Machine Learning for Charge State Characterization of Isolated Double Quantum Dots
Hyma Harish Vallabhapurapu, Marco Candido, Krishna Choudhary, Paul Steinacker, Ensar Vahapoglu, Christopher C. Escott, Wee Han Lim, André Saraiva, Nard Dumoulin Stuyck, MengKe Feng
Scaling semiconductor quantum dot arrays toward fault-tolerant quantum computing requires efficient tuneup of spin qubits, a process that depends on the analysis of charge stability maps (CSMs) and remains largely manual. While machine learning has been widely applied to CSM analysis in reservoir-coupled devices, automated tuning in the increasingly important isolated-mode regime has received limited attention. In isolated-mode CSMs, charge transitions appear as near-vertical lines, making them well suited to compact, task-specific models. We present two convolutional neural networks with fewer than one million parameters, trained on CSMs collected from 32 silicon metal-oxide-semiconductor (SiMOS) double-quantum-dot devices measured at approximately 1 K using an automated cryogenic probing system. Sixteen devices were used for training and sixteen were held out to evaluate cross-device generalization against hand-labeled ground truth. CSMClassifier identifies charge instability and sensor artifacts, achieving 94% macro-averaged accuracy across three quality classes on 2,407 held-out images. ChargeLineNet localizes charge-transition lines and determines electron occupancy, achieving 95.3% exact line-count accuracy on 1,131 held-out images. Combined into a single pipeline, the models correctly determine electron occupancy for 93.8% of clean held-out images. Pre-training on synthetic images substantially improves label efficiency. Fine-tuning the pre-trained model on limited experimental data maintains over 90% accuracy, whereas training from scratch degrades significantly under the same conditions. Together, the two models occupy only 6.5 MB and process images in less than 60 ms on standard laboratory hardware, demonstrating a practical path toward scalable, automated characterization and tuneup of quantum-dot devices.
Scaling semiconductor quantum dot arrays toward fault-tolerant quantum computing requires efficient tuneup of spin qubits, a process that depends on the analysis of charge stability maps (CSMs) and remains largely manual. While machine learning has been widely applied to CSM analysis in reservoir-coupled devices, automated tuning in the increasingly important isolated-mode regime has received limited attention. In isolated-mode CSMs, charge transitions appear as near-vertical lines, making them well suited to compact, task-specific models. We present two convolutional neural networks with fewer than one million parameters, trained on CSMs collected from 32 silicon metal-oxide-semiconductor (SiMOS) double-quantum-dot devices measured at approximately 1 K using an automated cryogenic probing system. Sixteen devices were used for training and sixteen were held out to evaluate cross-device generalization against hand-labeled ground truth. CSMClassifier identifies charge instability and sensor artifacts, achieving 94% macro-averaged accuracy across three quality classes on 2,407 held-out images. ChargeLineNet localizes charge-transition lines and determines electron occupancy, achieving 95.3% exact line-count accuracy on 1,131 held-out images. Combined into a single pipeline, the models correctly determine electron occupancy for 93.8% of clean held-out images. Pre-training on synthetic images substantially improves label efficiency. Fine-tuning the pre-trained model on limited experimental data maintains over 90% accuracy, whereas training from scratch degrades significantly under the same conditions. Together, the two models occupy only 6.5 MB and process images in less than 60 ms on standard laboratory hardware, demonstrating a practical path toward scalable, automated characterization and tuneup of quantum-dot devices.
Abstract Recent progress in building large-scale quantum devices for exploring quantum computing and simulation has relied upon effective tools for achieving and maintaining good experimental parameters, i.e., tuning up devices. In many cases, including quantum dot-based architectures, the parameter space grows substantially with the number of qubits, and may become a limit to scalability. Fortunately, machine learning techniques for pattern recognition and image classification, using so-called deep neural networks, have shown surprising successes for computer-aided understanding of complex systems. We propose a new paradigm for fully automated experimental initialization through a closed-loop system relying on machine learning and optimization techniques. We use deep convolutional neural networks to characterize states and charge configurations of semiconductor quantum dot arrays when only measurements of a current−voltage characteristic of transport are available. For simplicity, we model a semiconductor nanowire connected to leads and capacitively coupled to depletion gates using the Thomas−Fermi approximation and Coulomb blockade physics. We then generate labeled training data for the neural networks, and find at least 90 % accuracy for charge and state identification for single and double dots. Using these characterization networks, we can then optimize the parameter space to achieve a desired configuration of the array, a technique we call “auto-tuning”. Finally, we show how such techniques can be implemented in an experimental setting by applying our approach to an experimental dataset, and outline further problems in this domain, from using charge sensing data to extensions to full one- and two-dimensional arrays, that can be tackled with machine learning.
Abstract Tuning of gate-defined semiconductor quantum dots (QDs) is a major bottleneck for scaling spin-qubit technologies. We present a deep learning driven, semantic-segmentation pipeline that performs charge auto-tuning by locating transition lines in full charge stability diagrams (CSDs) and returns gate voltage targets for the single charge regime. We assemble and manually annotate a large, heterogeneous dataset of 1015 experimental CSDs measured from fully depleted silicon-on-insulator (FD-SOI) QD devices, spanning nine design geometries, multiple wafers, and fabrication runs. A U-Net style convolutional neural network with a MobileNetV2 encoder is trained and validated through five-fold group cross-validation. Our model achieves an overall offline tuning success of 80.0% in locating the single-charge regime, with peak performance exceeding 88% for some designs. We analyze dominant failure modes and propose targeted mitigations. Finally, wide-range diagram segmentation also naturally enables scalable physics-based feature extraction that can feed back to fabrication and design workflows and outline a roadmap for real-time integration in a cryogenic wafer prober. Overall, our results show that neural network based wide-diagram segmentation is a practical step toward automated, high-throughput charge tuning for silicon QD qubits.
Semiconductor quantum computing leverages quantum dots as qubits, where achieving high qubit fidelity is one essential requirement for scalability. The formation of qubits and associated sensor dots necessitates meticulous iterative voltage adjustments, a tuning process that is ordinarily executed manually by researchers. While various automated approaches have been proposed, only a few address scalability in the context of a system with a million qubits or consider shifting key data analysis tasks into the cryostat. The latter is necessary to alleviate wiring constraints and to minimize data transmission to room temperature electronics. This thesis explores scalable solutions for automated in-cryostat data analysis, identifying charge transition detection as a pivotal task. A simulation model is developed to generate realistic charge stability diagrams with known ground truth. The model’s output is benchmarked against experimental data to verify fidelity and diversity. Utilizing this model, a comprehensive evaluation of charge transition detection methods is conducted, comparing classical algorithms and a range of machine learning approaches. In consideration of energy-efficient integration, this study includes an initial investigation into reducing the complexity of convolutional neural networks. Subsequent to their optimization using simulated data, the approaches are benchmarked on both simulated and experimental data from diverse qubit samples. When applied to contemporary data qualities, evidence is presented that classical approaches are inadequate in terms of robustness and accuracy while numerous machine learning models demonstrate compelling performance. Among the latter, convolutional neural networks like U-Net are identified to be particularly eligible due to their advantageous structure for efficient hardware integration. Although the U-Net architecture already demonstrates a strong potential for network size reduction under current data quality constraints, a cryogenic hardware integration remains a significant challenge. Consequently, a subsequent study explores if enhanced sensor dot tuning and sensor compensation reduce the complexity of charge transition analysis and if they enable the utilization of ray-based detection methodologies. The findings indicate that particularly sensor compensation has a substantial impact on the data quality and allows a streamlining of the analytical process. However, achieving robust ray-based analysis remains feasible only if consistently reaching the highest observed measurement quality and utilizing machine learning. Even in this case, classical methods and a proposed averaging and thresholding circuit fall short of the requisite detection accuracy. Only with further improvements toward optimal data quality and additional enhancements to the proposed circuit, an integrated solution without machine learning appears attainable. Finally, the energy efficiency of scaled-down neural networks is assessed using state-of-the art hardware accelerators. The findings suggest that the cryogenic integration of machine learning-based charge transition detection is feasible, thus propelling the development of scalable and energy-efficient quantum control architectures.
