Neuroevolutionary learning of particles and protocols for self-assembly

TL;DR

This paper demonstrates that neuroevolutionary algorithms can autonomously design particles and protocols for self-assembly in simulations, bypassing traditional physical assumptions and enabling both targeted and exploratory material design.

Contribution

It introduces a neuroevolutionary approach for designing self-assembling particles and protocols without relying on physical equilibrium concepts or prior structural knowledge.

Findings

Successfully designed particles and protocols for self-assembly in simulations

Can target specific material properties through directed design

Explores novel structures beyond energy-minimized configurations

Abstract

Within simulations of molecules deposited on a surface we show that neuroevolutionary learning can design particles and time-dependent protocols to promote self-assembly, without input from physical concepts such as thermal equilibrium or mechanical stability and without prior knowledge of candidate or competing structures. The learning algorithm is capable of both directed and exploratory design: it can assemble a material with a user-defined property, or search for novelty in the space of specified order parameters. In the latter mode it explores the space of what can be made rather than the space of structures that are low in energy but not necessarily kinetically accessible.