An efficient two-stage Markov chain Monte Carlo method for dynamic data integration

被引：80

作者：

Efendiev, Y ^{[1
]}

Datta-Gupta, A

Ginting, V

Ma, X

Mallick, B

机构：

[1] Texas A&M Univ, Dept Math, College Stn, TX 77843 USA

[2] Texas A&M Univ, Inst Comp Sci, College Stn, TX 77843 USA

[3] Texas A&M Univ, Dept Petr Engn, College Stn, TX 77843 USA

[4] Texas A&M Univ, Dept Stat, College Stn, TX 77843 USA

来源：

WATER RESOURCES RESEARCH | 2005年 / 41卷 / 12期

关键词：

D O I：

10.1029/2004WR003764

中图分类号：

X [环境科学、安全科学];

学科分类号：

08 ; 0830 ;

摘要：

[1] In this paper, we use a two-stage Markov chain Monte Carlo (MCMC) method for subsurface characterization that employs coarse-scale models. The purpose of the proposed method is to increase the acceptance rate of MCMC by using inexpensive coarse-scale runs based on single-phase upscaling. Numerical results demonstrate that our approach leads to a severalfold increase in the acceptance rate and provides a practical approach to uncertainty quantification during subsurface characterization.

引用

页码：1 / 6

页数：6

共 18 条

[1] A new multistage groundwater transport inverse method: Presentation, evaluation, and implications [J].