Semiconductor quantum computing leverages quantum dots as qubits, where achieving high qubit fidelity is one essential requirement for scalability. The formation of qubits and associated sensor dots necessitates meticulous iterative voltage adjustments, a tuning process that is ordinarily executed manually by researchers. While various automated approaches have been proposed, only a few address scalability in the context of a system with a million qubits or consider shifting key data analysis tasks into the cryostat. The latter is necessary to alleviate wiring constraints and to minimize data transmission to room temperature electronics. This thesis explores scalable solutions for automated in-cryostat data analysis, identifying charge transition detection as a pivotal task. A simulation model is developed to generate realistic charge stability diagrams with known ground truth. The model’s output is benchmarked against experimental data to verify fidelity and diversity. Utilizing this model, a comprehensive evaluation of charge transition detection methods is conducted, comparing classical algorithms and a range of machine learning approaches. In consideration of energy-efficient integration, this study includes an initial investigation into reducing the complexity of convolutional neural networks. Subsequent to their optimization using simulated data, the approaches are benchmarked on both simulated and experimental data from diverse qubit samples. When applied to contemporary data qualities, evidence is presented that classical approaches are inadequate in terms of robustness and accuracy while numerous machine learning models demonstrate compelling performance. Among the latter, convolutional neural networks like U-Net are identified to be particularly eligible due to their advantageous structure for efficient hardware integration. Although the U-Net architecture already demonstrates a strong potential for network size reduction under current data quality constraints, a cryogenic hardware integration remains a significant challenge. Consequently, a subsequent study explores if enhanced sensor dot tuning and sensor compensation reduce the complexity of charge transition analysis and if they enable the utilization of ray-based detection methodologies. The findings indicate that particularly sensor compensation has a substantial impact on the data quality and allows a streamlining of the analytical process. However, achieving robust ray-based analysis remains feasible only if consistently reaching the highest observed measurement quality and utilizing machine learning. Even in this case, classical methods and a proposed averaging and thresholding circuit fall short of the requisite detection accuracy. Only with further improvements toward optimal data quality and additional enhancements to the proposed circuit, an integrated solution without machine learning appears attainable. Finally, the energy efficiency of scaled-down neural networks is assessed using state-of-the art hardware accelerators. The findings suggest that the cryogenic integration of machine learning-based charge transition detection is feasible, thus propelling the development of scalable and energy-efficient quantum control architectures.
As quantum dot (QD)-based spin qubits advance toward larger, more complex device architectures, rapid, automated device characterization and data analysis tools become critical. The orientation and spacing of transition lines in a charge stability diagram (CSD) contain a fingerprint of a QD device's capacitive environment, making these measurements useful tools for device characterization. However, manually interpreting these features is time-consuming, error-prone, and impractical at scale. Here, we present an automated protocol for extracting underlying capacitive properties from CSDs. Our method integrates machine learning, image processing, and object detection to identify and track charge transitions across large datasets without manual labeling. We demonstrate this method using experimentally measured data from a strained-germanium single-quantum-well (planar) and a strained-germanium double-quantum-well (bilayer) QD device. Unlike for planar QD devices, CSDs in bilayer germanium heterostructure exhibit a larger set of transitions, including interlayer tunneling and distinct loading lines for the vertically stacked QDs, making them a powerful testbed for automation methods. By analyzing the properties of many CSDs, we can statistically estimate physically relevant quantities, like relative lever arms and capacitive couplings. Thus, our protocol enables rapid extraction of useful, nontrivial information about QD devices.
Reliable detection of charge transitions in charge stability diagrams (CSDs) is a key requirement for the full automation of quantum dot device control. Performing this task directly at the cryogenic stage reduces data transfer and supports scalability. To provide the large labeled datasets required for developing and evaluating detection methods, we introduced SimCATS [1], a simulator that generates realistic CSDs including sensor responses and distortions. We optimize both traditional and machine-learning-based detection methods using simulated data and benchmark them on simulated and experimental measurements from GaAs and SiGe qubit devices. We also investigate the potential of model compression and find its performance closely tied to task complexity, which can be alleviated by sensor dot compensation. In fact, we find that sensor compensation allows machine-learning approaches to be reduced in size by up to two orders of magnitude while maintaining, or even improving, detection quality. Together with high-quality measurements, this enables robust and scalable (ray-based) charge transition detection. Finally, we estimate the cryogenic power budget for applying this approach to large-scale systems with up to one million qubits. [1] F. Hader et al., "Simulation of Charge Stability Diagrams for Automated Tuning Solutions (SimCATS)", IEEE Transactions on Quantum Engineering, DOI: 10.1109/TQE.2024.3445967 (2024).