Free trial Contact
Software for Chemistry & Materials Software for Chemistry & Materials
  • Amsterdam Modeling Suite
  • Applications
  • Tools
  • Docs & Support
  • Company
Search
Workflows
  • ChemTraYzer2
  • OLED Deposition and Properties
  • Reactions Discovery
  • Simple Active Learning
    • General
    • Quickstart guide
    • Input
    • Output
    • Python Examples
      • Single molecule: setup and run
      • Single molecule: access results
      • Single molecule: Compare to M3GNet-UP-2022
      • Single molecule: Production simulation with retrained ML potential
      • Continue active learning with a new system or new simulation settings
      • Liquid water: diffusion coefficient, radial distribution function, density
      • Conformers: Active learning with CREST metadynamics and custom addition of data points
      • Li-vacancy diffusion in a solid electrolyte
      • Active Learning with uncertainties predicted from committee models
      • Ru/H introduction
      • Ru/H Part 1: Initial reference data from lattice optimization, volume scan, bond scan
      • Ru/H Part 2: Initial reference data from cartesian coordinate scans and bond scans
      • Ru/H Part 3: Initial reference data MD simulation + single-point replays
      • Ru/H Part 4: Initial training
      • Ru/H Part 5: Active learning for molecule gun MD
    • Python API
    • Frequently Asked Questions
Workflows
  • Documentation/
  • Workflows/
  • Simple Active Learning/
  • Python Examples

Python ExamplesΒΆ

These examples show how to run Simple Active Learning with Python.

Getting Started

  • Single molecule: setup and run
  • Single molecule: access results
  • Single molecule: Compare to M3GNet-UP-2022
  • Single molecule: Production simulation with retrained ML potential
  • Continue active learning with a new system or new simulation settings

Case studies

  • Liquid water: diffusion coefficient, radial distribution function, density
  • Conformers: Active learning with CREST metadynamics and custom addition of data points
  • Li-vacancy diffusion in a solid electrolyte
  • Active Learning with uncertainties predicted from committee models

Ru/H case study

  • Ru/H introduction
  • Ru/H Part 1: Initial reference data from lattice optimization, volume scan, bond scan
  • Ru/H Part 2: Initial reference data from cartesian coordinate scans and bond scans
  • Ru/H Part 3: Initial reference data MD simulation + single-point replays
  • Ru/H Part 4: Initial training
  • Ru/H Part 5: Active learning for molecule gun MD

See also

  • Getting Started with PLAMS

  • PLAMS Examples

  • ParAMS Python tutorial

  • Simple Active Learning Python API

  • Simple Active Learning tutorial using the Graphical User Interface

Next Previous

  • Application Areas

    • Batteries & PVs
    • Bonding Analysis
    • Catalysis
    • Heavy Elements
    • Inorganic Chemistry
    • Life Sciences
    • Materials Science
    • Nanotechnology
    • Oil and Gas
    • Organic Electronics
    • Polymers
    • Spectroscopy
    • Supercomputer / HPC
    • Teaching Computational Chemistry with AMS
  • Products

    • AMS Driver
    • ADF
    • BAND
    • COSMO-RS
    • DFTB
    • GUI
    • ML Potentials & FF
    • MOPAC
    • ParAMS
    • PLAMS
    • Quantum ESPRESSO
    • ReaxFF
    • Workflows
  • Support

    • Brochure
    • Consulting & Contract Research
    • Discussion List
    • Documentation
    • Downloads
    • FAQs
    • GUI Tutorials
    • Installation
    • Literature Highlights
    • Papers Citing ADF
    • Release Notes
    • Support Overview
    • Teaching Materials
    • Videos
    • Webinars
    • Workshops
  • About Us

    • Careers
    • Collaborations
    • Contact Us
    • Contributors
    • EU Projects
    • Events
    • Mission & Vision
    • News
    • Newsletters
    • The SCM Team
  • Pricing & Licensing

    • License Terms
    • Ordering
    • Price Calculator
    • Price Quote
    • Pricing & Licensing
    • Resellers
  • Copyright
  • Terms of Use
  • Privacy Policy

ext6-wp19