Deep Spatial Learning with Molecular Vibration

TL;DR

This paper introduces a physics-informed data augmentation method based on molecular vibrations to improve machine learning predictions in molecular science, especially under data scarcity conditions.

Contribution

It presents a novel data augmentation technique leveraging molecular vibrations, significantly enhancing predictive accuracy in molecular machine learning tasks.

Findings

Relative error reduced from 16.34% to 6.71%.

Coefficient of determination increased from 0.16 to 0.75.

Demonstrated superiority over common algorithms.

Abstract

Machine learning over-fitting caused by data scarcity greatly limits the application of machine learning for molecules. Due to manufacturing processes difference, big data is not always rendered available through computational chemistry methods for some tasks, causing data scarcity problem for machine learning algorithms. Here we propose to extract the natural features of molecular structures and rationally distort them to augment the data availability. This method allows a machine learning project to leverage the powerful fit of physics-informed augmentation for providing significant boost to predictive accuracy. Successfully verified by the prediction of rejection rate and flux of thin film polyamide nanofiltration membranes, with the relative error dropping from 16.34% to 6.71% and the coefficient of determination rising from 0.16 to 0.75, the proposed deep spatial learning with molecular vibration is widely instructive for molecular science. Experimental comparison unequivocally demonstrates its superiority over common learning algorithms.