Machine learning methods for background potential estimation in 2DEGs

Abstract

Two-dimensional electron gases (2DEGs) can show exceptional carrier mobility, making them promising candidates for future quantum technologies. However, impurities and defects can significantly degrade their performance, impacting transport, conductivity, and coherence times. We leverage scanning gate microscopy (SGM) and machine learning approaches to extract the potential landscape of 2DEGs from SGM data. We compare three techniques: image-to-image translation with generative adversarial networks (GANs), cellular neural networks (CNNs), and an evolutionary search algorithm. Notably, the evolutionary approach outperforms both alternatives in defect identification and analysis. This work clarifies the interaction between defects and 2DEG properties, demonstrating the potential of machine learning for understanding and manipulating quantum materials, facilitating advancements in quantum computing and nanoelectronics.