{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T17:48:02Z","timestamp":1768412882009,"version":"3.49.0"},"reference-count":75,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T00:00:00Z","timestamp":1715040000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T00:00:00Z","timestamp":1715040000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft","doi-asserted-by":"crossref","award":["Project-ID 434434223 \u2013 SFB 1461"],"award-info":[{"award-number":["Project-ID 434434223 \u2013 SFB 1461"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2024,6,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Poisson\u2019s equation plays an important role in modeling many physical systems. In electrostatic self-consistent low-temperature plasma (LTP) simulations, Poisson\u2019s equation is solved at each simulation time step, which can amount to a significant computational cost for the entire simulation. In this paper, we describe the development of a generic machine-learned Poisson solver specifically designed for the requirements of LTP simulations in complex 2D reactor geometries on structured Cartesian grids. Here, the reactor geometries can consist of inner electrodes and dielectric materials as often found in LTP simulations. The approach leverages a hybrid CNN-transformer network architecture in combination with a weighted multiterm loss function. We train the network using highly randomized synthetic data to ensure the generalizability of the learned solver to unseen reactor geometries. The results demonstrate that the learned solver is able to produce quantitatively and qualitatively accurate solutions. Furthermore, it generalizes well on new reactor geometries such as reference geometries found in the literature. To increase the numerical accuracy of the solutions required in LTP simulations, we employ a conventional iterative solver to refine the raw predictions, especially to recover the high-frequency features not resolved by the initial prediction. With this, the proposed learned Poisson solver provides the required accuracy and is potentially faster than a pure GPU-based conventional iterative solver. This opens up new possibilities for developing a generic and high-performing learned Poisson solver for LTP systems in complex geometries.<\/jats:p>","DOI":"10.1088\/2632-2153\/ad4230","type":"journal-article","created":{"date-parts":[[2024,4,23]],"date-time":"2024-04-23T22:44:50Z","timestamp":1713912290000},"page":"025031","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Towards a machine-learned Poisson solver for low-temperature plasma simulations in complex geometries"],"prefix":"10.1088","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4232-4543","authenticated-orcid":true,"given":"Ihda","family":"Chaerony Siffa","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9324-3236","authenticated-orcid":true,"given":"Markus M","family":"Becker","sequence":"additional","affiliation":[]},{"given":"Klaus-Dieter","family":"Weltmann","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9136-8019","authenticated-orcid":true,"given":"Jan","family":"Trieschmann","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2024,5,7]]},"reference":[{"key":"mlstad4230bib1","first-page":"pp 338","author":"Low","year":"1997"},{"key":"mlstad4230bib2","first-page":"pp 567","author":"Wesseling","year":"2009"},{"key":"mlstad4230bib3","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6595\/aaa86d","volume":"27","author":"Alves","year":"2018","journal-title":"Plasma Sources Sci. Technol."},{"key":"mlstad4230bib4","author":"Jackson","year":"1998","edition":"3rd edn"},{"key":"mlstad4230bib5","author":"Hackbusch","year":"1985"},{"key":"mlstad4230bib6","author":"Trottenberg","year":"2001"},{"key":"mlstad4230bib7","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2023.108665","volume":"286","author":"Teunissen","year":"2023","journal-title":"Comput. Phys. Commun."},{"key":"mlstad4230bib8","doi-asserted-by":"publisher","first-page":"460","DOI":"10.1016\/j.jcp.2013.02.019","volume":"242","author":"Martinsson","year":"2013","journal-title":"J. Comput. Phys."},{"key":"mlstad4230bib9","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2020.110087","volume":"436","author":"Fortunato","year":"2021","journal-title":"J. Comput. Phys."},{"key":"mlstad4230bib10","doi-asserted-by":"publisher","DOI":"10.1016\/j.jcp.2022.111378","volume":"465","author":"Semenov","year":"2022","journal-title":"J. Comput. Phys."