[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127460-en":3,"doc-seo-127460-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":27,"seo_description":14,"update_tm":28,"read_time":29},127460,962084925290,"Ophelia","https://ap-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Automatic tuning of a donor in a silicon quantum device using machine learning","Donor spin qubits in silicon enable high-fidelity one- and two-qubit gates, long coherence times, and compatibility with industrial CMOS fabrication, motivating large-scale quantum processors that can be tuned and operated automatically. This work presents a first machine-learning algorithm that locates ion-implanted donor charge transitions, tunes single-shot charge readout, and finds gate-voltage settings where tunneling rates into and out of the donor site match within the readout bandwidth. The full tuning pipeline completes in minutes, enabling faster characterization than human experts.","arXiv :2511 .04543v1 [ cond-mat .mes-hall ] 6 Nov 2025  \nAutomatic tuning of a donor in a silicon quantum device using machine learning  \nBrandon Severin, 1, 2, 3 Tim Botzem,2, 4 Federico Fedele,5 Xi Yu,2, 3 Benjamin Wilhelm,2, 3 Holly G. Stemp,2, 3 Irene Fernández de Fuentes,2, 3 Daniel Schwienbacher,2 Danielle Holmes,2, 3 Fay E. Hudson,2, 4 Andrew S. Dzurak,2, 4 Alexander M. Jakob,3, 6 David N. Jamieson,3, 6 Andrea Morello,2, 3 and Natalia Ares5  \n1 Department of Materials, University of Oxford,  \nParks Road, Oxford, OX1 3PH, United Kingdom  \n2 School of Electrical Engineering and Telecommunications,  \nUniversity of New South Wales, Sydney, NSW 2052, Australia  \n3 ARC Centre of Excellence for Quantum Computation and Communication Technology  \n4 Diraq, Sydney, NSW, Australia  \n5 Department of Engineering Science, University of Oxford,  \nParks Road, Oxford OX1 3PJ, United Kingdom  \n6 School of Physics, The University of Melbourne, Parkville, VIC 3010, Australia  \n(Dated: November 7, 2025)  \nDonor 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.  \nINTRODUCTION  \nThe promised treasures held within silicon ionimplanted donor spin qubits have led to their repeated pursuit as a contending scalable, CMOS-compatible quantum computing architecture ever since their proposition in 1998 [1] . Exploiting silicon’s central role in the electronics industry and its mature fabrication techniques, placing a 31 P ion in natural [2–4] and isotopically enriched 28 Si material [5], has enabled milestones such as single shot electron spin readout [6], 30-second coherence times [7] and error correction threshold fidelities [8] . However, the realisation of quantum computers built upon ion-implanted donors in silicon [3, 4] is not only‘dependent on future refinements of conventional silicon electronics’ [1], but also the development of automatic approaches to tune, optimise and control such devices in CMOS compatible architectures [9, 10] .  \nIn this work, we take the first step to address this challenging task by introducing donorsearch, an algorithm that automatically tunes an ion-implanted donor device from a de-energised device to a regime poised for spin-selective readout. To achieve this, our algorithm automatically sets up a single-electron transistor (SET) for charge sensing readout, locates the donor’s charge transitions, tunes single-shot charge readout, and optimises the rates at which electrons tunnel on and off the donor site to be nearly equal to each other within the readout bandwidth. This establishes a reference operating regime for spin qubit operation.  \nUntil now, automatic methods have only catered to tuning gate-defined quantum dot devices [11–21] . Our algorithm utilises computer vision and embedded unsupervised machine learning-enabled methods to process and classify quantum transport signals synonymous with donors in silicon devices.  \nUnlike in gate-defined quantum dots, where gate voltages gradually modify the confinement potential and lead to smooth, gradual changes in the transport features observed in charge stability diagrams, tuning an ionimplanted donor device is a true needle-in-a-haystack problem. The extensive gate voltage space has to be searched to ","cbCaioWUssjYZhrW","https://ap.wps.com/l/cbCaioWUssjYZhrW","pdf",2464522,1,12,"English","en",105,"# Introduction\n## Donor spin qubits and the need for automatic tuning\n## Introducing donorsearch and its objectives\n## Why donor tuning is a needle-in-a-haystack problem\n## Algorithm stages: coarse tuning, handshake, and fine tuning","[{\"question\":\"What does the proposed machine-learning algorithm automatically tune in the silicon donor device?\",\"answer\":\"It automatically locates the donor charge transitions, tunes single-shot charge readout, and optimizes gate-voltage parameters so tunneling rates into and out of the donor site are nearly equal within the readout bandwidth.\"},{\"question\":\"How does donorsearch differ from previous automatic tuning methods?\",\"answer\":\"Prior automatic methods mainly tuned gate-defined quantum dot devices, while donorsearch uses computer vision and embedded unsupervised machine-learning methods to process transport signals associated with implanted donors in silicon.\"},{\"question\":\"How long does the complete tuning process take?\",\"answer\":\"The entire tuning pipeline is completed on the order of minutes, with reported tuning times as short as about 10 minutes.\"}]","Automatic tuning of a donor in a silicon quantum device using machine learning | PDF",1785939022,30,{"code":4,"msg":31,"data":32},"ok",{"site_id":24,"language":23,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"automatic-tuning-of-a-donor-in-a-silicon-quantum-device-using-machine-learning","",{"@graph":36,"@context":85},[37,54,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,48,51],{"item":41,"name":42,"@type":43,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":47},"https://docshare.wps.com/document/","Document",2,{"item":49,"name":12,"@type":43,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":43,"position":53},"https://docshare.wps.com/document/automatic-tuning-of-a-donor-in-a-silicon-quantum-device-using-machine-learning/127460/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":23,"description":14,"dateModified":62,"datePublished":62,"encodingFormat":61,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":41,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-05",true,{"@type":65,"interactionType":66,"userInteractionCount":4},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the proposed machine-learning algorithm automatically tune in the silicon donor device?","Question",{"text":75,"@type":76},"It automatically locates the donor charge transitions, tunes single-shot charge readout, and optimizes gate-voltage parameters so tunneling rates into and out of the donor site are nearly equal within the readout bandwidth.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How does donorsearch differ from previous automatic tuning methods?",{"text":80,"@type":76},"Prior automatic methods mainly tuned gate-defined quantum dot devices, while donorsearch uses computer vision and embedded unsupervised machine-learning methods to process transport signals associated with implanted donors in silicon.",{"name":82,"@type":73,"acceptedAnswer":83},"How long does the complete tuning process take?",{"text":84,"@type":76},"The entire tuning pipeline is completed on the order of minutes, with reported tuning times as short as about 10 minutes.","https://schema.org",{"og:url":52,"og:type":87,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":89,"canonical":52},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,122,127,130,134],{"id":20,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":47,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":29,"slug":121},"research-report",{"id":123,"doc_module":4,"doc_module_name":46,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":46,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":46,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":46,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]