# 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.

$sgdml_get.py dataset ethanol_dft$ 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: https://github.com/stefanch/sGDML

### Citing¶

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.

SOURCE DOCUMENTATION: