Quantum Machine Learning in Materials Prediction: A Case Study on ABO3 Perovskite Structures.
Quantum machine learning (QML), ML on quantum computers, offers a promising approach for discovering and screening novel materials. This study introduces a hybrid classical-quantum ML method using a variational quantum classifier to identify simple perovskite structures within a data set of ABO3 compounds. The model is trained using a data set of 397 known ABO3 compounds, with 254 perovskites and 143 non-perovskite structures labeled as +1 and -1, respectively. By considering feature correlation and eliminating less important features, the QML system achieves an optimal accuracy of 88% for training data and 87% for unseen test data. These results demonstrate the potential of QML in materials science classification tasks, even with limited training data, leveraging the intrinsic properties of quantum computation to enhance the investigation of materials. In addition, perspectives on QML applications in materials science are discussed.
Paper
Full text
Quantum Machine Learning in Materials Prediction: A Case Study on ABO3 Perovskite Structures.
Semantic Scholar · Materials Science · 2023
Abstract
Quantum machine learning (QML), ML on quantum computers, offers a promising approach for discovering and screening novel materials. This study introduces a hybrid classical-quantum ML method using a variational quantum classifier to identify simple perovskite structures within a data set of ABO3 compounds. The model is trained using a data set of 397 known ABO3 compounds, with 254 perovskites and 143 non-perovskite structures labeled as +1 and -1, respectively. By considering feature correlation and eliminating less important features, the QML system achieves an optimal accuracy of 88% for training data and 87% for unseen test data. These results demonstrate the potential of QML in materials science classification tasks, even with limited training data, leveraging the intrinsic properties of quantum computation to enhance the investigation of materials. In addition, perspectives on QML applications in materials science are discussed.