High-throughput discovery of high Curie point two-dimensional ferromagnetic materials

Databases for two-dimensional materials host numerous ferromagnetic materials without the vital information of Curie temperature since its calculation involves a manually intensive complex process. In this work, we develop a fully automated, hardware-accelerated, dynamic-translation based computer code, which performs first principles-based computations followed by Heisenberg model-based Monte Carlo simulations to estimate the Curie temperature from the crystal structure. We employ this code to conduct a high-throughput scan of 786 materials from a database to discover 26 materials with a Curie point beyond 400 K. For rapid data mining, we further use these results to develop an end-to-end machine learning model with generalized chemical features through an exhaustive search of the model space as well as the hyperparameters. We discover a few more high Curie point materials from different sources using this data-driven model. Such material informatics, which agrees well with recent experiments, is expected to foster practical applications of two-dimensional magnetism.