4 papers
PLAID: A Unified Data Model for Machine Learning on Heterogeneous Physics Simulations
Fabien Casenave, Xavier Roynard, Brian Staber +17
Machine learning-based surrogate models have emerged as a powerful tool to accelerate simulation-driven scientific workflows, but their adoption is limited by the lack of large-sca…
An End-to-End PyTorch Interface for Differentiable PDE Solvers: A RANS Model-Correction Study
Luca Saverio, Michele Alessandro Bucci, Gianmarco Farro +2
This work presents an end-to-end strategy for solving inverse problems constrained by Partial Differential Equations within a fully differentiable Machine Learning framework. The p…
Mean flow data assimilation using physics-constrained Graph Neural Networks
M. Quattromini, M. A. Bucci, S. Cherubini +1
Despite their widespread use, purely data-driven methods often suffer from overfitting, lack of physical consistency, and high data dependency, particularly when physical constrain…
Active learning of data-assimilation closures using Graph Neural Networks
Michele Quattromini, Michele Alessandro Bucci, Stefania Cherubini +1
The spread of machine learning techniques coupled with the availability of high-quality experimental and numerical data has significantly advanced numerous applications in fluid me…