[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"detail-sidebar-cat-0-en-105":3,"doc-seo-327463-105":59,"doc-detail-327463-en":130},{"code":4,"msg":5,"data":6},0,"success",[7,13,18,23,28,33,38,43,48,51,55],{"id":8,"doc_module":4,"doc_module_name":9,"category_name":10,"show_sort_weight":11,"slug":12},1,"Document","Story & Novel",90,"story-novel",{"id":14,"doc_module":4,"doc_module_name":9,"category_name":15,"show_sort_weight":16,"slug":17},2,"Literature",80,"literature",{"id":19,"doc_module":4,"doc_module_name":9,"category_name":20,"show_sort_weight":21,"slug":22},4,"Exam",70,"exam",{"id":24,"doc_module":4,"doc_module_name":9,"category_name":25,"show_sort_weight":26,"slug":27},5,"Comic",60,"comic",{"id":29,"doc_module":4,"doc_module_name":9,"category_name":30,"show_sort_weight":31,"slug":32},6,"Technology",50,"technology",{"id":34,"doc_module":4,"doc_module_name":9,"category_name":35,"show_sort_weight":36,"slug":37},7,"Healthcare",40,"healthcare",{"id":39,"doc_module":4,"doc_module_name":9,"category_name":40,"show_sort_weight":41,"slug":42},8,"Research & Report",30,"research-report",{"id":44,"doc_module":4,"doc_module_name":9,"category_name":45,"show_sort_weight":46,"slug":47},9,"Religion & Spirituality",20,"religion-spirituality",{"id":46,"doc_module":4,"doc_module_name":9,"category_name":49,"show_sort_weight":46,"slug":50},"World Cup","world-cup",{"id":52,"doc_module":4,"doc_module_name":9,"category_name":53,"show_sort_weight":52,"slug":54},10,"Lifestyle","lifestyle",{"id":56,"doc_module":4,"doc_module_name":9,"category_name":57,"show_sort_weight":24,"slug":58},19,"General","general",{"code":4,"msg":60,"data":61},"ok",{"site_id":62,"language":63,"slug":64,"title":65,"keywords":66,"description":67,"schema_data":68,"social_meta":123,"head_meta":125,"extra_data":127,"updated_unix":129},105,"en","neural-network-inverse-design-of-srf-cavities-and-transmons-for-bosonic-quantum-computation-arxiv260702289v2","Neural-Network Inverse Design of SRF Cavities and Transmons for Bosonic Quantum Computation - arXiv:2607.02289v2","","Three-dimensional superconducting radio-frequency cavities coupled with nonlinear transmon qubits form promising platforms for bosonic quantum information processing, but inverse design is inherently one-to-many. The qubit–cavity coupling depends sensitively on transmon geometry and position within the cavity field, making conventional iterative simulation costly at scale. Two complementary deep neural network methods directly recover SRF cavity geometries and transmon designs matching targets, validated by end-to-end re-simulation within about 5% (cavity) and 2% (transmon).",{"@graph":69,"@context":122},[70,84,105],{"@type":71,"itemListElement":72},"BreadcrumbList",[73,77,79,82],{"item":74,"name":75,"@type":76,"position":8},"https://docshare.wps.com","Home","ListItem",{"item":78,"name":9,"@type":76,"position":14},"https://docshare.wps.com/document/",{"item":80,"name":40,"@type":76,"position":81},"https://docshare.wps.com/document/research-report/",3,{"item":83,"name":65,"@type":76,"position":19},"https://docshare.wps.com/document/neural-network-inverse-design-of-srf-cavities-and-transmons-for-bosonic-quantum-computation-arxiv260702289v2/327463/",{"url":83,"name":65,"@type":85,"image":86,"author":91,"headline":65,"publisher":94,"fileFormat":97,"inLanguage":63,"description":67,"dateModified":98,"datePublished":99,"encodingFormat":97,"isAccessibleForFree":100,"interactionStatistic":101},"DigitalDocument",{"url":87,"@type":88,"width":89,"height":90},"https://docshare.wps.com/thumbnails/neural-network-inverse-design-of-srf-cavities-and-transmons-for-bosonic-quantum-computation-arxiv260702289v2/327463.png","ImageObject",300,407,{"name":92,"@type":93},"Ivy","Person",{"url":74,"name":95,"@type":96},"DocShare","Organization","application/pdf","2026-10-26","2026-09-21",true,{"@type":102,"interactionType":103,"userInteractionCount":34},"InteractionCounter",{"@type":104},"ViewAction",{"@type":106,"mainEntity":107},"FAQPage",[108,114,118],{"name":109,"@type":110,"acceptedAnswer":111},"Why is inverse design for SRF cavity–transmon systems difficult?","Question",{"text":112,"@type":113},"Because the mapping from device geometry to electromagnetic and coupling targets is generally one-to-many, so repeated simulation becomes expensive as design spaces grow.","Answer",{"name":115,"@type":110,"acceptedAnswer":116},"What do the two deep neural network approaches target?",{"text":117,"@type":113},"One recovers SRF cavity geometries to match target cavity observables, and the other recovers transmon qubit designs to match target qubit–cavity parameters such as coupling rate, qubit frequency, and anharmonicity.",{"name":119,"@type":110,"acceptedAnswer":120},"How accurate are the recovered designs according to the document?",{"text":121,"@type":113},"Recovered candidates match the targets within approximately 5% for cavity observables and about 2% for transmon parameters, confirmed by end-to-end re-simulation.","https://schema.org",{"og:url":83,"og:type":124,"og:title":65,"og:site_name":95,"og:description":67},"article",{"robots":126,"canonical":83},"index,follow",{"doc_id":128,"site_id":62},327463,1790342412,{"code":4,"msg":5,"data":131},{"doc_id":128,"user_id":132,"nickname":92,"user_avatar":133,"doc_module":4,"category_id":39,"category_name":40,"doc_title":65,"doc_description":67,"doc_content":134,"file_id":135,"file_url":136,"file_type":137,"file_size":138,"view_count":34,"is_deleted":4,"is_public":8,"is_downloadable":8,"audit_status":8,"page_count":139,"language":140,"language_code":63,"site_id":62,"html_lang":63,"table_of_contents":141,"faqs":142,"seo_title":143,"seo_description":67,"update_tm":144,"read_time":145,"preview_page_count":4},549758252649,"https://ap-avatar.wpscdn.com/avatar/8000253669c5317157?