{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T20:28:13Z","timestamp":1776457693931,"version":"3.51.2"},"reference-count":38,"publisher":"Cambridge University Press (CUP)","issue":"6","license":[{"start":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T00:00:00Z","timestamp":1670371200000},"content-version":"unspecified","delay-in-days":6,"URL":"https:\/\/www.cambridge.org\/core\/terms"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["PD\/00505\/2012"],"award-info":[{"award-number":["PD\/00505\/2012"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["PD\/BD\/114307\/2016"],"award-info":[{"award-number":["PD\/BD\/114307\/2016"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["PRT\/BD\/152270\/2021"],"award-info":[{"award-number":["PRT\/BD\/152270\/2021"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["UI\/BD\/151559\/2021"],"award-info":[{"award-number":["UI\/BD\/151559\/2021"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100010663","name":"H2020 European Research Council","doi-asserted-by":"publisher","award":["695088"],"award-info":[{"award-number":["695088"]}],"id":[{"id":"10.13039\/100010663","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["cambridge.org"],"crossmark-restriction":true},"short-container-title":["J. Plasma Phys."],"published-print":{"date-parts":[[2022,12]]},"abstract":"<jats:p>In this paper we propose a methodology for the efficient implementation of machine learning (ML)-based methods in particle-in-cell (PIC) codes, with a focus on Monte Carlo or statistical extensions to the PIC algorithm. The presented approach allows for neural networks to be developed in a Python environment, where advanced ML tools are readily available to proficiently train and test them. Those models are then efficiently deployed within highly scalable and fully parallelized PIC simulations during runtime. We demonstrate this methodology with a proof-of-concept implementation within the PIC code OSIRIS, where a fully connected neural network is used to replace a section of a Compton scattering module. We demonstrate that the ML-based method reproduces the results obtained with the conventional method and achieves better computational performance. These results offer a promising avenue for future applications of ML-based methods in PIC, particularly for physics extensions where a ML-based approach can provide a higher performance increase.<\/jats:p>","DOI":"10.1017\/s0022377822001180","type":"journal-article","created":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T02:36:06Z","timestamp":1670466966000},"update-policy":"https:\/\/doi.org\/10.1017\/policypage","source":"Crossref","is-referenced-by-count":10,"title":["Machine-learning-based models in particle-in-cell codes for advanced physics extensions"],"prefix":"10.1017","volume":"88","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6450-7511","authenticated-orcid":false,"given":"Chiara","family":"Badiali","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1841-4397","authenticated-orcid":false,"given":"Pablo J.","family":"Bilbao","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0761-6628","authenticated-orcid":false,"given":"F\u00e1bio","family":"Cruz","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2906-924X","authenticated-orcid":false,"given":"Lu\u00eds O.","family":"Silva","sequence":"additional","affiliation":[]}],"member":"56","published-online":{"date-parts":[[2022,12,7]]},"reference":[{"key":"S0022377822001180_ref11","volume-title":"Keras: The Python Deep Learning Library","author":"Chollet","year":"2018"},{"key":"S0022377822001180_ref19","doi-asserted-by":"crossref","first-page":"322","DOI":"10.1109\/TSSC.1969.300225","article-title":"Visual feature extraction by a multilayered network of analog threshold elements","volume":"5","author":"Fukushima","year":"1969","journal-title":"IEEE Trans. Syst. Sci. Cybern"},{"key":"S0022377822001180_ref21","doi-asserted-by":"crossref","unstructured":"Han, J. & Moraga, C. 1995 The influence of the sigmoid function parameters on the speed of backpropagation learning. In International Workshop on Artificial Neural Networks, pp. 195\u2013201. Springer.","DOI":"10.1007\/3-540-59497-3_175"},{"key":"S0022377822001180_ref1","unstructured":"Abadi, M. , Agarwal, A. , Barham, P. , Brevdo, E. , Chen, Z. , Citro, C. , Corrado, G.S. , Davis, A. , Dean, J. , Devin, M. , 2015 TensorFlow: Large-scale machine learning on heterogeneous systems. Software available from tensorflow.org."