An acceleration search method of higher T c superconductors by a machine learning algorithm

We propose a method to efficiently search for superconductors with higher critical temperature Tc by machine learning based on a superconductor database. The Tc prediction and the search for new superconductors are still difficult problems. With the progress of computer power and calculation algorithms, the possibility of finding new materials with higher Tc at high throughput is emerging. Using the obtained Tc prediction model, the scope is expanded to the search space of multielement materials that have never been searched, and candidates for superconductors with higher Tc that can be synthesized are proposed.