44 citations · 116 across the 6 of their papers we have counts for
8 papers
Accelerating multigrid solver with generative super-resolution
Francisco Holguin, GS Sidharth, Gavin Portwood
The geometric multigrid algorithm is an efficient numerical method for solving a variety of elliptic partial differential equations (PDEs). The method damps errors at progressively…
Multigrid Solver With Super-Resolved Interpolation
Francisco Holguin, GS Sidharth, Gavin Portwood
The multigrid algorithm is an efficient numerical method for solving a variety of elliptic partial differential equations (PDEs). The method damps errors at progressively finer gri…
Idealised Turbulent Wake With Steady, Non-Uniform Ambient Density Stratification
G. D. Portwood, S. M. de Bruyn Kops
Density stratification in geophysical environments can be non-uniform, particularly in thermohaline staircases and atmospheric layer transitions. Non-uniform stratification, howeve…
Accelerating Training in Artificial Neural Networks with Dynamic Mode Decomposition
Mauricio E. Tano, Gavin D. Portwood, Jean C. Ragusa
Training of deep neural networks (DNNs) frequently involves optimizing several millions or even billions of parameters. Even with modern computing architectures, the computational…
Interpreting neural network models of residual scalar flux
Gavin D. Portwood, Balasubramanya T. Nadiga, Juan A. Saenz +1
We show that in addition to providing effective and competitive closures, when analysed in terms of dynamics and physically-relevant diagnostics, artificial neural networks (ANNs)…
Turbulence forecasting via Neural ODE
Gavin D. Portwood, Peetak P. Mitra, Mateus Dias Ribeiro +9
Fluid turbulence is characterized by strong coupling across a broad range of scales. Furthermore, besides the usual local cascades, such coupling may extend to interactions that ar…