Tutorials

autoplex tutorials written by autoplex developers.

The user is advised to have a general familiarity with the following software packages and tools:

• VASP

• the machine-learned interatomic potential (MLIP) framework that is aimed to be used

• the Materials Project framework

• atomate2

• ase

• basic Python knowledge

The tutorials are aimed to demonstrate the usage of autoplex to generate MLIPs and benchmark it to DFT results. By the end of these tutorials, you should be able to:

• use autoplex out of the box with default settings

• customize the workflow settings

• use any of the submodule workflows to build your own workflows

Tutorial table of content

• Installation guide
  • Before you start using autoplex
  • Installation Documentation and Guides of the Dependencies
  • Workflow management

• RSS workflow
  • Brief overview
    • Features
  • Quick start
    • Running the workflow with a YAML configuration file
    • Running the workflow with direct parameter specification
    • Building RSS models with various ML potentials
    • Resuming workflow from point of interruption
  • Input YAML configuration file
    • General parameters
    • Buildcell parameters
    • Sampling parameters
    • DFT labelling parameters
    • Data preprocessing parameters
    • MLIP Parameters
    • RSS Exploration Parameters
  • Examples
    • SiO₂

• Phonon workflow
  • Out-of-the-box workflow
    • Phonon-accurate machine-learned potentials workflow
    • General workflow
    • Now start the workflow
    • Output and results
    • Iterative version of the default workflow
  • Generating reference data
    • Single-atom displaced supercell structures
    • Rattled supercell structures
    • Adjust supercell settings
    • VASP settings
  • Fitting phonon-accurate potentials
    • General settings
    • GAP
    • ACE
    • Nequip
    • M3GNet
    • MACE
    • Example script for autoplex workflow using GAP to fit and benchmark a Si database
    • Running a MLIP fit only
    • Is it possible to run the DFT calculations and the MLIP fitting step on different machines?
  • Benchmark of ML-based phonon structure
    • General settings
    • Error metrics
    • Run a benchmark with a pre-existing DFT calculation and GAP potential

Contributors and Their Contributions

• Christina Ertural

  • Initial setup documentation

  • Phonon flows:

    • Flows documentation

    • Data generation guide

    • Fitting documentation

    • Benchmarking documentation

  • Contributed to installation guide (with Aakash Naik)

  • Contributed to jobflow-remote and MongoDB setup (with Aakash Naik)

• Aakash Naik

  • Contributed to installation guide (with Christina Ertural)

  • Jobflow-remote and MongoDB setup documentation (with Christina Ertural)

• Yuanbin Liu

  • RSS documentation

• Janine George

  • Phonon flows documentation (with Christina Ertural)