},{"key":"mlstad4230bib11","first-page":"pp 1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"mlstad4230bib12","first-page":"pp 6000","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"mlstad4230bib13","first-page":"pp 873","article-title":"Large-scale deep unsupervised learning using graphics processors","author":"Raina","year":"2009"},{"key":"mlstad4230bib14","author":"Claudiu Ciresan","year":"2010"},{"key":"mlstad4230bib15","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/0021-9991(90)90007-N","volume":"91","author":"Lee","year":"1990","journal-title":"J. Comput. Phys."},{"key":"mlstad4230bib16","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1002\/cnm.1640100303","volume":"10","author":"Dissanayake","year":"1994","journal-title":"Commun. Numer. Methods Eng."},{"key":"mlstad4230bib17","doi-asserted-by":"publisher","first-page":"987","DOI":"10.1109\/72.712178","volume":"9","author":"Lagaris","year":"1998","journal-title":"IEEE Trans. Neural Netw."},{"key":"mlstad4230bib18","doi-asserted-by":"publisher","first-page":"686","DOI":"10.1016\/j.jcp.2018.10.045","volume":"378","author":"Raissi","year":"2019","journal-title":"J. Comput. Phys."},{"key":"mlstad4230bib19","doi-asserted-by":"publisher","first-page":"422","DOI":"10.1038\/s42254-021-00314-5","volume":"3","author":"Karniadakis","year":"1970","journal-title":"Nat. Rev. Phys."},{"key":"mlstad4230bib20","doi-asserted-by":"publisher","first-page":"208","DOI":"10.1137\/19M1274067","volume":"63","author":"Lu","year":"2021","journal-title":"SIAM Rev."},{"key":"mlstad4230bib21","author":"Lu","year":"2019"},{"key":"mlstad4230bib22","author":"Li","year":"2020"},{"key":"mlstad4230bib23","author":"Li","year":"2020"},{"key":"mlstad4230bib24","author":"Cao","year":"2021"},{"key":"mlstad4230bib25","doi-asserted-by":"publisher","first-page":"218","DOI":"10.1038\/s42256-021-00302-5","volume":"3","author":"Lu","year":"2021","journal-title":"Nat. Mach. Intell."},{"key":"mlstad4230bib26","author":"Shi","year":"2022"},{"key":"mlstad4230bib27","doi-asserted-by":"publisher","first-page":"eabi8605","DOI":"10.1126\/sciadv.abi8605","volume":"7","author":"Wang","year":"2021","journal-title":"Sci. Adv."},{"key":"mlstad4230bib28","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural Netw."},{"key":"mlstad4230bib29","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/0893-6080(91)90009-T","volume":"4","author":"Hornik","year":"1991","journal-title":"Neural Netw."},{"key":"mlstad4230bib30","doi-asserted-by":"publisher","first-page":"787","DOI":"10.1016\/j.acha.2019.06.004","volume":"48","author":"Zhou","year":"2020","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"mlstad4230bib31","author":"Hsieh","year":"2019"},{"key":"mlstad4230bib32","doi-asserted-by":"publisher","first-page":"e6","DOI":"10.1017\/dce.2021.7","volume":"2","author":"\u00d6zbay","year":"2021","journal-title":"Data-Centric Eng."},{"key":"mlstad4230bib33","first-page":"pp 305","article-title":"Solving Poisson\u2019s equation using deep learning in particle simulation of PN junction","author":"Zhang","year":"2019"},{"key":"mlstad4230bib34","author":"Cheng","year":"2021"},{"key":"mlstad4230bib35","first-page":"pp 234","article-title":"U-Net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"mlstad4230bib36","doi-asserted-by":"publisher","first-page":"04LT02","DOI":"10.1088\/1361-6595\/ac63df","volume":"31","author":"Jovanovi\u0107","year":"2022","journal-title":"Plasma Sources Sci. Technol."},{"key":"mlstad4230bib37","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6595\/aad2c5","volume":"27","author":"Engeling","year":"2018","journal-title":"Plasma Sources Sci. Technol."},{"key":"mlstad4230bib38","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6595\/abf598","volume":"30","author":"Zhang","year":"2021","journal-title":"Plasma Sources Sci. Technol."},{"key":"mlstad4230bib39","doi-asserted-by":"publisher","DOI":"10.1002\/ppap.202000243","volume":"18","author":"Baldry","year":"2021","journal-title":"Plasma Process Polym."},{"key":"mlstad4230bib40","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1016\/0305-0483(96)00010-2","volume":"24","author":"Shanker","year":"1996","journal-title":"Omega"},{"key":"mlstad4230bib41","first-page":"pp 9","author":"LeCun","year":"1998"},{"key":"mlstad4230bib42","article-title":"robbmcleod\/pyfastnoisesimd: Python module wrapping C++ FastNoiseSIMD at v0.4.2","author":"GitHub","year":"2021"},{"key":"mlstad4230bib43","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","volume":"585","author":"Harris","year":"2020","journal-title":"Nature"},{"key":"mlstad4230bib44","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"mlstad4230bib45","article-title":"numpy\/numpy at v1.24.0","author":"GitHub","year":"2022"},{"key":"mlstad4230bib46","article-title":"scipy\/scipy at v1.9.3","author":"GitHub","year":"2022"},{"key":"mlstad4230bib47","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Wang","year":"2004","journal-title":"IEEE Trans. Image Process."