公开(公告)号：US20240371154A1

公开(公告)日：2024-11-07

申请号：US18312084

申请日：2023-05-04

Applicant: Landmark Graphics Corporation

Inventor： Bilal Hungund ,  Gurunath Gandikota ,  Geetha Nair

IPC: G06V20/13 ,  G06Q50/26

Abstract: A method for determining an emissions associated with hydrocarbon recovery of a hydrocarbon site within a geographic region, the method comprises selecting the hydrocarbon site for which to determine the emissions. The method comprises determining current values of hydrocarbon related attributes that affect emissions at the hydrocarbon site for a current time frame. The method comprises inputting the current values of the hydrocarbon related attributes related to emissions at the hydrocarbon site into a learning machine to generate an emissions factor for each of the hydrocarbon related attributes that affect the emissions at the hydrocarbon site.

公开(公告)号：US20250111106A1

公开(公告)日：2025-04-03

申请号：US18477792

申请日：2023-09-29

Applicant: Landmark Graphics Corporation

Inventor： Mrigya Fogat ,  Estanislao Nicolás Kozlowski ,  Soumili Das ,  Shreshth Srivastav ,  Andrew Davies ,  Geetha Nair

IPC: G06F30/27

Abstract: In general, in one aspect, embodiments relate to a method that includes selecting one or more stratigraphic forward models from a digital analogue library, generating one or more k-layers based at least in part on the one or more selected stratigraphic forward models and one or more generative machine learning models, and predicting thicknesses of one or more geological properties based at least in part on the one or more k-layers.

公开(公告)号：US20250122794A1

公开(公告)日：2025-04-17

申请号：US18379067

申请日：2023-10-11

Applicant: Landmark Graphics Corporation

Inventor： Ailneni Rakshitha Rao ,  Shashwat Verma ,  Geetha Nair

IPC: E21B47/008

Abstract: Systems and methods are described using a trained ML model to monitor, detect failure within, and schedule a remediation procedure (RP) for an operating ESP within a well. ESP status data including a time series comprising ESP input variables representing ESP state are collected from a sensor. Using fuzzy logic, the ESP status data is cleaned to remove abnormal data and used to generate fuzzy logic-based labels, each representing an ESP condition associated with ESP state. The fuzzy logic-based labels are segregated into processed labels used to populate each ML model feature. A selected, trained ML model with improved accuracy for ESP monitoring, failure detection, and RP scheduling for the ESP (based on specific ML model, well, and ESP), accepts the ML model features as input. An ESP failure alert is generated by the ML model based on the ESP status data. The RP is scheduled before ESP catastrophic failure.