods are disclosed for identifying subsurface features as a function of position in a subsurface volume of interest. Exemplary implementations may include obtaining target subsurface data; obtaining a conditioned subsurface feature model; applying the conditioned subsurface feature model to the target subsurface data, which may include generating convoluted target subsurface data by convoluting the target subsurface data; generating target subsurface feature map layers by applying filters to the convoluted target subsurface data; detecting potential target subsurface features in the target subsurface feature map layers; masking the target subsurface features; and estimating target subsurface feature data by linking the masked subsurface features to the target subsurface feature data.

Systems and methods for identifying subsurface features as a function of position in a subsurface volume of interest

Systems, devices, and methods are disclosed for identifying subsurface features as a function of position in a subsurface volume of interest. A computer-implemented method may include obtaining training subsurface data and corresponding training subsurface feature data; obtaining an initial subsurface feature model including tiers of elements; generating a conditioned subsurface feature model by training the initial subsurface feature model using the training subsurface data and the corresponding training subsurface feature data; and storing the conditioned subsurface feature model in the non-transient electronic storage.

Systems and methods for identifying subsurface features as functions of feature positions in a subsurface volume of interest

Methods and systems for calibrating depth in a well to seismic data in a subsurface volume of interest are disclosed. Exemplary implementations may: obtain well data corresponding to the well in the subsurface volume of interest; convert the well data to converted well data; obtain a seismic trace and a corresponding wavelet; generate a transform model; apply the transform model to the converted well data to transform the converted well data into transformed well data; apply the corresponding wavelet to the transformed well data to generate a modified signal; generate a correspondence between the modified signal and the seismic trace; repeat one or more steps to select a given modified signal; and calibrate the well data to the seismic trace.

Methods and systems for calibrating depth in a well to seismic data in a subsurface volume of interest

A method is described for seismic amplitude analysis including receiving a seismic dataset representative of a subsurface volume of interest wherein the seismic dataset includes an angle or angle stack dimension; select a plurality of sets of sub-cubes in the seismic dataset wherein each set of sub-cubes includes a plurality of the angles or the angle stacks; compute standard score statistics for each of the plurality of sub-cubes; identify amplitude variation with angle (AVA) anomalies based on the standard score statistics for each of the set of sub-cubes; classify the AVA anomalies to generate classified AVA anomalies; and displaying, on a user interface, the classified AVA anomalies as a graphical display. The method is executed by a computer system.

System and method for seismic amplitude analysis

Systems and methods for refining estimated effects of parameters on amplitudes are disclosed. Exemplary implementations may: (a) obtain ranges of parameter values for individual parameters within a subsurface region of interest; (b) generate a first model of the subsurface region of interest; (c) calculate a synthetic seismogram from the first model to determine corresponding amplitudes; (d) store results of applying the synthetic seismogram; (e) repeat steps (b)-(d) for multiple additional models; (f) obtain a subsurface distribution; (g) apply the subsurface distribution to the multiple models and the corresponding amplitudes; (h) generate a representation; and (i) display the representation.

Systems and methods for refining estimated effects of parameters on amplitudes

A method is described for generating an improved digital image for a subsurface volume of interest that allows analysis of the depositional settings of rock facies in a subsurface volume of interest. The method may include identifying at least three different rock facies in the well log data; estimating a compaction trend for each of the at least three rock facies identified in the well log data to create at least three compaction trends; transforming the velocity model to produce a trend-match volume using the at least three compaction trends; and superimposing the trend-match volume and the seismic image to generate a digital image containing information regarding both structural features and stratigraphic features of the subsurface volume of interest. The method may be executed by a computer system.

System and method for analysis of depositional settings of subsurface reservoirs

Growing community of inventors

Houston, TX, United States of America

Reynaldo Cardona