Crystallization Machine Learning - Theory and Simulation Techniques

Explore the intersection of crystallization and machine learning in this comprehensive lecture from Advanced Cyberinfrastructure Training at RPI. Delve into theoretical foundations, including molecular dynamics and empirical models, with a focus on water and Tip3p water models. Examine density functional theory and electronic density of states before transitioning to machine learning applications in crystallization. Investigate initial machine learning methodologies and address the timescale problem in simulations. Learn about rare events, enhanced sampling techniques, and metadynamics. Conclude with an in-depth look at homogeneous crystal nucleation and associated simulation techniques. Gain valuable insights into cutting-edge approaches for understanding and predicting crystallization processes through advanced computational methods.

Outline
Theory
Molecular Dynamics
Empirical Models
Water
Tip3p Water
Density Functional Theory
Electronic Density of States
Machine Learning
Initial Machine Learning
Methodology
Timescale Problem
Rare Events
Enhanced Sampling
Metadynamics
Homogeneous crystal nucleation
Simulation technique