Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

ACS Nano

Machine Learning-Assisted Precision Manufacturing of Atom Qubits in Silicon

Aaron D. Tranter, Ludwik Kranz, Sam Sutherland, Joris Gerhard Keizer, Samuel Keith Gorman, B. C. Buchler, Michelle Yvonne Simmons

Published Jul 17, 2024• 11 citations
Publisher

Abstract

Donor-based qubits in silicon, manufactured using scanning tunneling microscope (STM) lithography, provide a promising route to realizing full-scale quantum computing architectures. This is due to the precision of donor placement, long coherence times, and scalability of the silicon material platform. The properties of multiatom quantum dot qubits, however, depend on the exact number and location of the donor atoms within the quantum dots. In this work, we develop machine learning techniques that allow accurate and real-time prediction of the donor number at the qubit site during STM patterning. Machine learning image recognition is used to determine the probability distribution of donor numbers at the qubit site directly from STM images during device manufacturing. Models in excess of 90% accuracy are found to be consistently achieved by mitigating overfitting through reduced model complexity, image preprocessing, data augmentation, and examination of the intermediate layers of the convolutional neural networks. The results presented in this paper constitute an important milestone in automating the manufacture of atom-based qubits for computation and sensing applications.

DOI
10.1021/acsnano.4c00080

Related papers

Framework for atomic-level characterisation of quantum computer arrays by machine learning

Muhammad Usman, Yi Zheng Wong, Charles D. Hill +1 more

Abstract Atomic-level qubits in silicon are attractive candidates for large-scale quantum computing; however, their quantum properties and controllability are sensitive to details such as the number of donor atoms comprising a qubit and their precise location. This work combines machine learning techniques with million-atom simulations of scanning tunnelling microscopic (STM) images of dopants to formulate a theoretical framework capable of determining the number of dopants at a particular qubit location and their positions with exact lattice site precision. A convolutional neural network (CNN) was trained on 100,000 simulated STM images, acquiring a characterisation fidelity (number and absolute donor positions) of >98% over a set of 17,600 test images including planar and blurring noise commensurate with experimental measurements. The formalism is based on a systematic symmetry analysis and feature-detection processing of the STM images to optimise the computational efficiency. The technique is demonstrated for qubits formed by single and pairs of closely spaced donor atoms, with the potential to generalise it for larger donor clusters. The method established here will enable a high-precision post-fabrication characterisation of dopant qubits in silicon, with high-throughput potentially alleviating the requirements on the level of resources required for quantum-based characterisation, which will otherwise be a challenge in the context of large qubit arrays for universal quantum computing.

arXiv:1904.01756•npj Computational Materials•Mar 16, 2020•28 citations

Automatic tuning of a donor in a silicon quantum device using machine learning

Brandon Severin, Tim Botzem, Federico Fedele +12 more

Donor spin qubits in silicon offer one- and two-qubit gates with fidelities beyond 99%, coherence times exceeding 30 seconds, and compatibility with industrial manufacturing methods. This motivates the development of large-scale quantum processors using this platform, and the ability to automatically tune and operate such complex devices. In this work, we present the first machine learning algorithm with the ability to automatically locate the charge transitions of an ion-implanted donor in a silicon device, tune single-shot charge readout, and identify the gate voltage parameters where tunnelling rates in and out the donor site are the same. The entire tuning pipeline is completed on the order of minutes. Our results enable both automatic characterisation and tuning of a donor in silicon devices faster than human experts.

cond-mat.mes-hallCross-listedarXiv:2511.04543•Nov 7, 2025•0 citations

Machine learning techniques for state recognition and auto-tuning in quantum dots

Sandesh S. Kalantre, Justyna P. Zwolak, Stephen Ragole +4 more

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.

