Prediction of ferromagnetic materials with high Curie temperature based on material composition information

The search for ferromagnetic materials with high Curie temperature (<i>T</i><sub>c</sub>) is a hot issue in condensed matter physics. In this work, an effective machine learning model of based on material component information established to predict variety temperature. Based the collected data 1568 materials, and taking as descriptors, work four efficient models are constructed, namely support vector regression, kernel ridge random forest extremely randomized trees, through hyperparameter optimization ten-break cross-validation. Of them, tree has best prediction performance, its cross-validation <i>R</i><sup>2</sup> score can reach 81.48%. At same time, also used 36949 project database, 338 <i>T</i><sub>c</sub> greater than 600 K found work. method proposed paper help obtain accelerate process design.