公开(公告)号：US20230145880A1

公开(公告)日：2023-05-11

申请号：US17907751

申请日：2021-03-23

Applicant: SHELL OIL COMPANY

Inventor： John SOLUM ,  Oriol FALIVENE ALDEA ,  Pedram ZARIAN ,  David Lawrence KIRSCHNER ,  Neal Christian AUCHTER ,  Antonino CILONA

IPC: G06T7/10 ,  G06V20/70

CPC classification number: G06T7/10 ,  G06V20/70

Abstract: A method for predicting an occurrence of a geological feature in a geologic core image uses a backpropagation-enabled segmentation process trained by inputting multiple training geologic core images and a set of associated labels of geological features, iteratively computing a prediction of the probability of occurrence of the geological feature for the training images and adjusting the parameters in the backpropagation-enabled segmentation model until the model is trained. The trained backpropagation-enabled segmentation model is used to predict the occurrence of the geological features in non-training geologic core images. Geological features to be predicted with this method include structural features (such as veins, fractures, bedding contacts, etc.), and stratigraphic features (such as lithologic types, sedimentary structures, sedimentary facies, etc.).

公开(公告)号：US20230289941A1

公开(公告)日：2023-09-14

申请号：US17999630

申请日：2021-06-22

Applicant: SHELL OIL COMPANY

Inventor： David Lawrence KIRSCHNER ,  John SOLUM

IPC: G06T7/00 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06T7/11

CPC classification number: G06T7/0002 ,  G06T7/11 ,  G06V10/764 ,  G06V10/774 ,  G06V10/82 ,  G06T2207/20076 ,  G06T2207/20081 ,  G06T2207/20084 ,  G06T2207/30181

Abstract: A method for predicting an occurrence of a structural feature in a core image using a backpropagation-enabled process trained by inputting a set of training images of a core image, iteratively computing a prediction of the probability of occurrence of the structural feature for the set of training images and adjusting the parameters in the backpropagation-enabled model until the model is trained. The trained backpropagation-enabled model is used to predict the occurrence of the structural features in non-training core images. The set of training images may include non-structural features and/or simulated data, including augmented images and synthetic images.