1 code implementation • 1 Apr 2020 • Kailai Xu, Daniel Z. Huang, Eric Darve
We present the Cholesky-factored symmetric positive definite neural network (SPD-NN) for modeling constitutive relations in dynamical equations.
Numerical Analysis Numerical Analysis
3 code implementations • 24 Feb 2020 • Kailai Xu, Eric Darve
Our approach allows for the potential to solve and accelerate a wide range of data-driven inverse modeling, where the physical constraints are described by PDEs and need to be satisfied accurately.
Numerical Analysis Numerical Analysis
1 code implementation • 16 Dec 2019 • Kailai Xu, Dongzhuo Li, Eric Darve, Jerry M. Harris
Numerical tests demonstrate the feasibility of IAD for learning hidden dynamics in complicated systems of PDEs; additionally, by incorporating custom built state adjoint method codes in IAD, we significantly accelerate the forward and inverse simulation.
Numerical Analysis Numerical Analysis
1 code implementation • 16 Dec 2019 • Dongzhuo Li, Kailai Xu, Jerry M. Harris, Eric Darve
We describe a novel framework for PDE (partial-differential-equation)-constrained full-waveform inversion (FWI) that estimates parameters of subsurface flow processes, such as rock permeability and porosity, using time-lapse observed data.
Geophysics
3 code implementations • 15 Oct 2019 • Kailai Xu, Eric Darve
Many scientific and engineering applications are formulated as inverse problems associated with stochastic models.
Numerical Analysis Numerical Analysis
4 code implementations • 29 May 2019 • Daniel Z. Huang, Kailai Xu, Charbel Farhat, Eric Darve
Its counterparts, like piecewise linear functions and radial basis functions, are compared, and the strength of neural networks is explored.
Numerical Analysis Numerical Analysis Computational Physics
2 code implementations • 20 Dec 2018 • Kailai Xu, Eric Darve
Traditionally this problem can be solved with nonparametric estimation using the empirical characteristic functions (ECF), assuming certain regularity, and results to date are mostly in 1D.