Lecture
Hydrodynamic Models: Machine Learning for Kinetic Equations
Description
This lecture explores the development of uniformly accurate hydrodynamic models for kinetic equations using machine learning. Starting with the Boltzmann equation, the instructor discusses numerical challenges, the fluid dynamical description, and the general strategy for modeling multi-scale physics. The lecture delves into moment methods, machine-learned moment methods, and the learning of moment fluxes and source terms. It also covers Galilean invariant moments, numerical results of various tasks, and end-to-end learning strategies in detail.
Official source
About this result
This page is automatically generated and may contain information that is not correct, complete, up-to-date, or relevant to your search query. The same applies to every other page on this website. Please make sure to verify the information with EPFL's official sources.
Ontological neighbourhood
Related lectures (57)
Eigenstate Thermalization Hypothesis
Explores the Eigenstate Thermalization Hypothesis in quantum systems, emphasizing the random matrix theory and the behavior of observables in thermal equilibrium.
Molecular dynamics under constraints
Explores molecular dynamics simulations under holonomic constraints, focusing on numerical integration and algorithm formulation.
Efficient Stochastic Numerical Methods
Explores efficient stochastic numerical methods for modeling and learning, covering topics like the Analytical Engine and kinase inhibitors.
Levy Flights and Central Limit Theorem
Covers Levy flights, Central Limit Theorem, and Mesoscopic Master Equation with transition rates in an assurance system.
Document Analysis: Topic Modeling
Explores document analysis, topic modeling, and generative models for data generation in machine learning.