Wavelet Scattering Networks for Atomistic Systems with Extrapolation of Material Properties

TL;DR

This paper demonstrates that wavelet scattering transforms can effectively serve as symmetry-preserving features for machine learning models in materials science, enabling accurate extrapolation of properties beyond training data.

Contribution

The work introduces the use of wavelet scattering coefficients for predicting diverse material properties, showing improved generalization and reduced overfitting in atomistic systems.

Findings

Wavelet scattering features achieve DFT-level accuracy at lower computational cost.

Statistical feature selection enhances extrapolation to unseen properties.

Models successfully predict elastic constants and migration barriers.

Abstract

The dream of machine learning in materials science is for a model to learn the underlying physics of an atomic system, allowing it to move beyond interpolation of the training set to the prediction of properties that were not present in the original training data. In addition to advances in machine learning architectures and training techniques, achieving this ambitious goal requires a method to convert a 3D atomic system into a feature representation that preserves rotational and translational symmetry, smoothness under small perturbations, and invariance under re-ordering. The atomic orbital wavelet scattering transform preserves these symmetries by construction, and has achieved great success as a featurization method for machine learning energy prediction. Both in small molecules and in the bulk amorphous $\text{Li}_{\alpha}\text{Si}$ system, machine learning models using wavelet scattering coefficients as features have demonstrated a comparable accuracy to Density Functional Theory at a small fraction of the computational cost. In this work, we test the generalizability of our $\text{Li}_{\alpha}\text{Si}$ energy predictor to properties that were not included in the training set, such as elastic constants and migration barriers. We demonstrate that statistical feature selection methods can reduce over-fitting and lead to remarkable accuracy in these extrapolation tasks.