Bias triangles represent features in stability diagrams of Quantum Dot (QD) devices, whose occurrence and property analysis are crucial indicators for spin physics. Nevertheless, challenges associated with quality and availability of data as well as the subtlety of physical phenomena of interest have hindered an automatic and bespoke analysis framework, often still relying (in part) on human labelling and verification. We introduce a feature extraction framework for bias triangles, built from unsupervised, segmentation-based computer vision methods, which facilitates the direct identification and quantification of physical properties of the former. Thereby, the need for human input or large training datasets to inform supervised learning approaches is circumvented, while additionally enabling the automation of pixelwise shape and feature labeling. In particular, we demonstrate that Pauli Spin Blockade (PSB) detection can be conducted effectively, efficiently and without any training data as a direct result of this approach.
Bias triangles represent features in stability diagrams of Quantum Dot (QD) devices, whose occurrence and property analysis are crucial indicators for spin physics. Nevertheless, challenges associated with quality and availability of data as well as the subtlety of physical phenomena of interest have hindered an automatic and bespoke analysis framework, often still relying (in part) on human labelling and verification. We introduce a feature extraction framework for bias triangles, built from unsupervised, segmentation-based computer vision methods, which facilitates the direct identification and quantification of physical properties of the former. Thereby, the need for human input or large training datasets to inform supervised learning approaches is circumvented, while additionally enabling the automation of pixelwise shape and feature labeling. In particular, we demonstrate that Pauli Spin Blockade (PSB) detection can be conducted effectively, efficiently and without any training data as a direct result of this approach.
Spanning over two decades, the study of qubits in semiconductors for quantum computing has yielded significant breakthroughs. However, the development of large-scale semiconductor quantum circuits is still limited by challenges in efficiently tuning and operating these circuits. Identifying optimal operating conditions for these qubits is complex, involving the exploration of vast parameter spaces. This presents a real ‘needle in the haystack’ problem, which, until now, has resisted complete automation due to device variability, fabrication imperfections, and limited data availability. In this thesis, I first present a machine learning algorithm capable of automatically identifying Pauli spin blockade (PSB) using charge transport measurements. PSB can be employed as a resource for spin qubit initialisation and readout but it can be difficult to identify. The scarcity of PSB data is circumvented by training the algorithm with simulated data and by using cross-device validation. I demonstrate the approach on a silicon field-effect transistor device and report a high accuracy on test devices, giving evidence that the approach is robust to device variability. Then, I present the first fully autonomous tuning of a semiconductor qubit, from a grounded device to Rabi oscillations, a clear indication of successful qubit operation. This automation, achieved without human intervention, is demonstrated in a Ge/Si core/shell nanowire device and integrates deep learning, Bayesian optimisation, and computer vision techniques. Further, I demonstrate the potential of full automation by characterising how the Rabi frequency and g-factor depend on barrier gate voltages for qubits in four different charge transitions. The data reveals that certain features in charge transport measurements can enhance automated tuning processes by recognising the conditions for successful readout. Finally, I present the autonomous optimisation of two qubits for maximal Rabi frequency. This optimisation extends the tuning algorithm, enabling it to enhance the performance of a qubit. I hope the mass tuning and characterisation of qubits, enabled by the methods in this thesis, will create a productive feedback loop between measurement and fabrication processes. Wafer-scale, high-throughput characterisation of quantum devices can mitigate device variability and contribute to their scalability. The continued evolution of these methods will support the growing demands of the field, ultimately – and hopefully – leading to practical and powerful quantum computers.
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.
Pauli spin blockade (PSB) can be employed as a great resource for spin qubit initialisation and readout even at elevated temperatures but it can be difficult to identify. We present a machine learning algorithm capable of automatically identifying PSB using charge transport measurements. The scarcity of PSB data is circumvented by training the algorithm with simulated data and by using cross-device validation. We demonstrate our approach on a silicon field-effect transistor device and report an accuracy of 96% on different test devices, giving evidence that the approach is robust to device variability. Our algorithm, an essential step for realising fully automatic qubit tuning, is expected to be employable across all types of quantum dot devices.
Abstract Pauli spin blockade (PSB) can be employed as a great resource for spin qubit initialisation and readout even at elevated temperatures but it can be difficult to identify. We present a machine learning algorithm capable of automatically identifying PSB using charge transport measurements. The scarcity of PSB data is circumvented by training the algorithm with simulated data and by using cross-device validation. We demonstrate our approach on a silicon field-effect transistor device and report an accuracy of 96% on different test devices, giving evidence that the approach is robust to device variability. The approach is expected to be employable across all types of quantum dot devices.
Abstract The rapid development of quantum dot (QD) devices for quantum computing has necessitated more efficient and automated methods for device characterization and tuning. Many of the measurements acquired during the tuning process come in the form of images that need to be properly analyzed to guide the subsequent tuning steps. By design, features present in such images capture certain behaviors or states of the measured QD devices. When considered carefully, such features can aid the control and calibration of QD devices. An important example of such images are so-called triangle plots , which visually represent current flow and reveal characteristics important for QD device calibration. While image-based classification tools, such as convolutional neural networks (CNNs), can be used to verify whether a given measurement is good and thus warrants the initiation of the next phase of tuning, they do not provide any insights into how the device should be adjusted in the case of bad images. This is because CNNs sacrifice prediction and model intelligibility for high accuracy. To ameliorate this trade-off, a recent study introduced an image vectorization approach that relies on the Gabor wavelet transform (Schug et al 2024 Proc. XAI4Sci: Explainable Machine Learning for Sciences Workshop (AAAI 2024) (Vancouver, Canada) pp 1–6). Here we propose an alternative vectorization method that involves mathematical modeling of synthetic triangles to mimic the experimental data. Using explainable boosting machines, we show that this new method offers superior explainability of model prediction without sacrificing accuracy. This work demonstrates the feasibility and advantages of applying explainable machine learning techniques to the analysis of QD measurements, paving the way for further advances in automated and transparent QD device tuning.
This paper explores the application of a novel quantum machine learning framework, termed "Adaptive Quantum Machine Learning" (AQML), for the extraction of crucial topological information from complex datasets. Traditional data analysis and feature extraction methods often rely on manual intervention, limiting efficiency and potentially introducing human bias. AQML leverages quantum computing's inherent parallelism to automatically identify and isolate key topological features within datasets, dramatically enhancing the speed and accuracy of analysis. We present a detailed implementation of the AQML algorithm, outlining its architecture, computational methodology, and validation results. This approach promises to revolutionize data analysis by automating the extraction of critical topological properties, enabling more efficient and insightful data exploration. This work is motivated by the need for more robust and adaptable methods in the analysis of complex, high-dimensional datasets, particularly in fields such as materials science, biology, and network analysis.