公开(公告)号：US20190170888A1

公开(公告)日：2019-06-06

申请号：US15833203

申请日：2017-12-06

Applicant: CHEVRON U.S.A. INC.

Inventor： Adam Dean HALPERT ,  Laura L. BANDURA ,  Shuxing CHENG ,  Konstantin OSYPOV

IPC: G01V1/28 ,  G01V1/34 ,  G01V1/36

Abstract: Systems and methods for training a model that refines estimated parameter values include computer processors and non-transitory electronic storage that stores subsurface map data sets that correspond to different subsurface volumes of interest, the system configured to obtain training data including unrefined subsurface map data sets specifying estimated parameter values of a first parameter as a function of position within corresponding subsurface volumes of interest, obtain an initial seismic mapping model, generate a conditioned seismic mapping model, and store the conditioned seismic mapping model in the electronic storage.

公开(公告)号：US20220058440A1

公开(公告)日：2022-02-24

申请号：US17410400

申请日：2021-08-24

Applicant: CHEVRON U.S.A. INC.

Inventor： Xin FENG ,  Shuxing CHENG ,  Tamas NEMETH ,  Irene E. STEIN ,  Larry A. BOWDEN JR. ,  Adam M. REEDER

IPC: G06K9/62 ,  G06N3/08

Abstract: Embodiments of labeling an unlabeled dataset are provided. One embodiment comprises (a) obtaining a labeled dataset comprising a first plurality of data inputs and corresponding labels; (b) training a classification model using the labeled dataset; (c) obtaining the unlabeled dataset comprising a second plurality of data inputs without labels; (d) applying the classification model to the unlabeled dataset to generate a predicted label for each data input of the unlabeled dataset; (e) determining a verification quantity of the predicted labels to be verified by a user; (f) obtaining a verification dataset for the verification quantity of the predicted labels verified by the user; (g) updating the classification model using the verification dataset; and (h) applying the updated classification model to the remaining predicted labels that did not undergo verification and updating in response to the updated classification model. The verification dataset comprises an update to at least one predicted label.