Feature Engineering of Solid‐State Crystalline Lattices for Machine Learning. Issue 2 (15th December 2019)

• Record Type: Journal Article
• Authors: Cox, Timothy; Motevalli, Benyamin; Opletal, George; Barnard, Amanda S.
• Is Part Of: Advanced theory and simulations. Volume 3:Issue 2(2020)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2019-12-15
• Subjects: amorphous materials -- crystal lattices -- machine learning -- semiconductors; Science -- Simulation methods -- Periodicals; Science -- Methodology -- Periodicals; Engineering -- Simulation methods -- Periodicals; Engineering -- Methodology -- Periodicals; 507.21
• DOI: 10.1002/adts.201900190
• Languages: English
• ISSNs: 2513-0390

Abstract

Abstract: The problem of feature extraction, in crystalline solid‐state systems with point defects, is considered. Novel methods for creating features for use in machine‐learning‐based predictive modeling of such systems are developed. The methods are illustrated in a case study where machine learning methods are used to predict the onset of amorphization in crystalline systems containing vacancy defects. How the methods developed may be generalized to study other problems in solid‐state materials is also discussed. Abstract : Machine learning is an important enabler in materials design, but results depend sensitively on the type of the features describing the material. Many materials features are drawn from materials chemistry, which risks biasing models toward a molecular description. This can be mitigated by extracting features relevant to solid‐state systems, in both real and reciprocal space, while respecting periodic boundary conditions.