Reinforcement learning-guided optimization of critical current in high-temperature superconductors

2025-10-25

AI Summary

The critical current density (J_c) of high-temperature superconductors is fundamentally limited by the efficacy of microscopic defects in pinning magnetic vortices; however, conventional defect engineering struggles to concurrently optimize defect type, density, and spatial correlations. Method: This work introduces reinforcement learning (RL) to superconducting defect design for the first time, establishing a closed-loop optimization framework that integrates RL with time-dependent Ginzburg–Landau micromagnetic simulations, using I–V characteristics as feedback to autonomously discover optimal defect configurations. Contribution/Results: The approach enables end-to-end intelligent optimization of defect distributions without requiring prior physical models. In two-dimensional thin films, the RL-optimized configuration achieves a J_c reaching 60% of the theoretical depairing limit—15× higher than that of random defects—demonstrating unprecedented proximity to the fundamental pinning performance ceiling. This establishes a new paradigm for rational design of high-field superconducting materials.

Technology Category

• Search and Optimization: Learning to Search
• Machine Learning: Optimization
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

Abstract

High-temperature superconductors are essential for next-generation energy and quantum technologies, yet their performance is often limited by the critical current density ($J_c$), which is strongly influenced by microstructural defects. Optimizing $J_c$ through defect engineering is challenging due to the complex interplay of defect type, density, and spatial correlation. Here we present an integrated workflow that combines reinforcement learning (RL) with time-dependent Ginzburg-Landau (TDGL) simulations to autonomously identify optimal defect configurations that maximize $J_c$. In our framework, TDGL simulations generate current-voltage characteristics to evaluate $J_c$, which serves as the reward signal that guides the RL agent to iteratively refine defect configurations. We find that the agent discovers optimal defect densities and correlations in two-dimensional thin-film geometries, enhancing vortex pinning and $J_c$ relative to the pristine thin-film, approaching 60% of theoretical depairing limit with up to 15-fold enhancement compared to random initialization. This RL-driven approach provides a scalable strategy for defect engineering, with broad implications for advancing HTS applications in fusion magnets, particle accelerators, and other high-field technologies.

Problem

• Optimizing critical current density in high-temperature superconductors through defect engineering
• Using reinforcement learning to identify optimal defect configurations for vortex pinning
• Enhancing superconductor performance for energy and quantum technologies

Innovation

• Reinforcement learning optimizes defect configurations autonomously
• TDGL simulations evaluate critical current as reward signal
• Agent discovers optimal defect densities and correlations