Proxy modeling pf reservoir hydrodynamics with graph neural networks

Author:

Umanovskiy Arseny W.1

Affiliation:

1. The Gubkin Russian State University of Oil and Gas

Abstract

The primary goal of hydrodynamic reservoir modeling is to predict the production wells performance, or more precisely, the dependence of this performance on the choice of the reservoir development plan. The achievement of this goal is hampered by the lack of accurate information about the properties of the reservoir. These properties have to be inferred from indirect data, first of all from the historical indicators of already functioning wells. This information is used to perform the adaptation of the numerical reservoir model or proxy models, which are less informative but have the advantage of speed and flexibility. The article proposes a reservoir proxy modeling method based on the use of a specific artificial neural network (ANN). The novel graph convolutional architecture of the ANN takes in the graph data describing the reservoir. The edges and vertices of the graph contain a spatial description of the reservoir along with the history of the well performance. Such architecture makes it possible to train the neural network for a whole class of situations instead of only one case. In accordance with the principles of the Physics-Informed Neural Networks (PINN), the task of the ANN is to derive a kind of formulation of a physical law guiding the system, rather than just a correlation between time series. The advantages of this approach over most ANN-based proxy models used today are, firstly, speed: adjustment to historical data and forecast output are made in seconds even for hundreds of wells; secondly, a certain degree of physical meaningfulness.

Publisher

Tyumen State University

Subject

General Earth and Planetary Sciences,General Environmental Science

Reference27 articles.

1. Ababkov А. V., Vasilyev V. M., Khisamutdinov N. I., Safiullin I. R., Shaislamov V. Sh. 2014. “Express method for assessing the degree of interaction between wells using frequency analysis of data from the history of operation of injection and production wells”. Oilfield business, no. 7, pp. 10-13. [In Russian]

2. Brilliant L. S., Dulkarnaev M. R., Danko M. Yu., Olisheva A. O., Nabiev D. Kh., Khutornaya A. I., Malkov I. N. 2022. “Oil production management based on neural network optimization of well operation modes at the site of pilot works of the YuV1 formation of the Vatyeganskoye field TPE ‘Povkhneftegaz’”. Georesources, no. 1 (24), pp. 3-15. [In Russian]

3. Proskurin V. A., Khisamutdinov N. I., Antonov M. S., Sagitov D. K. 2013. “Methods for assessing the effectiveness of the formation of a waterflooding system at the site of the West-Ust-Balykskoye field”. Automation, telemechanization and communication in the oil industry, no. 6, pp. 36-38. [In Russian]

4. Stepanov S. V., Sokolov S. V., Ruchkin A. A., Stepanov A. V., Knyazev A. V., Korytov A. V. 2018. “The problems of assessing the mutual influence of production and injection wells based on mathematical modeling”. Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy, no. 3 (4), pp. 146-164. [In Russian]

5. Stepanov S. V., Beckman A. D., Ruchkin A. A., Pospelova T. A. 2022. “Maintenance of oil field development using CRM models”. IPC Express. [In Russian]

Cited by 1 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. Simulation of liquid production and water cut dynamics using fluid flow model and neural networks;Tyumen State University Herald. Physical and Mathematical Modeling. Oil, Gas, Energy;2023-07-07

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3