sGDML Documentation

This is a highly optimized implementation of the recently proposed symmetric gradient domain machine learning (sGDML) force field model. It is able to faithfully reproduce a detailed global potential energy surfaces (PES) for small- and medium-sized molecules from a limited number of user-provided reference calculations.

We have previously demonstrated, that sGDML is able to reproduce quantum-chemical CCSD(T) level accuracy and achieve spectroscopic accuracy in molecular simulations at the cost of a traditional force field [1] [2]. Here, we offer a set of Python routines to reconstruct and evaluate custom sGDML force fields. A user-friendly command-line interface offers assistance through the complete process of model creation, in an effort to make this novel machine learning approach accessible to broad practitioners.

It’s easy to get going!

Here is how to reconstruct an ethanol force field using 200 samples from the published benchmark dataset [1]. We will be using another 1000 points as validation data and finally estimate the generalization error of our model on additional 5000 geometries.

$ dataset ethanol_dft
$ sgdml all ethanol_dft.npz 200 1000 5000

Here is how the output will look like:


Code Development

The sGDML code is developed through our GitHub repository:


Please cite GDML and sGDML as follows:

[1](1, 2) Chmiela, S., Sauceda, H. E., Müller, K.-R., Tkatchenko, A. Towards Exact Molecular Dynamics Simulations with Machine-Learned Force Fields. Nat. Commun., accepted
[2]Chmiela, S., Tkatchenko, A., Sauceda, H. E., Poltavsky, Igor, Schütt, K. T., Müller, K.-R. (2017). Machine learning of accurate energy-conserving molecular force fields. Sci. Adv., 3(5), e1603015.


This code is freely available under the terms of the MIT license.