The evolution of machine learning potentials for molecules, reactions and materials

Data faithfully to continuous and symmetry-preserving mathematical forms, MLPs have enabled accurate and efficient atomistic simulations in a large scale from first principles. In this review, we provide an overview of the evolution of MLPs in the past two decades and focus on the state-of-the-art MLPs proposed in the last a few years for molecules, reactions, and materials. We discuss some representative applications of MLPs and the trend of developing universal potentials across a variety of systems. Finally, we outline a list of open challenges and opportunities in the development and applications of MLPs.

• NN
  National Natural Science Foundation of China

  Awards: 22033007, 22221003, 22325304
• CA
  Chinese Academy of Sciences

  Award: XDB0450101
• NC
  National Center of Competence in Research Quantum Science and Technology

  Award: 2021ZD0303301