},{"key":"S0022377822001180_ref20","doi-asserted-by":"crossref","first-page":"095005","DOI":"10.1088\/1367-2630\/ac2004","article-title":"Quantum electrodynamics vacuum polarization solver","volume":"23","author":"Grismayer","year":"2021","journal-title":"New J. Phys"},{"key":"S0022377822001180_ref2","doi-asserted-by":"crossref","unstructured":"Aguilar, X. & Markidis, S. 2021 A deep learning-based particle-in-cell method for plasma simulations. In 2021 IEEE International Conference on Cluster Computing (CLUSTER), pp. 692\u2013697. IEEE.","DOI":"10.1109\/Cluster48925.2021.00103"},{"key":"S0022377822001180_ref31","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.122.035101"},{"key":"S0022377822001180_ref17","doi-asserted-by":"crossref","first-page":"124034","DOI":"10.1088\/0741-3335\/50\/12\/124034","article-title":"One-to-one direct modeling of experiments and astrophysical scenarios: pushing the envelope on kinetic plasma simulations","volume":"50","author":"Fonseca","year":"2008","journal-title":"Plasma Phys. Control. Fusion"},{"key":"S0022377822001180_ref7","first-page":"211","article-title":"Perception of numerical methods in rarefied gasdynamics","volume":"117","author":"Bird","year":"1989","journal-title":"Prog. Astronaut. Aeronaut"},{"key":"S0022377822001180_ref23","doi-asserted-by":"crossref","DOI":"10.1887\/0852743920","volume-title":"Computer Simulation Using Particles","author":"Hockney","year":"1988"},{"key":"S0022377822001180_ref30","doi-asserted-by":"crossref","unstructured":"Ott, J. , Pritchard, M. , Best, N. , Linstead, E. , Curcic, M. & Baldi, P. 2020 A fortran-keras deep learning bridge for scientific computing. Scientific Programming, 2020.","DOI":"10.1155\/2020\/8888811"},{"key":"S0022377822001180_ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.cpc.2016.04.002"},{"key":"S0022377822001180_ref22","doi-asserted-by":"crossref","first-page":"589","DOI":"10.1016\/j.jcp.2017.08.016","article-title":"A full-angle Monte-Carlo scattering technique including cumulative and single-event Rutherford scattering in plasmas","volume":"349","author":"Higginson","year":"2017","journal-title":"J. Comput. Phys"},{"key":"S0022377822001180_ref12","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1103\/PhysRev.21.483","article-title":"A quantum theory of the scattering of x-rays by light elements","volume":"21","author":"Compton","year":"1923","journal-title":"Phys. Rev"},{"key":"S0022377822001180_ref32","unstructured":"Paszke, A. , Gross, S. , Massa, F. , Lerer, A. , Bradbury, J. , Chanan, G. , Killeen, T. , Lin, Z. , Gimelshein, N. , Antiga, L. , 2019 Pytorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems 32, pp. 8024\u20138035. Curran Associates."},{"key":"S0022377822001180_ref5","doi-asserted-by":"crossref","first-page":"6","DOI":"10.3847\/1538-4365\/aac9ca","article-title":"Generalized, energy-conserving numerical simulations of particles in general relativity. I. Time-like and null geodesics","volume":"237","author":"Bacchini","year":"2018","journal-title":"Astrophys. J. Suppl. Ser"},{"key":"S0022377822001180_ref10","volume-title":"Deep Learning with Python","author":"Chollet","year":"2017"},{"key":"S0022377822001180_ref28","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1029\/94GL01835","article-title":"A Coulomb collision algorithm for weighted particle simulations","volume":"21","author":"Miller","year":"1994","journal-title":"Geophys. Res. Lett"},{"key":"S0022377822001180_ref25","unstructured":"Kingma, D.P. & Ba, J. 2014 Adam: a method for stochastic optimization. arXiv:1412.6980."},{"key":"S0022377822001180_ref14","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1103\/RevModPhys.55.403","article-title":"Particle simulation of plasmas","volume":"55","author":"Dawson","year":"1983","journal-title":"Rev. Mod. Phys"},{"key":"S0022377822001180_ref18","doi-asserted-by":"crossref","unstructured":"Fonseca, R.A. , Silva, L.O. , Tsung, F.S. , Decyk, V.K. , Lu, W. , Ren, C. , Mori, W.B. , Deng, S. , Lee, S. , Katsouleas, T. , 2002 OSIRIS: a three-dimensional, fully relativistic particle in cell code for modeling plasma based accelerators. In International Conference on Computational Science, pp. 342\u2013351. Springer.","DOI":"10.1007\/3-540-47789-6_36"},{"key":"S0022377822001180_ref9","unstructured":"Buneman, O. 1993 Tristan. Computer Space Plasma Physics: Simulation Techniques and Softwares."