Collaborative crystal structure prediction

作者：

Highlights：

• Machine learning based crystal structure prediction algorithms are proposed.

• Ionic substitution probabilities are refined by matrix factorization techniques.

• Using priors for implicit chemical property, probability model is further revised.

摘要

•Machine learning based crystal structure prediction algorithms are proposed.•Ionic substitution probabilities are refined by matrix factorization techniques.•Using priors for implicit chemical property, probability model is further revised.

论文关键词：Crystal structure prediction,High-throughput computational screening,Collaborative filtering,Side information

论文评审过程：Received 26 April 2016, Revised 27 June 2016, Accepted 1 July 2016, Available online 5 July 2016, Version of Record 15 July 2016.

论文官网地址：https://doi.org/10.1016/j.eswa.2016.07.001