_k=1778319167496531819","Neural-Network Inverse Design of SRF Cavities and Transmons for Bosonic Quantum  \nComputation  \narXiv :2607 .02289v2 [ quant-ph] 7 Jul 2026  \nJoseph Yaker, 1, 2 Jovan Markovic, 1, 3 Alessandro Reineri, 1, 4 Doga Murat Kurkcuoglu, 1 and Silvia Zorzetti 1, 5, ∗  \n1 Superconducting and Quantum Materials System Center (SQMS),  \nFermi National Accelerator Laboratory, Batavia, 60510, IL, USA  \n2 Applied Physics Program, Northwestern University, Evanston, 60208, IL, USA  \n3 Department of Physics, University of Cambridge, Cambridge, CB3 0US, UK  \n4 Illinois Institute of Technology, 10 W 35th Street, Chicago, 60616, IL, USA  \n5 Department of Physics and Astronomy, Northwestern University, Evanston, 60208, IL, USA  \nThree-dimensional superconducting radio-frequency (SRF) cavities provide exceptionally longlived electromagnetic modes and, when coupled to nonlinear elements such as transmon qubits, become promising architectures for bosonic quantum information processing. The inverse design of such systems, i.e., recovering device geometries that produce specified electromagnetic and coupling targets, is generally a one-to-many problem. The qubit-cavity coupling strength depends sensitivelyon both the transmon geometry and its position within the cavity’s electromagnetic field. As these systems scale up and their design parameter spaces grow, the cost of conventional iterative simulation becomes prohibitive. We present two deep neural network (DNN) approaches that address this inverse-design problem at complementary levels of the design stack. The first proposes SRF cavity geometries that produce target cavity observables. The second proposes transmon qubit designs that produce target qubit–cavity parameters — the coupling rate, qubit frequency, and anharmonicity (g,νq ,α) . The recovered candidate designs match the targets to within ∼5%(cavity) and ∼2%(transmon), confirmed by end-to-end re-simulation. Both approaches map desired device behavior directly to candidate designs, a fast alternative to the iterative simulation studies usually required.  \n1. INTRODUCTION  \nDesigning electromagnetic devices to meet target performance specifications is a recurring challenge across microwave engineering, photonics, and accelerator physics. The forward problem, i.e., predicting device performance from a given geometry, is routinely tackled with finiteelement software packages for electromagnetic and multiphysics simulations. The inverse problem is the recovery of a geometry that produces the desired response. This direction is harder because the mapping to viable solutions is generally one-to-many. Therefore, with traditional approaches, the cost of repeated simulation grows rapidly with the dimensionality of the design space. Machine learning offers a complementary route and has already been applied to a wide range of problems in the physical sciences [1, 2], including the rapid solution of complex electromagnetic inverse design problems [3, 4] . Here, we apply this approach to the design and optimization of superconducting devices for quantum computing and sensing.  \nSuperconducting radio frequency (SRF) cavities are highly efficient microwave resonators, historically developed to accelerate subatomic particles. They have also proven useful in quantum information science, acting as high-Q, low-loss resonators used to store and protect quantum states [5–7] . Coupled to nonlinear superconducting circuits, i.e., qubits [8], used to control and measure quantum information within, they can achieve very  \n∗ [zorzetti@fnal.gov](zorzetti@fnal.gov)  \nlong single-photon lifetimes in a range of 10–30 ms [9– 11] . These long-lived quantum memories are particularly relevant in the field of high energy physics for quantum simulations of field theories and related applications.  \nThe coupling between SRF cavities and superconducting qubits, most commonly transmons [8], is described by the formalism of three-dimensional circuit quantum electrodynamics (3D cQED) ","cbCaiaCnIW1BfbLq","https://ap.wps.com/l/cbCaiaCnIW1BfbLq","pdf",5583777,18,"English","# Introduction\n## Forward vs inverse problems\n## SRF cavities and transmon coupling\n## 3D cQED and bosonic state engineering\n## Motivation for fast geometry recovery","[{\"question\":\"Why is inverse design for SRF cavity–transmon systems difficult?\",\"answer\":\"Because the mapping from device geometry to electromagnetic and coupling targets is generally one-to-many, so repeated simulation becomes expensive as design spaces grow.\"},{\"question\":\"What do the two deep neural network approaches target?\",\"answer\":\"One recovers SRF cavity geometries to match target cavity observables, and the other recovers transmon qubit designs to match target qubit–cavity parameters such as coupling rate, qubit frequency, and anharmonicity.\"},{\"question\":\"How accurate are the recovered designs according to the document?\",\"answer\":\"Recovered candidates match the targets within approximately 5% for cavity observables and about 2% for transmon parameters, confirmed by end-to-end re-simulation.\"}]","Neural-Network Inverse Design of SRF Cavities and Transmons for Bosonic Quantum Computation - arXiv:2607.02289v2 | PDF",1789977252,45]