{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:20:43Z","timestamp":1782318043792,"version":"3.54.5"},"reference-count":28,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T00:00:00Z","timestamp":1675123200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T00:00:00Z","timestamp":1675123200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"RCUK Energy Programme","award":["EP\/I501045\/1"],"award-info":[{"award-number":["EP\/I501045\/1"]}]},{"name":"UCL Graduate Research and Overseas Research Scholarship"},{"name":"STFC UCL Centre for Doctoral Training in Data Intensive Science","award":["ST\/P006736\/1"],"award-info":[{"award-number":["ST\/P006736\/1"]}]},{"DOI":"10.13039\/100018708","name":"Euratom Research and Training Programme","doi-asserted-by":"crossref","award":["633053"],"award-info":[{"award-number":["633053"]}],"id":[{"id":"10.13039\/100018708","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Institutional Support for the Development of a Research Organization"},{"name":"EU Horizon 2020 Research & Innovation Programme","award":["758892"],"award-info":[{"award-number":["758892"]}]},{"name":"NVIDIA Corporation\u2019s GPU Grant"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2023,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    The tritium breeding ratio (TBR) is an essential quantity for the design of modern and next-generation D-T fueled nuclear fusion reactors. Representing the ratio between tritium fuel generated in breeding blankets and fuel consumed during reactor runtime, the TBR depends on reactor geometry and material properties in a complex manner. In this work, we explored the training of surrogate models to produce a cheap but high-quality approximation for a Monte Carlo (MC) TBR model in use at the UK Atomic Energy Authority. We investigated possibilities for dimensional reduction of its feature space, reviewed 9 families of surrogate models for potential applicability, and performed hyperparameter optimization. Here we present the performance and scaling properties of these models, the fastest of which, an artificial neural network, demonstrated\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:msup>\n                          <mml:mi>R<\/mml:mi>\n                          <mml:mn>2<\/mml:mn>\n                        <\/mml:msup>\n                        <mml:mo>=<\/mml:mo>\n                        <mml:mn>0.985<\/mml:mn>\n                      <\/mml:math>\n                      <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"mlstacb2b3ieqn1.gif\" xlink:type=\"simple\"\/>\n                    <\/jats:inline-formula>\n                    and a mean prediction time of\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mn>0.898<\/mml:mn>\n                        <mml:mtext>\u2009<\/mml:mtext>\n                        <mml:mi>\u03bc<\/mml:mi>\n                        <mml:mrow>\n                          <mml:mtext>s<\/mml:mtext>\n                        <\/mml:mrow>\n                      <\/mml:math>\n                      <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"mlstacb2b3ieqn2.gif\" xlink:type=\"simple\"\/>\n                    <\/jats:inline-formula>\n                    , representing a relative speedup of\n                    <jats:inline-formula>\n                      <jats:tex-math>\n                        \n                      <\/jats:tex-math>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" overflow=\"scroll\">\n                        <mml:mn>8<\/mml:mn>\n                        <mml:mo>\u00d7<\/mml:mo>\n                        <mml:msup>\n                          <mml:mn>10<\/mml:mn>\n                          <mml:mn>6<\/mml:mn>\n                        <\/mml:msup>\n                      <\/mml:math>\n                      <jats:inline-graphic xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"mlstacb2b3ieqn3.gif\" xlink:type=\"simple\"\/>\n                    <\/jats:inline-formula>\n                    with respect to the expensive MC model. We further present a novel adaptive sampling algorithm, Quality-Adaptive Surrogate Sampling, capable of interfacing with any of the individually studied surrogates. Our preliminary testing on a toy TBR theory has demonstrated the efficacy of this algorithm for accelerating the surrogate modelling process.\n                  <\/jats:p>","DOI":"10.1088\/2632-2153\/acb2b3","type":"journal-article","created":{"date-parts":[[2023,1,12]],"date-time":"2023-01-12T17:42:25Z","timestamp":1673545345000},"page":"015008","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Fast regression of the tritium breeding ratio in fusion reactors"],"prefix":"10.1088","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4306-0209","authenticated-orcid":true,"given":"P","family":"M\u00e1nek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"G","family":"Van Goffrier","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0904-3448","authenticated-orcid":true,"given":"V","family":"Gopakumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8453-7574","authenticated-orcid":false,"given":"N","family":"Nikolaou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6909-0946","authenticated-orcid":true,"given":"J","family":"Shimwell","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4205-5267","authenticated-orcid":false,"given":"I","family":"Waldmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"266","published-online":{"date-parts":[[2023,1,31]]},"reference":[{"key":"mlstacb2b3bib1","article-title":"Optimization using surrogate models","author":"S\u00f8ndergaard","year":"2003"},{"key":"mlstacb2b3bib2","author":"Myers","year":"2002","edition":"2nd