Differentiable physics: A position piece
B Ramsundar, D Krishnamurthy… - arXiv preprint arXiv …, 2021 - arxiv.org
Differentiable physics provides a new approach for modeling and understanding the
physical systems by pairing the new technology of differentiable programming with classical …
physical systems by pairing the new technology of differentiable programming with classical …
Improving CFD Simulations by Local Machine-Learned Corrections
P Mitra, M Haghshenas… - ASME …, 2023 - asmedigitalcollection.asme.org
High-fidelity computational fluid dynamics (CFD) simulations for design space explorations
can be exceedingly expensive due to the cost associated with resolving the finest scales …
can be exceedingly expensive due to the cost associated with resolving the finest scales …
Analysis and Interpretation of Data-Driven Closure Models for Large Eddy Simulation of Internal Combustion Engine
We present an automatic data-driven machine learning (ML) approach for the development,
evaluation and interpretation of deep neural networks (DNNs) for turbulence closures and …
evaluation and interpretation of deep neural networks (DNNs) for turbulence closures and …