Simple computational strategies for more effective physics-informed neural networks modeling of turbulent natural convection

D Lucor, A Agrawal, A Sergent - Journal of Computational Physics, 2022 - Elsevier
The high expressivity and agility of physics-informed neural networks (PINNs) make them
promising candidates for full fluid flow PDE modeling. An important question is whether this …

Multi-scale approach for reliability-based design optimization with metamodel upscaling

L Coelho, D Lucor, N Fabbiane, C Fagiano… - Structural and …, 2023 - Springer
For multi-scale materials, the interplay of material and design uncertainties and reliability-
based design optimization is complex and very dependent on the chosen modeling scale …

Uncertainty Propagation in High-Dimensional Fields using Non-Intrusive Reduced Order Modeling and Polynomial Chaos

N Iyengar, D Rajaram, K Decker… - AIAA SciTech 2023 Forum, 2023 - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2023-1686. vid High-fidelity, physics-
based modeling and simulation have become integral to the design of aircraft, but can have …

Reduced-order modeling for parameterized large-eddy simulations of atmospheric pollutant dispersion

BX Nony, MC Rochoux, T Jaravel, D Lucor - … Environmental Research and …, 2023 - Springer
Mapping near-field pollutant concentration is essential to track plume dispersion in urban
areas. By solving most of the turbulence spectrum, large-eddy simulations (LES) can …

Physics-informed neural networks modelling for systems with moving immersed boundaries: Application to an unsteady flow past a plunging foil

R Sundar, D Majumdar, D Lucor, S Sarkar - Journal of Fluids and …, 2024 - Elsevier
Physics informed neural networks (PINNs) have been explored extensively in the recent
past for solving various forward and inverse problems for facilitating querying applications in …

Contaminant source identification in an aquifer using a Bayesian framework with arbitrary polynomial chaos expansion

G Zhang, T Xu, C Lu, Y Xie, J Yang - Stochastic Environmental Research …, 2024 - Springer
Stochastic methods are widely used for the identification of contaminant source information.
However, these methods suffer from low computational efficiency. To address this issue …

Uncertainty Quantification in Flows with Discontinuities: A Probabilistic Approach on Nonlinear Manifolds

N Iyengar, D Rajaram, DN Mavris - AIAA AVIATION 2023 Forum, 2023 - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2023-4092. vid Uncertainty quantification
(UQ) in transonic and supersonic flows is difficult due to the presence of strong …

High-Dimensional Uncertainty Propagation in Aerodynamics using Polynomial Chaos-Kriging

N Iyengar, DN Mavris - AIAA AVIATION 2023 Forum, 2023 - arc.aiaa.org
View Video Presentation: https://doi. org/10.2514/6.2023-3766. vid Uncertainty propagation
in simulations with high-dimensional outputs, such as computational fluid dynamics, is …

Optimizing identification of mine water inrush source with manifold reduction and semi-supervised learning using improved autoencoder

S Wang, P Zhai, X Yu, J Han, L Shi - Stochastic Environmental Research …, 2024 - Springer
To enhance the accuracy of identifying water sources in mine inrush incidents, this study,
taking the Shengquan coal mine in Shandong, China, as a case study, proposes a novel …

Improved metamodels for predicting high-dimensional outputs by accounting for the dependence structure of the latent variables: application to marine flooding

J Rohmer, C Sire, S Lecacheux, D Idier… - … Research and Risk …, 2023 - Springer
Metamodelling techniques (also referred to as surrogate modelling) have shown high
performance to overcome the computational burden of numerical hydrodynamic models for …