中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 力学研究所
  3. 中国科学院力学研究所
  4. 非线性力学国家重点实验室
Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping

文献类型：期刊论文

作者Xu ZY(许昭越)1,2; Wang SZ(王士召)1,2; Zhang XL(张鑫磊)1,2; He GW(何国威)1,2
刊名JOURNAL OF COMPUTATIONAL PHYSICS
出版日期2024-10-01
卷号514页码:20
关键词Optimal sensor placement GradCAM CNN Ensemble Kalman method
ISSN号0021-9991
DOI10.1016/j.jcp.2024.113224
通讯作者Wang, Shizhao(wangsz@lnm.imech.ac.cn) ; Zhang, Xin-Lei(zhangxinlei@imech.ac.cn)
英文摘要We introduce an optimal sensor placement method using convolutional neural networks for ensemble -based data assimilation. The proposed method utilizes the gradient -weighted class activation mapping of the convolutional neural networks to identify important regions for assimilation processes. It is achieved by using the initial ensemble of samples for data assimilation as training data to construct a convolutional neural network -based surrogate model. In doing so, the method can estimate optimal sensor locations in an a priori manner, allowing for sensor placement before conducting data assimilation processing. Moreover, the gradientweighted class activation mapping is used to alleviate the effect of error accumulation during the backpropagation process through global averaging. Further, these observation sensors are incorporated to reconstruct mean turbulent flow fields based on the ensemble Kalman method. The proposed optimal sensor placement method is applied to two flow applications with complex geometries, i.e., flows around periodic hills and an axisymmetric body of revolution. Both cases demonstrate that the proposed method can significantly reduce the number of sensors without sacrificing the accuracy of the reconstructed flow field.
分类号一类/力学重要期刊
WOS关键词NEURAL-NETWORK ; FLUID-FLOW ; MODEL ; OPTIMIZATION ; SIMULATION ; ALGORITHM ; SPARSE ; DRIVEN
资助项目NSFC Basic Science Center Program for 'Multiscale Problems in Nonlinear Mechanics'[11988102] ; National Natural Science Foundation of China[92252203] ; National Natural Science Foundation of China[91952301] ; National Natural Science Foundation of China[12102435] ; CAS Project for Young Scientists in Basic Research[YSBR-087] ; CAST Young Elite Scientists Sponsorship Program[2022QNRC001]
WOS研究方向Computer Science ; Physics
语种英语
WOS记录号WOS:001264450400001
资助机构NSFC Basic Science Center Program for 'Multiscale Problems in Nonlinear Mechanics' ; National Natural Science Foundation of China ; CAS Project for Young Scientists in Basic Research ; CAST Young Elite Scientists Sponsorship Program
其他责任者Wang, Shizhao ; Zhang, Xin-Lei
源URL[http://dspace.imech.ac.cn/handle/311007/95983]  
专题力学研究所_非线性力学国家重点实验室
作者单位1.Univ Chinese Acad Sci, Sch Engn Sci, Beijing 100049, Peoples R China
2.Chinese Acad Sci, LNM, Inst Mech, Beijing 100190, Peoples R China;
推荐引用方式
GB/T 7714		 Xu ZY,Wang SZ,Zhang XL,et al. Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping[J]. JOURNAL OF COMPUTATIONAL PHYSICS,2024,514:20.
APA 许昭越,王士召,张鑫磊,&何国威.(2024).Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping.JOURNAL OF COMPUTATIONAL PHYSICS,514,20.
MLA 许昭越,et al."Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping".JOURNAL OF COMPUTATIONAL PHYSICS 514(2024):20.

入库方式： OAI收割

来源：力学研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。