[HTML][HTML] Flow completion network: Inferring the fluid dynamics from incomplete flow information using graph neural networks
This paper introduces a novel neural network—a flow completion network (FCN)—to infer
the fluid dynamics, including the flow field and the force acting on the body, from the …
the fluid dynamics, including the flow field and the force acting on the body, from the …
GD-VAEs: Geometric dynamic variational autoencoders for learning nonlinear dynamics and dimension reductions
R Lopez, PJ Atzberger - arXiv preprint arXiv:2206.05183, 2022 - arxiv.org
We develop data-driven methods incorporating geometric and topological information to
learn parsimonious representations of nonlinear dynamics from observations. We develop …
learn parsimonious representations of nonlinear dynamics from observations. We develop …
[HTML][HTML] SDYN-GANs: Adversarial learning methods for multistep generative models for general order stochastic dynamics
We introduce adversarial learning methods for data-driven generative modeling of dynamics
of nt h-order stochastic systems. Our approach builds on Generative Adversarial Networks …
of nt h-order stochastic systems. Our approach builds on Generative Adversarial Networks …
Probabilistic partition of unity networks for high‐dimensional regression problems
We explore the probabilistic partition of unity network (PPOU‐Net) model in the context of
high‐dimensional regression problems and propose a general framework focusing on …
high‐dimensional regression problems and propose a general framework focusing on …
Meshfree methods for PDEs on surfaces
AM Jones - 2022 - scholarworks.boisestate.edu
This dissertation focuses on meshfree methods for solving surface partial differential
equations (PDEs). These PDEs arise in many areas of science and engineering where they …
equations (PDEs). These PDEs arise in many areas of science and engineering where they …