GPUMD: A package for constructing accurate machine-learned potentials and performing highly efficient atomistic simulations.

We present our latest advancements of machine-learned potentials (MLPs) based on the neuroevolution potential (NEP) framework introduced in Fan et al. [Phys. Rev. B 104, 104309 (2021)] and their implementation in the open-source package gpumd. We increase the accuracy of NEP models both by improving the radial functions in the atomic-environment descriptor using a linear combination of Chebyshev basis functions and by extending the angular descriptor with some four-body and five-body contributions as in the atomic cluster expansion approach. We also detail our efficient implementation of the NEP approach in graphics processing units as well as our workflow for the construction of NEP models and demonstrate their application in large-scale atomistic simulations. By comparing to state-of-the-art MLPs, we show that the NEP approach not only achieves above-average accuracy but also is far more computationally efficient. These results demonstrate that the gpumd package is a promising tool for solving challenging problems requiring highly accurate, large-scale atomistic simulations. To enable the construction of MLPs using a minimal training set, we propose an active-learning scheme based on the latent space of a pre-trained NEP model. Finally, we introduce three separate Python packages, viz., gpyumd, calorine, and pynep, that enable the integration of gpumd into Python workflows.

Ultrahigh thermal isolation across heterogeneously layered two-dimensional materials.

Heterogeneous integration of nanomaterials has enabled advanced electronics and photonics applications. However, similar progress has been challenging for thermal applications, in part due to shorter wavelengths of heat carriers (phonons) compared to electrons and photons. Here, we demonstrate unusually high thermal isolation across ultrathin heterostructures, achieved by layering atomically thin two-dimensional (2D) materials. We realize artificial stacks of monolayer graphene, MoS2, and WSe2 with thermal resistance greater than 100 times thicker SiO2 and effective thermal conductivity lower than air at room temperature. Using Raman thermometry, we simultaneously identify the thermal resistance between any 2D monolayers in the stack. Ultrahigh thermal isolation is achieved through the mismatch in mass density and phonon density of states between the 2D layers. These thermal metamaterials are an example in the emerging field of phononics and could find applications where ultrathin thermal insulation is desired, in thermal energy harvesting, or for routing heat in ultracompact geometries.