Combustion machine learning: Principles, progress and prospects
Progress in combustion science and engineering has led to the generation of large amounts
of data from large-scale simulations, high-resolution experiments, and sensors. This corpus …
of data from large-scale simulations, high-resolution experiments, and sensors. This corpus …
[HTML][HTML] HPC-enabling technologies for high-fidelity combustion simulations
With the increase in computational power in the last decade and the forthcoming Exascale
supercomputers, a new horizon in computational modelling and simulation is envisioned in …
supercomputers, a new horizon in computational modelling and simulation is envisioned in …
An adaptive time-integration scheme for stiff chemistry based on computational singular perturbation and artificial neural networks
We leverage the computational singular perturbation (CSP) theory to develop an adaptive
time-integration scheme for stiff chemistry based on a local, projection-based, reduced order …
time-integration scheme for stiff chemistry based on a local, projection-based, reduced order …
DLODE: a deep learning-based ODE solver for chemistry kinetics
View Video Presentation: https://doi. org/10.2514/6.2021-1139. vid Developing efficient and
accurate algorithms for chemistry integration is a challenging task due to its strong stiffness …
accurate algorithms for chemistry integration is a challenging task due to its strong stiffness …
HYPPO: a surrogate-based multi-level parallelism tool for hyperparameter optimization
We present a new software, HYPPO, that enables the automatic tuning of hyperparameters
of various deep learning (DL) models. Unlike other hyperparameter optimization (HPO) …
of various deep learning (DL) models. Unlike other hyperparameter optimization (HPO) …
SUNDIALS time integrators for exascale applications with many independent systems of ordinary differential equations
Many complex systems can be accurately modeled as a set of coupled time-dependent
partial differential equations (PDEs). However, solving such equations can be prohibitively …
partial differential equations (PDEs). However, solving such equations can be prohibitively …
A deep learning-based ODE solver for chemical kinetics
Developing efficient and accurate algorithms for chemistry integration is a challenging task
due to its strong stiffness and high dimensionality. The current work presents a deep …
due to its strong stiffness and high dimensionality. The current work presents a deep …
FORest Canopy Atmosphere Transfer (FORCAsT) 2.0: model updates and evaluation with observations at a mixed forest site
The FORCAsT (FORest Canopy Atmosphere Transfer) model version 1.0 is updated to
FORCAsT 2.0 by implementing five major changes, including (1) a change to the operator …
FORCAsT 2.0 by implementing five major changes, including (1) a change to the operator …
SUNDIALS Time Integrators for Exascale Applications with Many Independent ODE Systems
Many complex systems can be accurately modeled as a set of coupled time-dependent
partial differential equations (PDEs). However, solving such equations can be prohibitively …
partial differential equations (PDEs). However, solving such equations can be prohibitively …
Variable time-stepping exponential integrators for chemical reactors with analytical Jacobians
J Stewart, M Tokman, F Bisetti, V Dallerit… - arXiv preprint arXiv …, 2023 - arxiv.org
Computational chemical combustion problems are known to be stiff, and are typically solved
with implicit time integration methods. A novel exponential time integrator, EPI3V, is …
with implicit time integration methods. A novel exponential time integrator, EPI3V, is …