Optimization of high-temperature superconducting multilayer films using artificial intelligence

We have studied the possibility of utilizing artificial intelligence (AI) models to optimize high-temperature superconducting (HTS) multilayer structures for applications working in a specific field and temperature range. For this, we propose a new vortex dynamics simulation method that enables unprecedented efficiency in the sampling of training data required by the AI models. The performance of several different types of AI models has been studied, including kernel ridge regression (KRR), gradient-boosted decision tree (GBDT) and neural network. From these, the GBDT based model was observed to be clearly the best fitted for the associated problem. We have demonstrated the use of GBDT for finding optimal multilayer structure at 10 K temperature under 1 T field. The GBDT model predicts that simple doped-undoped bilayer structures, where the vast majority of the film is undoped superconductor, provide the best performance under the given environment. The obtained results coincide well with our previous studies providing further validation for the use of AI in the associated problem. We generally consider the AI models as highly efficient tools for the broad-scale optimization of HTS multilayer structures and suggest them to be used as the foremost method to further push the limits of HTS films for specific applications.

Automated summary

This study investigates the possibility of using artificial intelligence (AI) models to optimize high-temperature superconducting (HTS) multilayer structures for specific field and temperature ranges. A new vortex dynamics simulation method is proposed to improve the efficiency of training data sampling required for AI models. The performance of different AI models, including kernel ridge regression (KRR), gradient-boosted decision tree (GBDT), and neural network, is compared, and the GBDT model is found to be the best fitted for the problem. The use of GBDT in finding optimal multilayer structures at 10K temperature under 1T field is demonstrated, and the results align well with previous studies, further validating the use of AI in this problem. The AI models are considered highly efficient tools for optimizing HTS multilayer structures and are suggested as the primary method for pushing the limits of HTS films for specific applications.