Neural-Network-Biased Genetic Algorithms for Materials Design: Evolutionary Algorithms That Learn
- 9 January 2017
- journal article
- research article
- Published by American Chemical Society (ACS) in ACS Combinatorial Science
- Vol. 19 (2), 96-107
- https://doi.org/10.1021/acscombsci.6b00136
Abstract
Machine learning has the potential to dramatically accelerate high-throughput approaches to materials design, as demonstrated by successes in biomolecular design and hard materials design. However, in the search for new soft materials exhibiting properties and performance beyond those previously achieved, machine learning approaches are frequently limited by two shortcomings. First, because they are intrinsically interpolative, they are better suited to the optimization of properties within the known range of accessible behavior than to the discovery of new materials with extremal behavior. Second, they require large pre-existing data sets, which are frequently unavailable and prohibitively expensive to produce. Here we describe a new strategy, the neural-network-biased genetic algorithm (NBGA), for combining genetic algorithms, machine learning, and high-throughput computation or experiment to discover materials with extremal properties in the absence of pre-existing data. Within this strategy, predictions from a progressively constructed artificial neural network are employed to bias the evolution of a genetic algorithm, with fitness evaluations performed via direct simulation or experiment. In effect, this strategy gives the evolutionary algorithm the ability to “learn” and draw inferences from its experience to accelerate the evolutionary process. We test this algorithm against several standard optimization problems and polymer design problems and demonstrate that it matches and typically exceeds the efficiency and reproducibility of standard approaches including a direct-evaluation genetic algorithm and a neural-network-evaluated genetic algorithm. The success of this algorithm in a range of test problems indicates that the NBGA provides a robust strategy for employing informatics-accelerated high-throughput methods to accelerate materials design in the absence of pre-existing data.Keywords
Funding Information
- W. M. Keck Foundation
This publication has 82 references indexed in Scilit:
- Swarm Intelligence Platform for Multiblock Polymer Inverse Formulation DesignACS Macro Letters, 2016
- Research Update: Computational materials discovery in soft matterAPL Materials, 2016
- Inverse methods for material designAIChE Journal, 2014
- Evolutionary pattern design for copolymer directed self-assemblySoft Matter, 2013
- Inverse Design of Topographical Templates for Directed Self-Assembly of Block CopolymersACS Macro Letters, 2013
- The high-throughput highway to computational materials designNature Materials, 2013
- Quantitative Structure–Property Relationship Modeling of Diverse Materials PropertiesChemical Reviews, 2012
- Robust QSAR model development in high-throughput catalyst discovery based on genetic parameter optimisationChemical Engineering Research and Design, 2009
- Combinatorial and High‐Throughput Materials ScienceAngewandte Chemie-International Edition, 2007
- Computer-based de novo design of drug-like moleculesNature Reviews Drug Discovery, 2005