Machine Learning for Molecular Dynamics on Long Timescales
This work aims to bridge the gap between molecular dynamics and machine learning research, potentially benefiting researchers in chemistry, materials science, and drug design by outlining unsolved problems and fostering new interdisciplinary solutions.
The paper addresses the challenge of computing statistical quantities from long-timescale molecular dynamics simulations, which are often prohibitively expensive, by exploring how machine learning methods can improve efficiency and interpretability in this field.
Molecular Dynamics (MD) simulation is widely used to analyze the properties of molecules and materials. Most practical applications, such as comparison with experimental measurements, designing drug molecules, or optimizing materials, rely on statistical quantities, which may be prohibitively expensive to compute from direct long-time MD simulations. Classical Machine Learning (ML) techniques have already had a profound impact on the field, especially for learning low-dimensional models of the long-time dynamics and for devising more efficient sampling schemes for computing long-time statistics. Novel ML methods have the potential to revolutionize long-timescale MD and to obtain interpretable models. ML concepts such as statistical estimator theory, end-to-end learning, representation learning and active learning are highly interesting for the MD researcher and will help to develop new solutions to hard MD problems. With the aim of better connecting the MD and ML research areas and spawning new research on this interface, we define the learning problems in long-timescale MD, present successful approaches and outline some of the unsolved ML problems in this application field.