Bringing Atomistic Deep Learning to Prime Time

2021/12/09 by Nathan C. Frey, Frey, Nathan C., Siddharth Samsi +7
Materials Science · #Machine Learning in Materials Science #Electronic and Structural Properties of Oxides #Electron and X-Ray Spectroscopy Techniques

paper · pdf · doi:10.48550/arxiv.2112.04977

Abstract

Artificial intelligence has not yet revolutionized the design of materials and molecules. In this perspective, we identify four barriers preventing the integration of atomistic deep learning, molecular science, and high-performance computing. We outline focused research efforts to address the opportunities presented by these challenges.

Related

• Beyond potentials: integrated machine-learning models for materials
• Machine learning-accelerated quantum mechanics-based atomistic simulations for industrial applications
• Deep Molecular Representation Learning via Fusing Physical and Chemical Information
• Machine Learning Potentials: A Roadmap Toward Next-Generation Biomolecular Simulations
• Off-the-shelf deep learning is not enough: parsimony, Bayes and\n causality