Machine-learned interatomic potentials (MLIPs) have become the state-of-the-art for performing accurate, scalable molecular dynamics (MD) simulations. It is, therefore, crucial to understand and quantify the reliability of MLIPs for downstream property predictions. Uncertainty in predicted properties can arise from limitations in first-principles training data, intrinsic MLIP model errors in representing the data, and the statistical noise introduced during subsequent MD simulations. Using ion transport in Li7P3S11 as a case study, we systematically assess the impact of training set size and selection, neural network stochasticity, and MD sampling statistics on predicted diffusivity and activation energy. We find that when using equivariant MLIP architectures with standard MD protocols, uncertainty arising from MD sampling dominates over model-induced errors. In contrast, MLIP errors relative to the underlying first-principles data are consistently minor. Given this, there are two main routes to improving the accuracy of predictions based on MLIP potentials: adopting higher accuracy reference data generation methods and improving the MD sampling statistics.
This work presents a physics-informed pretraining strategy that leverages simple empirical potentials to improve the robustness and stability of MLIPs for MD simulations and demonstrates that this physics-informed pretraining consistently improves both prediction accuracy as well as stability in MD.
Qian-Yu Zheng, Victor Fung· Journal of Chemical Informat...· 0 citations
This work introduces a framework for propagating MLIP uncertainty to the averaged committor probability, a kinetic observable that enables reaction-rate calculations and demonstrates that path-space reweighting provides an efficient route for propagating MLIP uncertainty to rare event kinetics.
Léonard Moracchini, Thomas Pigeon, Morgane Menz et al.· 0 citations
AdaptNTK is introduced, a single-model framework that measures uncertainty as a regularized Mahalanobis distance in empirical neural tangent kernel (NTK) feature space, providing efficient single-model uncertainty estimation with sequential updates for data-efficient active learning.
The limits of equivariant MLIPs are examined, and a family of foundation potentials in the NequIP and Allegro equivariant MLIP architectures are presented which achieve leading inference speeds and strong scalability as well as excellent accuracies across a range of community benchmarks.
Seán R. Kavanagh, Chuin Wei Tan, Menghang Wang et al.· 0 citations
benchmarks demonstrate that GRACE-OFF achieves higher MD performance than comparable MACE-OFF models in both single and double precision, establishing GRACE-OFF as an accurate and computationally efficient foundation potential for routine simulations of organic liquids and biomolecular systems.
Anna Katharina Picha, Johannes Karwounopoulos, Linus C. Erhard et al.· Journal of Chemical Theory a...· 2 citations
Pretrained machine-learning interatomic potentials, so-called universal or foundation models offer an appealing starting point for atomistic simulations, but their accuracy for material-specific observables often remains limited without additional reference data (fine-tuning). Here, we systematically quantify how much...
Jonas Hänseroth, Christian Dreßler· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
