Setting standards for data driven materials science
Keith T. Butler, Kamal Choudhary, Gábor Cśanyi, Alex M. Ganose, Sergei V. Kalinin, Dane Morgan
Abstract
A young Steve Jobs once called computers ‘bicycles for the mind’—he was referring to the dramatic decrease in the energetic cost of transportation that could be obtained with the bicycle, which breaks all scaling laws for how efficiently an animal can achieve motion. The creativity of new approaches to old materials science problems facilitated by the dramatic uptake of machine learning (ML) is a testament to this notion. The uptake of ML in our subject has been facilitated by exceptional efforts to provide open datasets, e.g. Novel Materials Discovery (NOMAD) 1 , Materials Project 2 , Joint Automated Repository for Various Integrated Simulations (JARVIS) 3 , Automatic FLOW for Materials Discovery (AFLOW) 4 , Open Quantum Materials Database (OQMD) 5 and many others, as well as the extremely high quality of openly available software packages such as scikit-learn 6 , PyTorch 7 , (Just After eXecution) JAX 8 , Quantum Espresso 9 , and Large-scale Atomic/Molecular Massively Parallel Simulator (LAMMPS) 10 . These resources, along with continued extraordinary developments in hardware, are helping a wide-range of researchers integrate ML into their work.