Synthetic Data¶
A dataset of synthetic amorphous Silicon structures, taken from Signatures of paracrystallinity in amorphous silicon. Each structure is the final snapshot from a unique melt-quench MD trajectory. The combined dataset covers a wide range of quench rates and densities, and includes the labels from the MTP \(M_{16}^{''}\) potential used to generate the structures.
Amorphous, 2D graphene structures generated using a Monte Carlo bond-switching algorithm, as described in Figure 3 of the paper: Exploring the Configurational Space of Amorphous Graphene with Machine-Learned Atomic Energies. Files are downloaded from Zenodo.
The complete “synthetic” dataset of carbon structures from Synthetic Data Enable Experiments in Atomistic Machine Learning. This dataset comprises 546 uncorrelated MD trajectories, each containing 200 atoms, driven by the C-GAP-17 interatomic potential, and sampled every 1ps. The structures cover a wide range of densities, temperatures and degrees of dis/order.