Optimizing the architecture of Behler-Parrinello neural network potentials.

The architecture of neural network potentials is typically optimized at the beginning of the training process and remains unchanged throughout. Here, we investigate the accuracy of Behler-Parrinello neural network potentials for varying training set sizes. Using the QM9 and 3BPA datasets, we show that adjusting the network architecture according to the training set size improves the accuracy significantly. We demonstrate that both an insufficient and an excessive number of fitting parameters can have a detrimental impact on the accuracy of the neural network potential. Furthermore, we investigate the influences of descriptor complexity, neural network depth, and activation function on the model's performance. We find that for the neural network potentials studied here, two hidden layers yield the best accuracy and that unbounded activation functions outperform bounded ones.

Crystal Structure and Magnetic Properties of Uranium Hydride UH2 Stabilized as a Thin Film.

A new type of uranium binary hydride, UH2, with the CaF2 crystal structure, was synthesized in a thin-film form using reactive sputter deposition at low temperatures. The material has a grain size of 50-100 nm. The lattice parameter a = (535.98 ± 0.14 pm) is close to that in known Np (534.3 pm) and Pu (535.9 pm) iso-types. UH2 is a metallic ferromagnet with the Curie temperature TC ≈ 120 K. A very wide hysteresis loop indicates strong magnetocrystalline anisotropy. X-ray photoelectron spectroscopy reveals similarities with electronic structure of UH3, which is also ferromagnet with higher TC = 165 K.

Diffusion and Coalescence of Phosphorene Monovacancies Studied Using High-Dimensional Neural Network Potentials.

The properties of two-dimensional materials are strongly affected by defects that are often present in considerable numbers. In this study, we investigate the diffusion and coalescence of monovacancies in phosphorene using molecular dynamics (MD) simulations accelerated by high-dimensional neural network potentials. Trained and validated with reference data obtained with density functional theory (DFT), such surrogate models provide the accuracy of DFT at a much lower cost, enabling simulations on time scales that far exceed those of first-principles MD. Our microsecond long simulations reveal that monovacancies are highly mobile and move predominantly in the zigzag rather than armchair direction, consistent with the energy barriers of the underlying hopping mechanisms. In further simulations, we find that monovacancies merge into energetically more stable and less mobile divacancies following different routes that may involve metastable intermediates.