Figure 2. (IMAGE) Research Organization of Information and Systems Caption Figure 2. Machine learning workflow. A model was created using a random forest classifier that predicts the class label of a given chemical composition as quasicrystal (QC), approximant (AC), or “others”. Model training and testing were performed on the compositional features of 80 known quasicrystals, 78 approximants, and 10,090 ordinary crystals. We then performed high-throughput screening across all Al-TM-TM (TM: transition metal) alloys to generate their predicted phase diagrams. Credit © The Institute of Statistical Mathematics Usage Restrictions Credit required. License Original content Disclaimer: AAAS and EurekAlert! are not responsible for the accuracy of news releases posted to EurekAlert! by contributing institutions or for the use of any information through the EurekAlert system.