典型文献
Sequential Gaussian simulation for geosystems modeling:A machine learning approach
文献摘要：
Sequential Gaussian Simulation (SGSIM) as a stochastic method has been developed to avoid the smooth-ing effect produced in deterministic methods by generating various stochastic realizations.One of the main issues of this technique is,however,an intensive computation related to the inverse operation in solving the Kriging system,which significantly limits its application when several realizations need to be produced for uncertainty quantification.In this paper,a physics-informed machine learning (PIML)model is proposed to improve the computational efficiency of the SGSIM.To this end,only a small amount of data produced by SGSIM are used as the training dataset based on which the model can dis-cover the spatial correlations between available data and unsampled points.To achieve this,the govern-ing equations of the SGSIM algorithm are incorporated into our proposed network.The quality of realizations produced by the PIML model is compared for both 2D and 3D cases,visually and quantita-tively.Furthermore,computational performance is evaluated on different grid sizes.Our results demon-strate that the proposed PIML model can reduce the computational time of SGSIM by several orders of magnitude while similar results can be produced in a matter of seconds.
文献关键词：
中图分类号：
作者姓名：
Tao Bai;Pejman Tahmasebi
作者机构：
College of Engineering and Applied Science,University of Wyoming,Laramie,WY 82071,USA
文献出处：
引用格式：
[1]Tao Bai;Pejman Tahmasebi-.Sequential Gaussian simulation for geosystems modeling:A machine learning approach)[J].地学前缘（英文版）,2022(01):1-14
A类：
geosystems,SGSIM,PIML,unsampled
B类：
Sequential,Gaussian,simulation,modeling,machine,learning,approach,Simulation,stochastic,been,developed,avoid,smooth,effect,produced,deterministic,methods,by,generating,various,realizations,One,main,issues,this,technique,however,intensive,related,inverse,operation,solving,Kriging,which,significantly,limits,application,when,several,need,uncertainty,quantification,In,paper,physics,informed,proposed,improve,computational,efficiency,To,end,only,small,amount,used,training,dataset,dis,cover,spatial,correlations,between,available,points,achieve,govern,equations,algorithm,incorporated,into,our,network,quality,compared,both,2D,cases,visually,quantita,tively,Furthermore,performance,evaluated,different,grid,sizes,Our,results,demon,strate,that,reduce,orders,magnitude,while,similar,matter,seconds
AB值：
0.526939
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
