ParAMS, the parameter optimization toolkit

Parametrized models such as the reactive Force Field ReaxFF or the new Machine Learning Potentials can model large, realistic, systems with high efficency. However, the accuracy of such models varies. the The purpose of ParAMS is refitting the parameters of such models to increase the accuracy, or enable the study of new systems by creating new parameters in the first place. For this ParAMS helps you create and manage your training data, run high-dimensional parameter fits in smart and efficient way and evaluate the fitness of your new model.

Params gui
  • Excellent documentation with many hands-on tutorials
  • GUI and Python support
  • Parametrize ReaxFF, DFTB and ML Potentials
  • Easily generate/manipulate/refine training data: Sort/search/weight entries, split off validation sets,…
  • Sensitivity analysis of parameterspace: Which parameters should be optimized and which not?
  • Apply recommended ReaxFF parameter constraints during the optimization
  • Run multiple optimizers in parallel
  • Automatically turn off and restart optimizers not performing well

Not sure what modeling tools you need for you research project?