Composable and adaptive design of machine learning interatomic potentials guided by Fisher-information analysis
By: Weishi Wang , Mark K. Transtrum , Vincenzo Lordi and more
Potential Business Impact:
Makes computer models of atoms more accurate.
An adaptive physics-informed model design strategy for machine-learning interatomic potentials (MLIPs) is proposed. This strategy follows an iterative reconfiguration of composite models from single-term models, followed by a unified training procedure. A model evaluation method based on the Fisher information matrix (FIM) and multiple-property error metrics is proposed to guide model reconfiguration and hyperparameter optimization. Combining the model reconfiguration and the model evaluation subroutines, we provide an adaptive MLIP design strategy that balances flexibility and extensibility. In a case study of designing models against a structurally diverse niobium dataset, we managed to obtain an optimal configuration with 75 parameters generated by our framework that achieved a force RMSE of 0.172 eV/{\AA} and an energy RMSE of 0.013 eV/atom.
Similar Papers
Iterative Pretraining Framework for Interatomic Potentials
Computational Physics
Makes computer models of atoms faster and more accurate.
Learning Smooth and Expressive Interatomic Potentials for Physical Property Prediction
Computational Physics
Makes computer models of materials more accurate.
Energy & Force Regression on DFT Trajectories is Not Enough for Universal Machine Learning Interatomic Potentials
Materials Science
Finds new materials much faster.