We provide an introduction to Gaussian process regression (GPR) machine-learning
methods in computational materials science and chemistry. The focus of the present review …

Since the classical molecular dynamics simulator LAMMPS was released as an open source
code in 2004, it has become a widely-used tool for particle-based modeling of materials at …

Interatomic potentials approximate the potential energy of atoms as a function of their
coordinates. Their main application is the effective simulation of many-atom systems. Here …

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 …

Molecular dynamics simulation is an important tool in computational materials science and
chemistry, and in the past decade it has been revolutionized by machine learning. This rapid …

We demonstrate that fast and accurate linear force fields can be built for molecules using the
atomic cluster expansion (ACE) framework. The ACE models parametrize the potential …

Abstract Machine learning interatomic potentials are revolutionizing large-scale, accurate
atomistic modeling in material science and chemistry. Many potentials use atomic cluster …

Data-driven interatomic potentials have emerged as a powerful tool for approximating ab
initio potential energy surfaces. The most time-consuming step in creating these interatomic …

We present an atomic cluster expansion (ACE) for carbon that improves over available
classical and machine learning potentials. The ACE is parametrized from an exhaustive set …

The recently discovered metal-like room-temperature plasticity in inorganic semiconductors
reshapes our knowledge of the physical properties of materials, giving birth to a series of …