(747b) Discovering Crystals Using Shape Matching and Machine Learning
AIChE Annual Meeting
2013
2013 AIChE Annual Meeting
Computing and Systems Technology Division
Molecular and Mesoscopic Systems: Methods and Applications
Thursday, November 7, 2013 - 3:35pm to 3:55pm
As the effective interactions between particles at the nano- to colloidal scale can be tailored and tuned in many ways, by using DNA and polymer functionalization, depletants, and solvents, there is a vast parameter space of design choices. Using simplified coarse-grained representations of the effective interactions between particles, computer experiments are an essential research tool for both exploring the vast space, and for investigating the first principles of self-assembly. The rate at which data can be amassed through computational simulation continues to accelerate, and thus the pace of discovery becomes limited not by the rate at which data can be generated, but can be analyzed.
We show how new crystalline structures can be identified automatically from analysis of large data set. By deploying a hierarchy of pattern analysis techniques using shape matching[1] and machine learning algorithms[2], local structures are extracted, classified, and then used to partition a data set into a phase diagram of similar crystals[3]. This method requires no a-priori knowledge of what might be present in the data set.
To demonstrate the method, we apply it to data generated from a parameter sweep of a constructed pair potential for a system of interacting particles (though our approach is generalizable to any model or data source). The data set contains a broad range of structures from simple to complex. We show how phase diagrams can be automatically generated, searches for new structures focused, and how the discovery of new materials can be accelerated.
[1] C.R. Iacovella, A.S. Keys and S.C. Glotzer, “Characterizing complex particle morphologies through shape matching: Descriptors, applications, and algorithms,” J. Comp. Physics 230(17), 6436-6463 (2011)
[2] A. Pandini, A. Fornili and J. Kleinjung, "Structural alphabets derived from attractors in conformational space," BMC Bioinformatics 11 (2010)
[3] C.L. Phillips, G.A.Voth, "Discovering crystals using shape matching and machine learning," Preprint, 2013