.png){kind=icon}
.png){kind=icon}
Return
Synthetic data enable experiments in atomistic machine learning
.png){kind=icon}
OA
AI
DOI：10.1039/d2dd00137c.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Machine-learning models are increasingly used to predict properties of atoms in chemical systems. There have been major advances in developing descriptors and regression frameworks for this task, typically starting from (relatively) small sets of quantum-mechanical reference data. Larger datasets of this kind are becoming available, but remain expensive to generate. Here we demonstrate the use of a large dataset that we have synthetically labelled with per-atom energies from an existing ML potential model. The cheapness of this process, compared to the quantum-mechanical ground truth, allows us to generate millions of datapoints, in turn enabling rapid experimentation with atomistic ML models from the small- to the large-data regime. This approach allows us here to compare regression frameworks in depth, and to explore visualisation based on learned representations. We also show that learning synthetic data labels can be a useful pre-training task for subsequent fine-tuning on small datasets. In the future, we expect that our open-sourced dataset, and similar ones, will be useful in rapidly exploring deep-learning models in the limit of abundant chemical data. We introduce a large synthetic dataset of atomistic structures and energies, generated using a fast machine-learning model, and we demonstrate its usefulness for supervised and unsupervised ML tasks in chemistry.
Keywords:
CHEMICAL SPACE