• Corpus ID: 155100084

The Statistical Finite Element Method

@article{Girolami2019TheSF,
  title={The Statistical Finite Element Method},
  author={Mark A. Girolami and Alastair Gregory and Ge Yin and Fehmi Cirak},
  journal={arXiv: Methodology},
  year={2019}
}
The finite element method (FEM) is one of the great triumphs of modern day applied mathematics, numerical analysis and algorithm development. Engineering and the sciences benefit from the ability to simulate complex systems with FEM. At the same time the ability to obtain data by measurements from these complex systems, often through sensor networks, poses the question of how one systematically incorporates data into the FEM, consistently updating the finite element solution in the face of… 

Figures from this paper

Prior-informed Uncertainty Modelling with Bayesian Polynomial Approximations
TLDR
It is shown that prior knowledge of sparsity in the model, approximate knowledge of the polynomial coefficients, and correlated models that share similar functional and/or physical behaviours can be leveraged to produce orthogonalPolynomial approximations with enhanced predictive accuracy through a Bayesian framework.
Variational Autoencoding of PDE Inverse Problems
TLDR
This work folds the mechanistic model into a flexible data-driven surrogate to arrive at a physically structured decoder network that provides accelerated inference for the Bayesian inverse problem, and can act as a drop-in regulariser that encodes a-priori physical information.

References

SHOWING 1-10 OF 25 REFERENCES
Subdivision surfaces: a new paradigm for thin‐shell finite‐element analysis
We develop a new paradigm for thin-shell finite-element analysis based on the use of subdivision surfaces for (i) describing the geometry of the shell in its undeformed configuration, and (ii)
Inverse problems: A Bayesian perspective
TLDR
The Bayesian approach to regularization is reviewed, developing a function space viewpoint on the subject, which allows for a full characterization of all possible solutions, and their relative probabilities, whilst simultaneously forcing significant modelling issues to be addressed in a clear and precise fashion.
Further analysis of multilevel Monte Carlo methods for elliptic PDEs with random coefficients
TLDR
It is proved that convergence of the multilevel Monte Carlo algorithm for estimating any bounded, linear functional and any continuously Fréchet differentiable non-linear functional of the solution is convergence.
Analysis Of The Finite Element Method
Fully C1-conforming subdivision elements for finite deformation thin-shell analysis
We have extended the subdivision shell elements of Cirak et al. [18] to the finite-deformation range. The assumed finite-deformation kinematics allows for finite membrane and thickness stretching, as
Simulating Normalizing Constants: From Importance Sampling to Bridge Sampling to Path Sampling
TLDR
It is shown that the acceptance ratio method and thermodynamic integration are natural generalizations of importance sampling, which is most familiar to statistical audiences.
Subdivision shells with exact boundary control and non‐manifold geometry
We introduce several new extensions to subdivision shells that provide an improved level of shape control over shell boundaries and facilitate the analysis of shells with non‐smooth and non‐manifold
Bayesian Calibration of computer models
TLDR
A Bayesian calibration technique which improves on this traditional approach in two respects and attempts to correct for any inadequacy of the model which is revealed by a discrepancy between the observed data and the model predictions from even the best‐fitting parameter values is presented.
...
...