arXiv:1712.04914•npj Quantum Information•Jan 14, 2019•122 citations

Autotuning of Double-Dot Devices In Situ with Machine Learning

Justyna P. Zwolak, Thomas McJunkin, Sandesh S. Kalantre +7 more

A primary obstacle in scaling up quantum computing platforms based on semiconductor quantum dots (QDs) is the full automation of initialization and control. Using ideas from machine learning (ML), pattern recognition, and optimization, the authors implement an autotuning protocol that needs no human intervention to navigate between QD states in real time. A convolutional neural network identifies QD states from $i\phantom{\rule{0}{0ex}}n$ $s\phantom{\rule{0}{0ex}}i\phantom{\rule{0}{0ex}}t\phantom{\rule{0}{0ex}}u$ measurements; importantly, the network is trained exclusively on simulated data, and the scans used are significantly smaller that in manual tuning, and hence much faster. This development is critical to moving up to larger numbers of quantum dots.

arXiv:1909.08030•Physical Review Applied•Mar 31, 2020•88 citations

Fabricating an all-epitaxial silicon quantum computer

John R. Tucker, T. C. Shen

Scalable silicon quantum computers will require a material perfection that has never been attempted. Ground state wavefunctions for conduction electrons orbiting individual phosphorous donors must be polarized electronically and coupled to nearest neighbors with great precision. Elimination of all randomizing influences can be achieved only with a fully epitaxial structure; and we believe that output circuitry must also be integrated into the qubit arrays in order to achieve the uniformity needed for large-scale integration. A process that could potentially accomplish this will be outlined, based on scanning tunneling microscope (STM) removal of individual hydrogen atoms from the H-terminated silicon surface followed by phosphine dosing and ultra-low-temperature overgrowth. Self-ordering of PH3 molecules onto extended areas of bare silicon should permit patterning of planar single-electron transistors along with P-donor qubits in the same lithographic step. Initial plans for an experiment to characterize exchange coupling under gate control will be described.

Quantum Information and Computation•Dec 1, 2001•2 citations

Characterization of a Scalable Donor-Based Singlet–Triplet Qubit Architecture in Silicon

Prasanna Pakkiam, Matthew Gregory House, Matthias Koch +1 more

We present a donor-based quadruple-quantum-dot device, designed to host two singlet–triplet qubits fabricated by scanning tunnelling microscope lithography, with just two leads per qubit. The design is geometrically compact, with each pair of dots independently controlled via one gate and one reservoir. The reservoirs both supply electrons for the dots and measure the singlet–triplet state of each qubit via dispersive sensing. We verify the locations of the four phosphorus donor dots via an electrostatic model of the device. We study one of the observed singlet–triplet states with a tunnel coupling of 39 GHz and a S 0 -to- T – decay of 2 ms at zero detuning. We measure a 5 GHz electrostatic interaction between two pairs of dots separated by 65 nm. The results outline a low-gate-density pathway to a scalable 1D building block of atomic-precision singlet–triplet qubits using donors with dispersive readout.

