公开(公告)号：US20210406512A1

公开(公告)日：2021-12-30

申请号：US16911258

申请日：2020-06-24

Applicant: SHELL OIL COMPANY

Inventor： David A. LAVALLEE ,  Russell David POTTER ,  Oliver MUELLENHOFF ,  Benjamin Thomas KING ,  Stephen Edward KEEDWELL ,  Jason Dane MCCONOCHIE ,  Paul Henry GARDNER

IPC: G06K9/00 ,  G01V8/00 ,  G06N20/00 ,  G06K9/62

Abstract: A method for assessing risk to a marine hydrocarbon recovery operation involves collecting a set of training images and labeling sea surface anomalies on the set of training images. The set of training images and associated labels are used to train a model via backpropagation. A set of non-training images is collected and the trained model is applied to identify a potentially disruptive sea surface anomaly on the set of non-training images. Any risk to the marine hydrocarbon recovery operation by the potentially disruptive sea surface anomaly is then assessed.

公开(公告)号：US20210390343A1

公开(公告)日：2021-12-16

申请号：US17287562

申请日：2019-10-23

Applicant: SHELL OIL COMPANY

Inventor： David A. LAVALLEE ,  Russell David POTTER ,  Stephen Edward KEEDWELL ,  Oliver MUELLENHOFF ,  Benjamin Thomas KING

IPC: G06K9/62 ,  G06T7/70 ,  G06T7/10

Abstract: A backpropagation-enabled method for identifying a sea surface anomaly involves collecting an initial set of images and labeling the anomaly on the initial set of images. The initial set of images are selected from satellite-acquired images and/or simulated satellite images. The labels are used to train a model via backpropagation. A subsequent set of images, including satellite-acquired, airborne-acquired images, and combinations thereof, is collected and the trained model is applied to identify a sea surface anomaly on the subsequent set of images.