[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-127261-en":3,"doc-seo-127261-105":31,"detail-sidebar-cat-0-en-105":92},{"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":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":28,"seo_description":14,"update_tm":29,"read_time":30},127261,2336475104362,"Eden","https://ap-avatar.wpscdn.com/avatar/22000c4c46a41b752dd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1786595829695023868",8,"Research & Report","Convolutional Machine Learning Method for Accelerating Non-Equilibrium Green’s Function Simulations in Nanosheet Transistor - Abstract and Research Summary","A novel simulation approach combines machine learning with device modelling simulations based on the quantum mechanical non-equilibrium Green’s function (NEGF) framework. The ML component extends a convolutional generative network and is implemented in the in-house NESS simulator as ML-NEGF. Results show substantially improved convergence speed versus standard NEGF, with the trained model learning nanosheet transistor physics and accelerating coupled Poisson–NEGF self-consistency. Quantitatively, ML-NEGF delivers an average 60% convergence speedup while preserving accuracy, reducing computational time for quantum transport simulations.","Aleksandrov, P., Rezaei, A., Dutta, T., Xeni, N., Asenov, A. and Georgiev, V. (2023) Convolutional machine learning method for accelerating nonequilibrium Green’s function simulations in nanosheet transistor. IEEE Transactions on Electron Devices, 70(10)5448-5453 (doi: 10.1109/ TED.2023.3306319) .  \nAvailable under Creative Commons licence: [https://creativecommons.org/](https://creativecommons.org/)[ ](https://creativecommons.org/)[licenses/by/4.0/](licenses/by/4.0/)  \nThere may be differences between this version and the published version. You are advised to consult the published version if you wish to cite from it.  \n[http://eprints.gla.ac.uk/304810/](http://eprints.gla.ac.uk/304810/)  \n[Deposited on: 16 August 2023](Deposited on: 16 August 2023)  \nEnlighten – Research publications by members of the University of Glasgow  \n[http://eprints.gla.ac.uk](http://eprints.gla.ac.uk)  \nConvolutional Machine Learning Method for Accelerating Non-Equilibrium Green’s Function Simulations in Nanosheet Transistor  \nPreslav Aleksandrov, Ali Rezaei, Tapas Dutta, Nikolas Xeni, Asen Asenov, Fellow, IEEE, and Vihar Georgiev,  \nSenior Member, IEEE  \nAbstract—This work describes a novel simulation approach that combines machine learning and device modelling simulations. The device simulations are based on the quantum mechanical non-equilibrium Green’s function (NEGF) approach, and the machine learning (ML) method is an extension of a convolutional generative network. We have named our new simulation approach ML-NEGF. It is implemented in our in-house simulator called NESS (Nano-Electronics Simulation Software). The reported results demonstrate the improved convergence speed of the ML-NEGF method in comparison to the ‘standard’NEGF approach. The trained ML model effectively learns the underlying physics of nano-sheet transistor behaviour, resulting in faster convergence of the coupled Poisson-NEGF self-consistency simulations. Quantitatively, our ML-NEGF approach achieves an average convergence speedup of 60%, substantially reducing the computational time while maintaining the same accuracy.  \nIndex Terms—Non-Equilibrium Green’s Function (NEGF), nano-sheet transistors, autoencoder, convergence acceleration, quantum transport, silicon nanowire  \nI. INTRODUCTION  \nThe silicon nanowire and nanosheet transistors have a wide spectrum of promising applications [1], such as current fieldeffect transistors [2] and photovoltaics [3] . Moreover, the state-of-the-art CMOS technologies are based on single or stacked configurations of nanosheet or nanowire architectures [4] . Despite the recent advances in fabrication technology, TCAD simulations remain the main method through which the design of these devices is performed. To achieve useful results in the ever-shrinking size domain, more complex simulation methods, such as the NEGF method, are being adopted by industry. However, major bottlenecks for the wide adoption of these more complex methods are the increase in simulation time and the difficulty of achieving convergence. Therefore, this paper aims to tackle these challenges by introducing a machine learning model that can predict device performance. The proposed method aims to decrease computation time and improve convergence without sacrificing the physical accuracy and device output characteristics.  \nThe main aim of this work is to investigate the possibility of significantly improving or even replacing numerical Tech  \nManuscript received July XX, 2023; accepted July XX, 2023 . Date of publication July XX, 2023; date of current version August XX, 2023 . The authors are with the Device Modelling Group at James Watt School of Engineering, University of Glasgow, Glasgow G12 8LT, U.K. (e-mail: [vihar.georgiev@glasgow.ac.uk](vihar.georgiev@glasgow.ac.uk)). Color versions of one or more of the figures in this letter are availableonline at [http://ieeexplore.ieee.org](http://ieeexplore.ieee.org).  \nDigital Object Identifier 10.1109/XXXXXXXXXX  \nnology Com","cbCaitCYbELsSGaI","https://ap.wps.com/l/cbCaitCYbELsSGaI","pdf",1160094,2,1,7,"English","en",105,"# Introduction\n## Device simulation background and bottlenecks\n## Proposed ML-NEGF approach\n# Device Structure\n## N-type silicon nanosheet transistor geometry\n## Simulation flow overview","[{\"question\":\"What is the ML-NEGF simulation approach introduced in the work?\",\"answer\":\"ML-NEGF integrates a convolutional generative machine learning model with NEGF-based quantum device simulations, implemented within the NESS simulator for nanosheet transistors.\"},{\"question\":\"How does ML-NEGF improve simulation convergence compared with standard NEGF?\",\"answer\":\"The trained ML model learns the underlying physics, accelerating coupled Poisson–NEGF self-consistency iterations and improving convergence speed substantially over the standard NEGF approach.\"},{\"question\":\"What performance gains and accuracy impact are reported?\",\"answer\":\"The method achieves an average convergence speedup of 60% while maintaining the same accuracy as the standard approach, substantially reducing computational time.\"}]","Convolutional Machine Learning Method for Accelerating Non-Equilibrium Green’s Function Simulations in Nanosheet Transistor - Abstract and Research Summary | PDF",1785937808,18,{"code":4,"msg":32,"data":33},"ok",{"site_id":25,"language":24,"slug":34,"title":13,"keywords":35,"description":14,"schema_data":36,"social_meta":87,"head_meta":89,"extra_data":91,"updated_unix":29},"convolutional-machine-learning-method-for-accelerating-non-equilibrium-greens-function-simulations-in-nanosheet-transistor-abstract-and-research-summary","",{"@graph":37,"@context":86},[38,54,69],{"@type":39,"itemListElement":40},"BreadcrumbList",[41,45,48,51],{"item":42,"name":43,"@type":44,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":46,"name":47,"@type":44,"position":20},"https://docshare.wps.com/document/","Document",{"item":49,"name":12,"@type":44,"position":50},"https://docshare.wps.com/document/research-report/",3,{"item":52,"name":13,"@type":44,"position":53},"https://docshare.wps.com/document/convolutional-machine-learning-method-for-accelerating-non-equilibrium-greens-function-simulations-in-nanosheet-transistor-abstract-and-research-summary/127261/",4,{"url":52,"name":13,"@type":55,"author":56,"headline":13,"publisher":58,"fileFormat":61,"inLanguage":24,"description":14,"dateModified":62,"datePublished":63,"encodingFormat":61,"isAccessibleForFree":64,"interactionStatistic":65},"DigitalDocument",{"name":9,"@type":57},"Person",{"url":42,"name":59,"@type":60},"DocShare","Organization","application/pdf","2026-08-22","2026-08-05",true,{"@type":66,"interactionType":67,"userInteractionCount":20},"InteractionCounter",{"@type":68},"ViewAction",{"@type":70,"mainEntity":71},"FAQPage",[72,78,82],{"name":73,"@type":74,"acceptedAnswer":75},"What is the ML-NEGF simulation approach introduced in the work?","Question",{"text":76,"@type":77},"ML-NEGF integrates a convolutional generative machine learning model with NEGF-based quantum device simulations, implemented within the NESS simulator for nanosheet transistors.","Answer",{"name":79,"@type":74,"acceptedAnswer":80},"How does ML-NEGF improve simulation convergence compared with standard NEGF?",{"text":81,"@type":77},"The trained ML model learns the underlying physics, accelerating coupled Poisson–NEGF self-consistency iterations and improving convergence speed substantially over the standard NEGF approach.",{"name":83,"@type":74,"acceptedAnswer":84},"What performance gains and accuracy impact are reported?",{"text":85,"@type":77},"The method achieves an average convergence speedup of 60% while maintaining the same accuracy as the standard approach, substantially reducing computational time.","https://schema.org",{"og:url":52,"og:type":88,"og:title":13,"og:site_name":59,"og:description":14},"article",{"robots":90,"canonical":52},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":93},[94,98,102,106,111,116,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":47,"category_name":95,"show_sort_weight":96,"slug":97},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":47,"category_name":99,"show_sort_weight":100,"slug":101},"Literature",80,"literature",{"id":53,"doc_module":4,"doc_module_name":47,"category_name":103,"show_sort_weight":104,"slug":105},"Exam",70,"exam",{"id":107,"doc_module":4,"doc_module_name":47,"category_name":108,"show_sort_weight":109,"slug":110},5,"Comic",60,"comic",{"id":112,"doc_module":4,"doc_module_name":47,"category_name":113,"show_sort_weight":114,"slug":115},6,"Technology",50,"technology",{"id":22,"doc_module":4,"doc_module_name":47,"category_name":117,"show_sort_weight":118,"slug":119},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":47,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":47,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":47,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":47,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":47,"category_name":137,"show_sort_weight":107,"slug":138},19,"General","general"]