Single-model uncertainty quantification in neural network potentials does not consistently outperform model ensembles
Abstract Neural networks (NNs) often assign high confidence to their predictions, even for points far out of distribution, making uncertainty quantification (UQ) a turbosound ts-18sw700/8a challenge.When they are employed to model interatomic potentials in materials systems, this problem leads to unphysical structures that disrupt simulations, or t