skip to main content
Idioma:

Adaptive machine learning framework to accelerate ab initio molecular dynamics

Botu, Venkatesh ; Ramprasad, Rampi

International journal of quantum chemistry, 2015-08, Vol.115 (16), p.1074-1083 [Periódico revisado por pares]

Hoboken: Blackwell Publishing Ltd

Texto completo disponível

Citações Citado por
  • Título:
    Adaptive machine learning framework to accelerate ab initio molecular dynamics
  • Autor: Botu, Venkatesh ; Ramprasad, Rampi
  • Assuntos: ab initio molecular dynamics ; accelerate ; adaptive ; Chemistry ; fingerprint ; machine learning ; Physical chemistry ; Quantum physics
  • É parte de: International journal of quantum chemistry, 2015-08, Vol.115 (16), p.1074-1083
  • Notas: istex:92FBFA9AEBFCAAC93E7BA0FE4263792D29E5E161
    ArticleID:QUA24836
    ark:/67375/WNG-0H28FTJ0-R
    Office of Naval Research - No. N00014-14-1-0098
  • Descrição: Quantum mechanics‐based ab initio molecular dynamics (MD) simulation schemes offer an accurate and direct means to monitor the time evolution of materials. Nevertheless, the expensive and repetitive energy and force computations required in such simulations lead to significant bottlenecks. Here, we lay the foundations for an accelerated ab initio MD approach integrated with a machine learning framework. The proposed algorithm learns from previously visited configurations in a continuous and adaptive manner on‐the‐fly, and predicts (with chemical accuracy) the energies and atomic forces of a new configuration at a minuscule fraction of the time taken by conventional ab initio methods. Key elements of this new accelerated ab initio MD paradigm include representations of atomic configurations by numerical fingerprints, a learning algorithm to map the fingerprints to the properties, a decision engine that guides the choice of the prediction scheme, and requisite amount of ab initio data. The performance of each aspect of the proposed scheme is critically evaluated for Al in several different chemical environments. This work has enormous implications beyond ab initio MD acceleration. It can also lead to accelerated structure and property prediction schemes, and accurate force fields. © 2014 Wiley Periodicals, Inc. The dynamical atomic‐level evolution of typical chemical processes extends to timescales longer than nanoseconds—hard to access routinely using present ab initio methods. Here, an adaptive machine learning framework is proposed to significantly accelerate ab initio molecular dynamics simulations. The scheme learns to predict energies and atomic forces with unprecedented speed and accuracy from an initial ab initio dataset, and systematically expands its predictive capability on‐the‐fly by including newly encountered chemical environments in its training.
  • Editor: Hoboken: Blackwell Publishing Ltd
  • Idioma: Inglês;Francês;Alemão
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.