},{"key":"S0022377822001180_ref13","doi-asserted-by":"crossref","unstructured":"Curcic, M. 2019 A parallel Fortran framework for neural networks and deep learning. In Acm sigplan fortran forum (Vol. 38, No. 1, pp. 421). New York, NY, USA: ACM.","DOI":"10.1145\/3323057.3323059"},{"key":"S0022377822001180_ref24","doi-asserted-by":"publisher","DOI":"10.1063\/1.1814367"},{"key":"S0022377822001180_ref16","doi-asserted-by":"crossref","DOI":"10.1017\/S002237782000118X","article-title":"Compton scattering in particle-in-cell codes","volume":"86","author":"Del Gaudio","year":"2020","journal-title":"J. Plasma Phys"},{"key":"S0022377822001180_ref34","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevResearch.2.023129"},{"key":"S0022377822001180_ref3","doi-asserted-by":"crossref","first-page":"113001","DOI":"10.1088\/0741-3335\/57\/11\/113001","article-title":"Contemporary particle-in-cell approach to laser-plasma modelling","volume":"57","author":"Arber","year":"2015","journal-title":"Plasma Phys. Control. Fusion"},{"key":"S0022377822001180_ref26","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proc. Natl Acad. Sci"},{"key":"S0022377822001180_ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"S0022377822001180_ref27","unstructured":"Kube, R. , Churchill, R.M. & Sturdevant, B. 2021 Machine learning accelerated particle-in-cell plasma simulations. arXiv preprint arXiv:2110.12444."},{"key":"S0022377822001180_ref8","doi-asserted-by":"crossref","first-page":"237","DOI":"10.1103\/RevModPhys.42.237","article-title":"Bremsstrahlung, synchrotron radiation, and compton scattering of high-energy electrons traversing dilute gases","volume":"42","author":"Blumenthal","year":"1970","journal-title":"Rev. Mod. Phys"},{"key":"S0022377822001180_ref4","doi-asserted-by":"crossref","first-page":"023103","DOI":"10.1103\/PhysRevResearch.3.023103","article-title":"Generating ultradense pair beams using 400 GeV\/c protons","volume":"3","author":"Arrowsmith","year":"2021","journal-title":"Phys. Rev. Res"},{"key":"S0022377822001180_ref33","doi-asserted-by":"crossref","first-page":"2286","DOI":"10.1016\/j.jcp.2007.11.037","article-title":"A Monte-Carlo method for Coulomb collisions in hybrid plasma models","volume":"227","author":"Sherlock","year":"2008","journal-title":"J. Comput. Phys"},{"key":"S0022377822001180_ref6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s41781-021-00059-x","article-title":"Efficiency parameterization with neural networks","volume":"5","author":"Bello","year":"2021","journal-title":"Comput. Softw. Big Sci"},{"key":"S0022377822001180_ref29","doi-asserted-by":"crossref","first-page":"4642","DOI":"10.1103\/PhysRevE.55.4642","article-title":"Theory of cumulative small-angle collisions in plasmas","volume":"55","author":"Nanbu","year":"1997","journal-title":"Phys. Rev. E"},{"key":"S0022377822001180_ref35","doi-asserted-by":"publisher","DOI":"10.1016\/0021-9991(77)90099-7"},{"key":"S0022377822001180_ref37","doi-asserted-by":"publisher","DOI":"10.1088\/1367-2630\/18\/7\/073035"},{"key":"S0022377822001180_ref15","doi-asserted-by":"crossref","first-page":"95","DOI":"10.1016\/j.cpc.2007.02.092","article-title":"Upic: a framework for massively parallel particle-in-cell codes","volume":"177","author":"Decyk","year":"2007","journal-title":"Comput. Phys. Commun"}],"container-title":["Journal of Plasma Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.cambridge.org\/core\/services\/aop-cambridge-core\/content\/view\/S0022377822001180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,8]],"date-time":"2022-12-08T02:36:23Z","timestamp":1670466983000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.cambridge.org\/core\/product\/identifier\/S0022377822001180\/type\/journal_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12]]},"references-count":38,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2022,12]]}},"alternative-id":["S0022377822001180"],"URL":"https:\/\/doi.org\/10.1017\/s0022377822001180","relation":{},"ISSN":["0022-3778","1469-7807"],"issn-type":[{"value":"0022-3778","type":"print"},{"value":"1469-7807","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12]]},"assertion":[{"value":"Copyright \u00a9 The Author(s), 2022. Published by Cambridge University Press","name":"copyright","label":"Copyright","group":{"name":"copyright_and_licensing","label":"Copyright and Licensing"}}],"article-number":"895880602"}}