Standard model outputs¶
In order for multiple simulation engines to be able use arbitrary metatensor atomistic models to compute atomic properties, we need all the models to return the same metadata for a given output. If your model returns one of the output defined in this documentation, then it should follow the metadata structure described here.
For other kind of output, you are free to use any relevant metadata structure, but if multiple people are producing the same kind of outputs, they are encouraged to come together, define the metadata they need and add a new section to these pages.
Physical quantities¶
The first set of standardized outputs in metatensor atomistic models are physical quantities, i.e. quantities with a well-defined physical meaning.
The potential energy associated with a given system conformation. This can be used to run molecular simulations based on machine learning interatomic potentials.
An ensemble of multiple potential energies predictions, when running multiple models simultaneously.
Machine learning outputs¶
The first set of standardized outputs in metatensor atomistic models are specific to machine learning and related tools.
Features are numerical vectors representing a given structure or atomic environment in an abstract n-dimensional space.