Neuroevolutionary learning of particles and protocols for self-assembly
This work addresses the challenge of designing self-assembling materials for researchers in materials science, offering a method that does not require traditional physical insights.
This paper demonstrates that neuroevolutionary learning can design both particles and time-dependent protocols to achieve self-assembly in molecular simulations. The algorithm successfully promotes self-assembly without relying on physical concepts or prior knowledge of structures, and can operate in both directed and exploratory design modes.
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.