},{"key":"mlstad4230bib48","author":"Godard","year":"2016"},{"key":"mlstad4230bib49","author":"Godard","year":"2018"},{"key":"mlstad4230bib50","doi-asserted-by":"publisher","DOI":"10.1016\/j.advwatres.2022.104180","volume":"163","author":"Wen","year":"2022","journal-title":"Adv. Water Resour."},{"key":"mlstad4230bib51","author":"Dosovitskiy","year":"2020"},{"key":"mlstad4230bib52","author":"Yu","year":"2022"},{"key":"mlstad4230bib53","author":"Chen","year":"2022"},{"key":"mlstad4230bib54","author":"Chen","year":"2022"},{"key":"mlstad4230bib55","author":"Xie","year":"2022"},{"key":"mlstad4230bib56","author":"Chen","year":"2021"},{"key":"mlstad4230bib57","first-page":"pp 2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"mlstad4230bib58","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/BF00342633","volume":"20","author":"Fukushima","year":"1975","journal-title":"Biol. Cybern."},{"key":"mlstad4230bib59","first-page":"pp 807","article-title":"Rectified linear units improve restricted Boltzmann machines","author":"Nair","year":"2010"},{"key":"mlstad4230bib60","first-page":"pp 448","article-title":"Batch normalization: accelerating deep network training by reducing internal covariate shift","author":"Ioffe","year":"2015"},{"key":"mlstad4230bib61","author":"Kingma","year":"2014"},{"key":"mlstad4230bib62","author":"Loshchilov","year":"2016"},{"key":"mlstad4230bib63","first-page":"pp 265","article-title":"TensorFlow: a system for large-scale machine learning","author":"Abadi","year":"2016"},{"key":"mlstad4230bib64","article-title":"tensorflow\/tensorflow at v2.11.0","author":"GitHub","year":"2022"},{"key":"mlstad4230bib65","author":"Van Rossum","year":"2009"},{"key":"mlstad4230bib66","doi-asserted-by":"publisher","DOI":"10.3389\/fdata.2021.669097","volume":"4","author":"Markidis","year":"2021","journal-title":"Front. Big Data"},{"key":"mlstad4230bib67","author":"Rahaman","year":"2018"},{"key":"mlstad4230bib68","author":"Cao","year":"2019"},{"key":"mlstad4230bib69","first-page":"pp 264","author":"Xu","year":"2019"},{"key":"mlstad4230bib70","author":"Xu","year":"2019"},{"key":"mlstad4230bib71","doi-asserted-by":"publisher","first-page":"S602","DOI":"10.1137\/140980260","volume":"37","author":"Naumov","year":"2015","journal-title":"SIAM J. Sci. Comput."},{"key":"mlstad4230bib72","article-title":"NVIDIA\/AMGX: distributed multigrid linear solver library on GPU at v2.3.0","author":"GitHub","year":"2022"},{"key":"mlstad4230bib73","article-title":"shwina\/pyamgx: GPU accelerated multigrid library for Python","author":"GitHub","year":"2018"},{"key":"mlstad4230bib74","author":"Pfaff","year":"2020"},{"key":"mlstad4230bib75","author":"L\u00f6tzsch","year":"2022"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4230","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4230\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4230","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4230\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4230\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4230\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4230\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4230\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T08:51:10Z","timestamp":1715071870000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/ad4230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,7]]},"references-count":75,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2024,5,7]]},"published-print":{"date-parts":[[2024,6,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/ad4230","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5,7]]},"assertion":[{"value":"Towards a machine-learned Poisson solver for low-temperature plasma simulations in complex geometries","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2024 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2023-11-15","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-04-23","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2024-05-07","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}