A Physics-Based Data-Driven Model for History Matching, Prediction, and Characterization of Unconventional Reservoirs

被引：11

作者：

Zhang, Yanbin ^{[1
]}

He, Jincong ^{[1
]}

Yang, Changdong ^{[1
]}

Xie, Jiang ^{[1
]}

Fitzmorris, Robert ^{[2
]}

Wen, Xian-Huan ^{[3
]}

机构：

[1] Chevron Energy Technol Co, Richmond, CA 94802 USA

[2] Chevron Energy Technol Co, Reservoir Performance Serv Unit, Richmond, CA USA

[3] Chevron Energy Technol Co, Reservoir Performance Serv Unit, Reservoir Simulat & Optimizat Res Team, Richmond, CA USA

来源：

SPE JOURNAL | 2018年 / 23卷 / 04期

关键词：

GAS-RESERVOIRS; SIMULATION; WELL; FLOW;

D O I：

10.2118/191126-PA

中图分类号：

TE [石油、天然气工业];

学科分类号：

0820 ;

摘要：

We developed a physics-based data-driven model for history matching, prediction, and characterization of unconventional reservoirs. It uses 1D numerical simulation to approximate 3D problems. The 1D simulation is formulated in a dimensionless space by introducing a new diffusive diagnostic function (DDF). For radial and linear flow, the DDF is shown analytically to be a straight line with a positive or zero slope. Without any assumption of flow regime, the DDF can be obtained in a data-driven manner by means of history matching using the ensemble smoother with multiple data assimilation (ES-MDA). The history-matched ensemble of DDFs offers diagnostic characteristics and probabilistic predictions for unconventional reservoirs.

引用

下载

页码：1105 / 1125

页数：21

共 50 条

[21] History-Matching and Forecasting Production Rate and Bottomhole Pressure Data Using an Enhanced Physics-Based Data-Driven Simulator
Li Y.
Alpak F.O.
Jain V.
Lu R.
Onur M.
SPE Reservoir Evaluation and Engineering, 2023, 26 (03): : 957 - 974
[22] Hybrid RGNet: A physics-based model enhanced by machine learning for history matching, characterization and future prediction
Guo, Zhenyu (zhenyuguo2006@gmail.com), 2025, 246
[23] Physics-based and data-driven modeling for biomanufacturing 4.0
Ogunsanya, Michael
Desai, Salil
MANUFACTURING LETTERS, 2023, 36 : 91 - 95
[24] Data-driven physics-based modeling of pedestrian dynamics
Pouw, Caspar A. S.
Van Der Vleuten, Geert G. M.
Corbetta, Alessandro
Toschi, Federico
Physical Review E, 2024, 110 (06)
[25] INSIM-BHP: A physics-based data-driven reservoir model for history matching and forecasting with bottomhole pressure and production rate data under waterflooding
Li, Ying
Onur, Mustafa
JOURNAL OF COMPUTATIONAL PHYSICS, 2023, 473
[26] A hybrid physics-based and data-driven method for gear contact fatigue life prediction
Zhou, Changjiang
Wang, Haoye
Hou, Shengwen
Han, Yong
INTERNATIONAL JOURNAL OF FATIGUE, 2023, 175
[27] A new physics-based data-driven guideline for wear modelling and prediction of train wheels
Zeng, Yuanchen
Song, Dongli
Zhang, Weihua
Zhou, Bin
Xie, Mingyuan
Tang, Xu
WEAR, 2020, 456 (456-457)
[28] Data-driven prediction of keyhole features in metal additive manufacturing based on physics-based simulation
Xie, Ziyuan
Chen, Fan
Wang, Lu
Ge, Wenjun
Yan, Wentao
JOURNAL OF INTELLIGENT MANUFACTURING, 2024, 35 (05) : 2313 - 2326
[29] A prediction method for ship added resistance based on symbiosis of data-driven and physics-based models
Yang, Ke
Duan, Wenyang
Huang, Limin
Zhang, Peixin
Ma, Shan
OCEAN ENGINEERING, 2022, 260
[30] Combining physics-based and data-driven methods in metal stamping
Abanda, Amaia
Arroyo, Amaia
Boto, Fernando
Esteras, Miguel
JOURNAL OF INTELLIGENT MANUFACTURING, 2024,

← 1 2 3 4 5 →