Fast, accurate, and transferable many-body interatomic potentials by genetic programming

by   Alberto Hernández, et al.

The length and time scales of atomistic simulations are limited by the computational cost of the methods used to predict material properties. In recent years there has been great progress in the use of machine learning algorithms to develop fast and accurate interatomic potential models, but it remains a challenge to develop models that generalize well and are fast enough to be used at extreme time and length scales. To address this challenge, we have developed a machine learning algorithm based on genetic programming that is capable of discovering accurate, computationally efficient many-body potential models. The key to our approach is to explore a hypothesis space of models based on fundamental physical principles and select models within this hypothesis space based on their accuracy, speed, and simplicity. The focus on simplicity reduces the risk of overfitting the training data and increases the chances of discovering a model that generalizes well. Our algorithm was validated by rediscovering an exact Lennard Jones potential and a Sutton Chen embedded atom method potential from training data generated using these models. By using training data generated from density functional theory calculations, we found potential models for elemental copper that are simple, as fast as embedded atom models, and capable of accurately predicting properties outside of their training set. Our approach requires relatively small sets of training data, making it possible to generate training data using highly accurate methods at a reasonable computational cost. We present our approach, the forms of the discovered models, and assessments of their transferability, accuracy and speed.




Fast, accurate, and transferable many-body interatomic potentials by symbolic regression

The length and time scales of atomistic simulations are limited by the c...

Data Aggregation for Reducing Training Data in Symbolic Regression

The growing volume of data makes the use of computationally intense mach...

Symbolic Regression in Materials Science: Discovering Interatomic Potentials from Data

Particle-based modeling of materials at atomic scale plays an important ...

A study in Rashomon curves and volumes: A new perspective on generalization and model simplicity in machine learning

The Rashomon effect occurs when many different explanations exist for th...

Searching for Globally Optimal Functional Forms for Inter-Atomic Potentials Using Parallel Tempering and Genetic Programming

We develop a Genetic Programming-based methodology that enables discover...

Data Generation for Neural Programming by Example

Programming by example is the problem of synthesizing a program from a s...

Machine Learning Approach to Earthquake Rupture Dynamics

Simulating dynamic rupture propagation is challenging due to the uncerta...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.