Probabilistic error estimation for non-intrusive reduced models learned from data of systems governed by linear parabolic partial differential equations

Probabilistic error estimation for non-intrusive reduced models learned from data of systems governed by linear parabolic partial differential equations
复制标题

从线性抛物型偏微分方程控制的系统数据中学习的非侵入式简化模型的概率误差估计

DOI:
10.1051/m2an/2021010
复制
发表时间:
2021
期刊:
ESAIM: Mathematical Modelling and Numerical Analysis
影响因子:
--
通讯作者:
Peherstorfer, Benjamin
Peherstorfer, Benjamin
中科院分区:
--
文献类型:
--
作者:
Uy, Wayne Isaac;Peherstorfer, Benjamin

文献摘要

参考文献

被引文献

相似文献

这项工作推导了一种基于残差的后验误差估计器,用于通过非侵入式模型简化从高维系统的数据中学习的简化模型,该高维系统由具有控制输入的线性抛物型偏微分方程控制。结果表明,误差估计器所需的量可以通过非侵入式方式从初始条件、控制输入和高维解轨迹等数据中精确地获得最小二乘问题的解,或者在概率意义上有界。计算过程遵循离线/在线分解。在离线(训练)阶段,高维系统以黑盒方式明智地求解,以生成数据并设置误差估计器。在在线阶段,估计器用于限制新初始条件和新控制输入的简化模型预测的误差,而无需求助于高维系统。数值结果证明了所提出的方法从数据到简化模型再到经过认证的预测的工作流程。
This work derives a residual-baseda posteriorierror estimator for reduced models learned with non-intrusive model reduction from data of high-dimensional systems governed by linear parabolic partial differential equations with control inputs. It is shown that quantities that are necessary for the error estimator can be either obtained exactly as the solutions of least-squares problems in a non-intrusive way from data such as initial conditions, control inputs, and high-dimensional solution trajectories or bounded in a probabilistic sense. The computational procedure follows an offline/online decomposition. In the offline (training) phase, the high-dimensional system is judiciously solved in a black-box fashion to generate data and to set up the error estimator. In the online phase, the estimator is used to bound the error of the reduced-model predictions for new initial conditions and new control inputs without recourse to the high-dimensional system. Numerical results demonstrate the workflow of the proposed approach from data to reduced models to certified predictions.
DOI: 10.1137/18m120364x
发表时间: 2018
期刊: SIAM J. Sci. Comput.
影响因子: --
作者:
K. Smetana;O. Zahm;A. Patera
通讯作者: A. Patera
DOI: 10.1137/15m1041432
发表时间: 2016-01-01
影响因子: 3.1
作者:
Antoulas, A. C.;Gosea, I. V.;Ionita, A. C.
通讯作者: Ionita, A. C.
DOI: 10.1137/20m1331718
发表时间: 2021-01-01
影响因子: 1.5
作者:
Bujanovic, Zvonimir;Kressner, Daniel
通讯作者: Kressner, Daniel
DOI: 10.1051/cocv/2017011
发表时间: 2018
期刊: ESAIM: Control, Optimisation and Calculus of Variations
影响因子: --
作者:
A. Schmidt;B. Haasdonk
通讯作者: B. Haasdonk
DOI: 10.1051/m2an/2012029
发表时间: 2010
期刊: Mathematical Modelling and Numerical Analysis
影响因子: --
作者:
Alexandre Janon;M. Nodet;C. Prieur
通讯作者: C. Prieur