Inversion of the chemical environment representations

TL;DR

This paper introduces a general optimization method to invert local many-body chemical environment descriptors into Cartesian atomic configurations, enhancing the flexibility of generative models in material design.

Contribution

It presents a novel, general inversion algorithm for local many-body descriptors, demonstrated with bispectrum, enabling better structural generative models.

Findings

Successfully inverted bispectrum descriptors for molecules

Enhanced flexibility in choosing structural descriptors

Facilitated the construction of generative models

Abstract

Machine-learning generative methods for material design are constructed by representing a given chemical structure, either a solid or a molecule, over appropriate atomic features, generally called structural descriptors. These must be fully descriptive of the system, must facilitate the training process and must be invertible, so that one can extract the atomic configurations corresponding to the output of the model. In general, this last requirement is not automatically satisfied by the most efficient structural descriptors, namely the representation is not directly invertible. Such drawback severely limits our freedom of choice in selecting the most appropriate descriptors for the problem, and thus our flexibility to construct generative models. In this work, we present a general optimization method capable of inverting any local many-body descriptor of the chemical environment, back to a cartesian representation. The algorithm is then implemented together with the bispectrum representation of the local structure and demonstrated for a number of molecules. The scheme presented here, thus, represents a general approach to the inversion of structural descriptors, enabling the construction of efficient structural generative models.