{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T01:49:59Z","timestamp":1769046599038,"version":"3.49.0"},"reference-count":48,"publisher":"IOP Publishing","issue":"3","license":[{"start":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T00:00:00Z","timestamp":1623628800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,6,14]],"date-time":"2021-06-14T00:00:00Z","timestamp":1623628800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,9,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Electron-neutral scattering cross sections are fundamental quantities in simulations of low temperature plasmas used for many technological applications today. From these microscopic cross sections, several macro-scale quantities (called \u2018swarm\u2019 parameters) can be calculated. However, measurements as well as theoretical calculations of cross sections are challenging. Since the 1960s, researchers have attempted to solve the inverse swarm problem of obtaining cross sections from swarm data; but the solutions are not necessarily unique. To address these issues, we examine the use of deep learning models which are trained using the previous determinations of elastic momentum transfer, ionization and excitation cross sections for different gases available on the LXCat website and their corresponding swarm parameters calculated using the BOLSIG+ solver for the numerical solution of the Boltzmann equation for electrons in weakly ionized gases. We implement artificial neural network (ANN), convolutional neural network (CNN) and densely connected convolutional network (DenseNet) for this investigation. To the best of our knowledge, there is no study exploring the use of CNN and DenseNet for the inverse swarm problem. We test the validity of predictions by all these trained networks for a broad range of gas species and we deduce that DenseNet effectively extracts both long and short term features from the swarm data and hence, it predicts cross sections with significantly higher accuracy compared to ANN. Further, we apply Monte Carlo dropout as Bayesian approximation to estimate the probability distribution of the cross sections to determine all plausible solutions of this inverse problem.<\/jats:p>","DOI":"10.1088\/2632-2153\/abf15a","type":"journal-article","created":{"date-parts":[[2021,3,24]],"date-time":"2021-03-24T22:15:35Z","timestamp":1616624135000},"page":"035025","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["Extracting electron scattering cross sections from swarm data using deep neural networks"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3440-0996","authenticated-orcid":false,"given":"Vishrut","family":"Jetly","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7618-3737","authenticated-orcid":false,"given":"Bhaskar","family":"Chaudhury","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2021,6,14]]},"reference":[{"key":"mlstabf15abib1","doi-asserted-by":"publisher","DOI":"10.1088\/0022-3727\/45\/25\/253001","article-title":"The 2012 plasma roadmap","volume":"45","author":"Samukawa","year":"2012","journal-title":"J. Phys. D: Appl. Phys."},{"key":"mlstabf15abib2","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6463\/aa76f5","article-title":"The 2017 plasma roadmap: low temperature plasma science and technology","volume":"50","author":"Adamovich","year":"2017","journal-title":"J. Phys. D: Appl. Phys."},{"key":"mlstabf15abib3","author":"Shohet","year":"2016"},{"key":"mlstabf15abib4","author":"Laroussi","year":"2012"},{"key":"mlstabf15abib5","doi-asserted-by":"publisher","DOI":"10.1002\/ppap.201877002","article-title":"Special issue: plasma and agriculture","volume":"15","author":"Gherardi","year":"2018","journal-title":"Plasma Process. Polym."},{"key":"mlstabf15abib6","doi-asserted-by":"publisher","first-page":"09","DOI":"10.1088\/1361-6595\/aa8d4c","article-title":"Foundations of low-temperature plasma physics\u2014an introduction","volume":"26","author":"Keudell","year":"2017","journal-title":"Plasma Sources Sci. Technol."},{"key":"mlstabf15abib7","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1088\/0022-3727\/38\/19\/R01","article-title":"Topical review: particle and fluid simulations of low-temperature plasma discharges: benchmarks and kinetic effects","volume":"38","author":"Kim","year":"2005","journal-title":"J. Phys. D: Appl. Phys."},{"key":"mlstabf15abib8","doi-asserted-by":"publisher","first-page":"02","DOI":"10.1088\/1361-6595\/aaa86d","article-title":"Foundations of modelling of nonequilibrium low-temperature plasmas","volume":"27","author":"Alves","year":"2018","journal-title":"Plasma Sources Sci. Technol."},{"key":"mlstabf15abib9","doi-asserted-by":"publisher","DOI":"10.1088\/0022-3727\/46\/33\/330301","article-title":"GEC plasma data exchange project","volume":"46","author":"Pitchford","year":"2013","journal-title":"J. Phys. D: Appl. Phys."},{"key":"mlstabf15abib10","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1073\/pnas.1606132113","article-title":"Electron collisions with atoms, ions, molecules and surfaces: fundamental science empowering advances in technology","volume":"113","author":"Bartschat","year":"2016","journal-title":"Proc. Natl Acad. Sci."},{"key":"mlstabf15abib11","doi-asserted-by":"publisher","first-page":"2009","DOI":"10.1063\/1.1382833","article-title":"Electron cross section set for CHF3","volume":"90","author":"Morgan","year":"2001","journal-title":"J. Appl. Phys."},{"key":"mlstabf15abib12","doi-asserted-by":"publisher","first-page":"1621","DOI":"10.1103\/PhysRev.127.1621","article-title":"Rotational excitation and momentum transfer cross sections for electrons in H2 and N2 from transport coefficients","volume":"127","author":"Frost","year":"1962","journal-title":"Phys. Rev."},{"key":"mlstabf15abib13","doi-asserted-by":"publisher","first-page":"2115","DOI":"10.1103\/PhysRev.131.2115","article-title":"Elastic and inelastic collision cross sections in hydrogen and deuterium from transport coefficients","volume":"131","author":"Engelhardt","year":"1963","journal-title":"Phys. Rev."},{"key":"mlstabf15abib14","doi-asserted-by":"publisher","first-page":"A1566","DOI":"10.1103\/PhysRev.135.A1566","article-title":"Determination of momentum transfer and inelastic collision cross sections for electrons in nitrogen using transport coefficients","volume":"135","author":"Engelhardt","year":"1964","journal-title":"Phys. Rev."