Efficient AI-Physics hybrid model with productive capabilities to reduce the time of history matching and scenario assessment; a case study: Minagish oil field

IF 1.3 4区工程技术 Q4 ENERGY & FUELS

Petroleum Science and Technology Pub Date : 2024-03-08 DOI:10.1080/10916466.2024.2324818

Ali Qubian, Mohammed Ahmad Zekraoui, Sina Mohajeri, Emad Mortezazadeh, Reza Eslahi, Maryam Bakhtiari, Abrar Al Dabbous, Asma Al Sagheer, Ali Alizadeh, Mostafa Zeinali

引用次数: 0

Abstract

This paper proposes a novel approach that combines physics-based numerical simulation with deep-learning neural networks to create an AI-Physics hybrid model for reservoir simulation. Our primary o...

查看原文本刊更多论文

具有生产能力的高效人工智能-物理混合模型，可缩短历史匹配和情景评估时间；案例研究：米纳吉什油田

本文提出了一种新方法，将基于物理的数值模拟与深度学习神经网络相结合，为储层模拟创建人工智能-物理混合模型。我们的主要目标是...

本文章由计算机程序翻译，如有差异，请以英文原文为准。

求助全文

约1分钟内获得全文求助全文

来源期刊

Petroleum Science and Technology 工程技术-工程：化工

CiteScore

2.90

自引率

13.30%

发文量

277

审稿时长

2.7 months

期刊介绍： The international journal of Petroleum Science and Technology publishes original, high-quality peer-reviewed research and review articles that explore: -The fundamental science of fluid-fluid and rock-fluids interactions and multi-phase interfacial and transport phenomena through porous media related to advanced petroleum recovery processes, -The application of novel concepts and processes for enhancing recovery of subsurface energy resources in a carbon-sensitive manner, -Case studies of scaling up the laboratory research findings to field pilots and field-wide applications. -Other salient technological challenges facing the petroleum industry.