[HTML][HTML] The transition to sustainable combustion: Hydrogen-and carbon-based future fuels and methods for dealing with their challenges

H Pitsch - Proceedings of the Combustion Institute, 2024 - Elsevier
While the world is already facing substantial impacts of global warming, the transition
towards a sustainable-energy future is slow because of the sheer scale of global energy …

Investigation of the generalization capability of a generative adversarial network for large eddy simulation of turbulent premixed reacting flows

L Nista, CDK Schumann, T Grenga, A Attili… - Proceedings of the …, 2023 - Elsevier
In the past decades, Deep Learning (DL) frameworks have demonstrated excellent
performance in modeling nonlinear interactions and are a promising technique to move …

3d super-resolution model for vehicle flow field enrichment

TL Trinh, F Chen, T Nanri… - Proceedings of the IEEE …, 2024 - openaccess.thecvf.com
In vehicle shape design from aerodynamic performance perspective, deep learning methods
enable us to estimate the flow field in a short period. However, the estimated flow fields are …

[HTML][HTML] Parallel implementation and performance of super-resolution generative adversarial network turbulence models for large-eddy simulation

L Nista, CDK Schumann, P Petkov, V Pavlov… - Computers & …, 2025 - Elsevier
Super-resolution (SR) generative adversarial networks (GANs) are promising for turbulence
closure in large-eddy simulation (LES) due to their ability to accurately reconstruct high …

Convolutional-neural-network-based DES-level aerodynamic flow field generation from URANS data

JP Romano, O Baysal, AC Brodeur - AIP Advances, 2023 - pubs.aip.org
The present paper culminates several investigations into the use of convolutional neural
networks (CNNs) as a post-processing step to improve the accuracy of unsteady Reynolds …

Influence of adversarial training on super-resolution turbulence reconstruction

L Nista, H Pitsch, CDK Schumann, M Bode, T Grenga… - Physical Review …, 2024 - APS
Supervised super-resolution deep convolutional neural networks (CNNs) have gained
significant attention for their potential in reconstructing velocity and scalar fields in turbulent …

Super-Resolution Generative Adversarial Network for Data Compression of Direct Numerical Simulations

L Nista, CDK Schumann, F Fröde, M Gowely… - arXiv preprint arXiv …, 2024 - arxiv.org
The advancement of high-performance computing has enabled the generation of large
direct numerical simulation (DNS) datasets of turbulent flows, driving the need for efficient …

Faster, Cheaper, and Better CFD: A Case for Machine Learning to Augment Reynolds-Averaged Navier-Stokes

JP Romano II - 2023 - digitalcommons.odu.edu
In recent years, the field of machine learning (ML) has made significant advances,
particularly through applying deep learning (DL) algorithms and artificial intelligence (AI) …