edn"},{"key":"mlstacb2b3bib3","article-title":"Paramak","author":"","year":"2020"},{"key":"mlstacb2b3bib4","article-title":"Muir energy spectrum","author":"","year":"2019"},{"key":"mlstacb2b3bib5","article-title":"FENDL-3.1d: fusion evaluated nuclear data library ver.3.1d"},{"key":"mlstacb2b3bib6","article-title":"The joint evaluated fission and fusion file (JEFF) version 3.3"},{"key":"mlstacb2b3bib7","doi-asserted-by":"publisher","first-page":"2887","DOI":"10.1016\/j.nds.2011.11.002","article-title":"ENDF\/B-VII.1 Nuclear Data for Science and Technology: cross sections, covariances, fission product yields and decay data","volume":"112","author":"Chadwick","year":"2011","journal-title":"Nucl. Data Sheets"},{"key":"mlstacb2b3bib8","first-page":"pp 1598","author":"Kleijnen","year":"2013"},{"key":"mlstacb2b3bib9","first-page":"1871","volume":"9","author":"Fan","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"mlstacb2b3bib10","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.5555\/1953048.2078195","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"mlstacb2b3bib11","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","volume":"29","author":"Friedman","year":"2001","journal-title":"Ann. Stat."},{"key":"mlstacb2b3bib12","article-title":"Stochastic gradient boosting technical report","author":"Friedman","year":"1999"},{"key":"mlstacb2b3bib13","doi-asserted-by":"publisher","author":"Hastie","year":"2009","DOI":"10.1007\/978-0-387-84858-7"},{"key":"mlstacb2b3bib14","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/s10994-006-6226-1","volume":"63","author":"Geurts","year":"2006","journal-title":"Mach. Learn."},{"key":"mlstacb2b3bib15","doi-asserted-by":"publisher","first-page":"107","DOI":"10.5555\/645526.657132","article-title":"Improving regressors using boosting techniques","volume":"97","author":"Drucker","year":"1997","journal-title":"ICML"},{"key":"mlstacb2b3bib16","volume":"vol 2","author":"Williams","year":"2006"},{"key":"mlstacb2b3bib17","article-title":"Keras","author":"Chollet","year":"2015"},{"key":"mlstacb2b3bib18","first-page":"pp 517","article-title":"A two-dimensional interpolation function for irregularly-spaced data","author":"Shepard","year":"1968"},{"key":"mlstacb2b3bib19","doi-asserted-by":"publisher","DOI":"10.1016\/j.advengsoft.2019.03.005","volume":"135","author":"Bouhlel","year":"2019","journal-title":"Adv. Eng. Softw."},{"key":"mlstacb2b3bib20","first-page":"pp 400","article-title":"On Bayesian methods for seeking the extremum","author":"Mo\u010dkus","year":"1975"},{"key":"mlstacb2b3bib21","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.compchemeng.2016.10.006","volume":"96","author":"Garud","year":"2016","journal-title":"Comput. Chem. Eng."},{"key":"mlstacb2b3bib22","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.jconhyd.2018.08.005","volume":"216","author":"Zhou","year":"2018","journal-title":"J. Contaminant Hydrol."},{"key":"mlstacb2b3bib23","doi-asserted-by":"publisher","DOI":"10.1029\/2019WR025721","volume":"56","author":"Zhang","year":"2020","journal-title":"Water Resour. Res."},{"key":"mlstacb2b3bib24","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.envsoft.2017.05.005","volume":"95","author":"Gong","year":"2017","journal-title":"Environ. Modelling Softw."},{"key":"mlstacb2b3bib25","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1007\/s10596-011-9236-4","volume":"15","author":"Ginting","year":"2011","journal-title":"Comput. Geosci."},{"key":"mlstacb2b3bib26","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1214\/12-BA724","volume":"7","author":"Solonen","year":"2012","journal-title":"Bayesian Anal."},{"key":"mlstacb2b3bib27","article-title":"UCL TBR group project","author":"M\u00e1nek","year":"2020"},{"key":"mlstacb2b3bib28","article-title":"Surrogate modelling of the tritium breeding ratio CDT DIS note","author":"M\u00e1nek","year":"2020"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb2b3","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb2b3\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb2b3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb2b3\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb2b3\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb2b3\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb2b3\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb2b3\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,31]],"date-time":"2023-01-31T05:04:44Z","timestamp":1675141484000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/acb2b3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,31]]},"references-count":28,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,1,31]]},"published-print":{"date-parts":[[2023,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/acb2b3","relation":{"has-review":[{"id-type":"doi","id":"10.1088\/2632-2153\/ACB2B3\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/ACB2B3\/v2\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/ACB2B3\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/ACB2B3\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1088\/2632-2153\/ACB2B3\/v2\/response1","asserted-by":"object"}]},"ISSN":["2632-2153"],"issn-type":[{"value":"2632-2153","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,31]]},"assertion":[{"value":"Fast regression of the tritium breeding ratio in fusion reactors","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 2023 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2022-09-12","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-01-12","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2023-01-31","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}