English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The dream of machine learning in materials science is for a model to learnthe underlying physics of an atomic system, allowing it to move beyondinterpolation of the training set to the prediction of properties that were notpresent in the original training data. In addition to advances in machinelearning architectures and training techniques, achieving this ambitious goalrequires a method to convert a 3D atomic system into a feature representationthat preserves rotational and translational symmetry, smoothness under smallperturbations, and invariance under re-ordering. The atomic orbital waveletscattering transform preserves these symmetries by construction, and hasachieved great success as a featurization method for machine learning energyprediction. Both in small molecules and in the bulk amorphous$\text{Li}_{\alpha}\text{Si}$ system, machine learning models using waveletscattering coefficients as features have demonstrated a comparable accuracy toDensity Functional Theory at a small fraction of the computational cost. Inthis work, we test the generalizability of our $\text{Li}_{\alpha}\text{Si}$energy predictor to properties that were not included in the training set, suchas elastic constants and migration barriers. We demonstrate that statisticalfeature selection methods can reduce over-fitting and lead to remarkableaccuracy in these extrapolation tasks.

Wavelet Scattering Networks for Atomistic Systems with Extrapolation of Material Properties