Nano Letters•May 24, 2018•12 citations
Donor-based qubits in silicon, manufactured using scanning tunneling microscope (STM) lithography, provide a promising route to realizing full-scale quantum computing architectures. This is due to the precision of donor placement, long coherence times, and scalability of the silicon material platform. The properties of multiatom quantum dot qubits, however, depend on the exact number and location of the donor atoms within the quantum dots. In this work, we develop machine learning techniques that allow accurate and real-time prediction of the donor number at the qubit site during STM patterning. Machine learning image recognition is used to determine the probability distribution of donor numbers at the qubit site directly from STM images during device manufacturing. Models in excess of 90% accuracy are found to be consistently achieved by mitigating overfitting through reduced model complexity, image preprocessing, data augmentation, and examination of the intermediate layers of the convolutional neural networks. The results presented in this paper constitute an important milestone in automating the manufacture of atom-based qubits for computation and sensing applications.
Abstract Atomic-level qubits in silicon are attractive candidates for large-scale quantum computing; however, their quantum properties and controllability are sensitive to details such as the number of donor atoms comprising a qubit and their precise location. This work combines machine learning techniques with million-atom simulations of scanning tunnelling microscopic (STM) images of dopants to formulate a theoretical framework capable of determining the number of dopants at a particular qubit location and their positions with exact lattice site precision. A convolutional neural network (CNN) was trained on 100,000 simulated STM images, acquiring a characterisation fidelity (number and absolute donor positions) of >98% over a set of 17,600 test images including planar and blurring noise commensurate with experimental measurements. The formalism is based on a systematic symmetry analysis and feature-detection processing of the STM images to optimise the computational efficiency. The technique is demonstrated for qubits formed by single and pairs of closely spaced donor atoms, with the potential to generalise it for larger donor clusters. The method established here will enable a high-precision post-fabrication characterisation of dopant qubits in silicon, with high-throughput potentially alleviating the requirements on the level of resources required for quantum-based characterisation, which will otherwise be a challenge in the context of large qubit arrays for universal quantum computing.
Donor spin qubits in silicon offer one- and two-qubit gates with fidelities beyond 99%, coherence times exceeding 30 seconds, and compatibility with industrial manufacturing methods. This motivates the development of large-scale quantum processors using this platform, and the ability to automatically tune and operate such complex devices. In this work, we present the first machine learning algorithm with the ability to automatically locate the charge transitions of an ion-implanted donor in a silicon device, tune single-shot charge readout, and identify the gate voltage parameters where tunnelling rates in and out the donor site are the same. The entire tuning pipeline is completed on the order of minutes. Our results enable both automatic characterisation and tuning of a donor in silicon devices faster than human experts.
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.
A primary obstacle in scaling up quantum computing platforms based on semiconductor quantum dots (QDs) is the full automation of initialization and control. Using ideas from machine learning (ML), pattern recognition, and optimization, the authors implement an autotuning protocol that needs no human intervention to navigate between QD states in real time. A convolutional neural network identifies QD states from $i\phantom{\rule{0}{0ex}}n$ $s\phantom{\rule{0}{0ex}}i\phantom{\rule{0}{0ex}}t\phantom{\rule{0}{0ex}}u$ measurements; importantly, the network is trained exclusively on simulated data, and the scans used are significantly smaller that in manual tuning, and hence much faster. This development is critical to moving up to larger numbers of quantum dots.
Scalable silicon quantum computers will require a material perfection that has never been attempted. Ground state wavefunctions for conduction electrons orbiting individual phosphorous donors must be polarized electronically and coupled to nearest neighbors with great precision. Elimination of all randomizing influences can be achieved only with a fully epitaxial structure; and we believe that output circuitry must also be integrated into the qubit arrays in order to achieve the uniformity needed for large-scale integration. A process that could potentially accomplish this will be outlined, based on scanning tunneling microscope (STM) removal of individual hydrogen atoms from the H-terminated silicon surface followed by phosphine dosing and ultra-low-temperature overgrowth. Self-ordering of PH3 molecules onto extended areas of bare silicon should permit patterning of planar single-electron transistors along with P-donor qubits in the same lithographic step. Initial plans for an experiment to characterize exchange coupling under gate control will be described.
We present a donor-based quadruple-quantum-dot device, designed to host two singlet–triplet qubits fabricated by scanning tunnelling microscope lithography, with just two leads per qubit. The design is geometrically compact, with each pair of dots independently controlled via one gate and one reservoir. The reservoirs both supply electrons for the dots and measure the singlet–triplet state of each qubit via dispersive sensing. We verify the locations of the four phosphorus donor dots via an electrostatic model of the device. We study one of the observed singlet–triplet states with a tunnel coupling of 39 GHz and a S 0 -to- T – decay of 2 ms at zero detuning. We measure a 5 GHz electrostatic interaction between two pairs of dots separated by 65 nm. The results outline a low-gate-density pathway to a scalable 1D building block of atomic-precision singlet–triplet qubits using donors with dispersive readout.