},{"key":"mlstabf15abib15","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1103\/PhysRev.158.70","article-title":"Momentum-transfer and inelastic-collision cross sections for electrons in O2, CO, and CO2","volume":"158","author":"Hake Jr","year":"1967","journal-title":"Phys. Rev."},{"key":"mlstabf15abib16","doi-asserted-by":"publisher","first-page":"842","DOI":"10.1088\/0022-3727\/23\/7\/013","article-title":"Momentum transfer cross section of argon deduced from electron drift velocity data","volume":"23","author":"Suzuki","year":"1990","journal-title":"J. Phys. D: Appl. Phys."},{"key":"mlstabf15abib17","doi-asserted-by":"publisher","first-page":"1677","DOI":"10.1103\/PhysRevA.44.1677","article-title":"Use of numerical optimization algorithms to obtain cross sections from electron swarm data","volume":"44","author":"Morgan","year":"1991","journal-title":"Phys. Rev. A"},{"key":"mlstabf15abib18","doi-asserted-by":"publisher","first-page":"250","DOI":"10.1109\/27.106821","article-title":"The feasibility of using neural networks to obtain cross sections from electron swarm data","volume":"19","author":"Morgan","year":"1991","journal-title":"IEEE Trans. Plasma Sci."},{"key":"mlstabf15abib19","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1140\/epjd\/e2013-40111-9","article-title":"Applications of artificial neural networks to proton-impact ionization double differential cross sections","volume":"67","author":"Harris","year":"2013","journal-title":"Eur. Phys. J. D"},{"key":"mlstabf15abib20","doi-asserted-by":"publisher","DOI":"10.1002\/ppap.201600098","article-title":"LXCat: an open-access, web-based platform for data needed for modeling low temperature plasmas","volume":"14","author":"Pitchford","year":"2017","journal-title":"Plasma Process. Polym."},{"key":"mlstabf15abib21","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6595\/ab85b6","article-title":"Determining cross sections from transport coefficients using deep neural networks","volume":"29","author":"Stokes","year":"2020","journal-title":"Plasma Sources Sci. Technol."},{"key":"mlstabf15abib22","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6595\/abb4f6","article-title":"Self-consistent electron\u2013THF cross sections derived using data-driven swarm analysis with a neural network model","volume":"29","author":"Stokes","year":"2020","journal-title":"Plasma Sources Sci. Technol."},{"key":"mlstabf15abib23","author":""},{"key":"mlstabf15abib24","first-page":"pp 1050","article-title":"Dropout as a Bayesian approximation: representing model uncertainty in deep learning","author":"Gal","year":"2016"},{"key":"mlstabf15abib25","article-title":"Biagi database"},{"key":"mlstabf15abib26","article-title":"Bordage database"},{"key":"mlstabf15abib27","article-title":"BSR database"},{"key":"mlstabf15abib28","article-title":"CCC database"},{"key":"mlstabf15abib29","article-title":"Hayashi database"},{"key":"mlstabf15abib30","article-title":"IST-Lisbon database"},{"key":"mlstabf15abib31","article-title":"Puech database"},{"key":"mlstabf15abib32","article-title":"SIGLO database"},{"key":"mlstabf15abib33","article-title":"TRINITY database"},{"key":"mlstabf15abib34","doi-asserted-by":"crossref","first-page":"R5","DOI":"10.1103\/PhysRevA.55.R5","article-title":"Analytical parametrization for the shape of atomic ionization cross sections","volume":"55","author":"Rost","year":"1997","journal-title":"Phys. Rev. A"},{"key":"mlstabf15abib35","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1088\/0963-0252\/14\/4\/011","article-title":"Solving the Boltzmann equation to obtain electron transport coefficients and rate coefficients for fluid models","volume":"14","author":"Hagelaar","year":"2005","journal-title":"Plasma Sources Sci. Technol."},{"key":"mlstabf15abib36","first-page":"1995","article-title":"Convolutional networks for images, speech and time series","volume":"vol 3361","author":"LeCun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"mlstabf15abib37","first-page":"pp 4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"mlstabf15abib38","article-title":"Adam: a method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"mlstabf15abib39","article-title":"Keras","author":"Chollet","year":"2015"},{"key":"mlstabf15abib40","article-title":"TensorFlow: large-scale machine learning on heterogeneous systems","author":"Abadi","year":"2015"},{"key":"mlstabf15abib41","article-title":"Itikawa database"},{"key":"mlstabf15abib42","article-title":"Biagi-v7.1 database"},{"key":"mlstabf15abib43","article-title":"Morgan database"},{"key":"mlstabf15abib44","article-title":"QUANTEMOL database"},{"key":"mlstabf15abib45","article-title":"Christophorou database"},{"key":"mlstabf15abib46","article-title":"Phelps database"},{"key":"mlstabf15abib47","article-title":"FLINDERS database"},{"key":"mlstabf15abib48","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1162\/neco.1992.4.3.448","article-title":"A practical Bayesian framework for backpropagation networks","volume":"4","author":"MacKay","year":"1992","journal-title":"Neural Comput."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf15a","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf15a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf15a","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf15a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf15a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf15a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf15a\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf15a\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,12]],"date-time":"2021-12-12T17:48:21Z","timestamp":1639331301000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abf15a"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,14]]},"references-count":48,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,6,14]]},"published-print":{"date-parts":[[2021,9,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abf15a","relation":{},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,14]]},"assertion":[{"value":"Extracting electron scattering cross sections from swarm data using deep neural networks","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 2021 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-10-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-03-24","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2021-06-14","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}