activity
20172021
most citedPhysics Constrained Learning for Data-driven Inverse Modeling from Sparse Observations

22 citations · 67 across the 9 of their papers we have counts for

collaborators
Showing 2020Show all

8 papers · 1 filter

physics.geo-ph2020

Integrating Deep Neural Networks with Full-waveform Inversion: Reparametrization, Regularization, and Uncertainty Quantification

Weiqiang Zhu, Kailai Xu, Eric Darve +2

Full-waveform inversion (FWI) is an accurate imaging approach for modeling velocity structure by minimizing the misfit between recorded and predicted seismic waveforms. However, th…

math.NA2020★ 18 cited

ADCME: Learning Spatially-varying Physical Fields using Deep Neural Networks

Kailai Xu, Eric Darve

ADCME is a novel computational framework to solve inverse problems involving physical simulations and deep neural networks (DNNs). This paper benchmarks its capability to learn spa…

cs.DC2020★ 5 cited

Distributed Machine Learning for Computational Engineering using MPI

Kailai Xu, Weiqiang Zhu, Eric Darve

We propose a framework for training neural networks that are coupled with partial differential equations (PDEs) in a parallel computing environment. Unlike most distributed computi…

math.NA2020

Solving Inverse Problems in Steady-State Navier-Stokes Equations using Deep Neural Networks

Tiffany Fan, Kailai Xu, Jay Pathak +1

Inverse problems in fluid dynamics are ubiquitous in science and engineering, with applications ranging from electronic cooling system design to ocean modeling. We propose a genera…

math.NA2020★ 17 cited

Inverse Modeling of Viscoelasticity Materials using Physics Constrained Learning

Kailai Xu, Alexandre M. Tartakovsky, Jeff Burghardt +1

We propose a novel approach to model viscoelasticity materials using neural networks, which capture rate-dependent and nonlinear constitutive relations. However, inputs and outputs…

math.NA2020

Learning Constitutive Relations using Symmetric Positive Definite Neural Networks

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. Instead of directly predicting the…