Machine Learning based prediction of noncentrosymmetric crystal materials
This work addresses the challenge of discovering noncentrosymmetric materials for applications like laser technology and quantum computing, but it is incremental as it applies existing machine learning methods to a new dataset.
The researchers tackled the problem of predicting noncentrosymmetric crystal materials, which are hard to discover experimentally, by developing a machine learning model that achieved an accuracy of 84.8% on a dataset of 82,506 samples and up to 86.9% for materials with only 3 elements, and used it to screen 2,000,000 hypothetical materials to identify top candidates.
Noncentrosymmetric materials play a critical role in many important applications such as laser technology, communication systems,quantum computing, cybersecurity, and etc. However, the experimental discovery of new noncentrosymmetric materials is extremely difficult. Here we present a machine learning model that could predict whether the composition of a potential crystalline structure would be centrosymmetric or not. By evaluating a diverse set of composition features calculated using matminer featurizer package coupled with different machine learning algorithms, we find that Random Forest Classifiers give the best performance for noncentrosymmetric material prediction, reaching an accuracy of 84.8% when evaluated with 10 fold cross-validation on the dataset with 82,506 samples extracted from Materials Project. A random forest model trained with materials with only 3 elements gives even higher accuracy of 86.9%. We apply our ML model to screen potential noncentrosymmetric materials from 2,000,000 hypothetical materials generated by our inverse design engine and report the top 20 candidate noncentrosymmetric materials with 2 to 4 elements and top 20 borate candidates