{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T20:17:27Z","timestamp":1780604247763,"version":"3.54.1"},"reference-count":47,"publisher":"Wiley","issue":"11","license":[{"start":{"date-parts":[[2021,9,16]],"date-time":"2021-09-16T00:00:00Z","timestamp":1631750400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["advanced.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Advanced Intelligent Systems"],"published-print":{"date-parts":[[2021,11]]},"abstract":"<jats:sec><jats:label\/><jats:p>Bayesian optimization (BO) has emerged as the algorithm of choice for guiding the selection of experimental parameters in automated active learning driven high throughput experiments in materials science and chemistry. Previous studies suggest that optimization performance of the typical surrogate model in the BO algorithm, Gaussian processes (GPs), may be limited due to its inability to handle complex datasets. Herein, various surrogate models for BO, including GPs and neural network ensembles (NNEs), are investigated. Two materials datasets of different complexity with different properties are used, to compare the performance of GP and NNE\u2014the first is the compressive strength of concrete (8 inputs and 1 target), and the second is a simulated high\u2010dimensional dataset of thermoelectric properties of inorganic materials (22 inputs and 1 target). While NNEs can converge faster toward optimum values, GPs with optimized kernels are able to ultimately achieve the best evaluated values after 100 iterations, even for the most complex dataset. This surprising result is contrary to expectations. It is believed that these findings shed new light on the understanding of surrogate models for BO, and can help accelerate the inverse design of new materials with better structural and functional performance.<\/jats:p><\/jats:sec>","DOI":"10.1002\/aisy.202100101","type":"journal-article","created":{"date-parts":[[2021,9,16]],"date-time":"2021-09-16T03:15:46Z","timestamp":1631762146000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["Extrapolative Bayesian Optimization with Gaussian Process and Neural Network Ensemble Surrogate Models"],"prefix":"10.1002","volume":"3","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8276-2364","authenticated-orcid":false,"given":"Yee-Fun","family":"Lim","sequence":"first","affiliation":[{"name":"Institute of Materials Research and Engineering A*STAR (Agency for Science Technology and Research)  2 Fusionopolis Way #08-03 Innovis Singapore 138634 Republic of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2044-5296","authenticated-orcid":false,"given":"Chee Koon","family":"Ng","sequence":"additional","affiliation":[{"name":"Institute of Materials Research and Engineering A*STAR (Agency for Science Technology and Research)  2 Fusionopolis Way #08-03 Innovis Singapore 138634 Republic of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"U.S.","family":"Vaitesswar","sequence":"additional","affiliation":[{"name":"Department of Materials Science and Engineering Nanyang Technological University  50 Nanyang Avenue Singapore 639798 Republic of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1270-9047","authenticated-orcid":false,"given":"Kedar","family":"Hippalgaonkar","sequence":"additional","affiliation":[{"name":"Institute of Materials Research and Engineering A*STAR (Agency for Science Technology and Research)  2 Fusionopolis Way #08-03 Innovis Singapore 138634 Republic of Singapore"},{"name":"Department of Materials Science and Engineering Nanyang Technological University  50 Nanyang Avenue Singapore 639798 Republic of Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2021,9,16]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.joule.2018.05.009"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41578-018-0005-z"},{"key":"e_1_2_8_4_1","unstructured":"The Materials Project https:\/\/materialsproject.org\/ (accessed: May 2021)."},{"key":"e_1_2_8_5_1","unstructured":"Automatic \u2013 FLOW for Materials Discovery http:\/\/www.aflowlib.org\/ (accessed: May 2021)."},{"key":"e_1_2_8_6_1","unstructured":"NIMS Materials Database https:\/\/mits.nims.go.jp\/en\/ (accessed: May 2021)."},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.1021\/cm400893e"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1063\/1.4944683"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0224-1"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1335-8"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41570-018-0066-y"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1002\/aenm.201903242"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-matsci-090319-010954"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscatal.9b04186"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-020-2442-2"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aaz1708"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.8b00307"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-020-64397-3"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1126\/sciadv.aaz8867"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1039\/D0TA04096G"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1039\/D0TA04441E"},{"key":"e_1_2_8_22_1","doi-asserted-by":"publisher","DOI":"10.1002\/adfm.202102606"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1002\/adma.202001626"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aat0650"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1038\/npjcompumats.2016.31"},{"key":"e_1_2_8_26_1","unstructured":"P. I.Frazier arXiv preprint arXiv:1807.02811 [stat.ML] 2018."},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"e_1_2_8_28_1","unstructured":"J.Snoek O.Rippel K.Swersky R.Kiros N.Satish N.Sundaram M. M. A.Patwary R. P. AdamsPrabhat presented atProc. of the 32nd Int. Conf. on Machine Learning Lille France July2015."},{"key":"e_1_2_8_29_1","volume-title":"30th Conf. on Neural Information Processing Systems","author":"Springenberg J. T.","year":"2016"},{"key":"e_1_2_8_30_1","unstructured":"C.Blundell J.Cornebise K.Kavukcuoglu D.Wierstra.Proc. of the 32nd Int. Conf. on Machine Learning Lille France July2015."},{"key":"e_1_2_8_31_1","unstructured":"Y.Gal Z.Ghahramani.arXiv preprint arXiv:1506.02142v6 [stat.ML] 2016."},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202000245"},{"key":"e_1_2_8_33_1","volume-title":"UCI Machine Learning Repository","author":"Dua D.","year":"2019"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.85"},{"key":"e_1_2_8_35_1","unstructured":"Scikit-Optimize: Sequential model-based optimization in Python https:\/\/scikit-optimize.github.io\/stable\/ (accessed: May 2021)."},{"key":"e_1_2_8_36_1","first-page":"2825","volume":"12","author":"Pedregosa F.","year":"2011","journal-title":"J. Machine Learn. Res."},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41524-019-0209-9"},{"key":"e_1_2_8_38_1","unstructured":"Keras: the Python Deep Learning API https:\/\/keras.io\/ (accessed: May 2021)."},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1039\/D0MH00062K"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0008-8846(98)00165-3"},{"key":"e_1_2_8_41_1","volume-title":"Gaussian Processes For Machine Learning","author":"Rasmussen C. E.","year":"2006"},{"key":"e_1_2_8_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2014.02.027"},{"key":"e_1_2_8_43_1","unstructured":"H.Kaya P.Tufekci F. S.Gurgen inInt. Conf. on Emerging Trends in Computer and Electronics Engineering (ICETCEE) 2012 pp.13\u201318."},{"key":"e_1_2_8_44_1","doi-asserted-by":"publisher","DOI":"10.1038\/sdata.2017.85"},{"key":"e_1_2_8_45_1","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/87.4.954"},{"key":"e_1_2_8_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"e_1_2_8_47_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"e_1_2_8_48_1","volume-title":"Hands-on Machine Learning with Scikit-Learn, Keras & TensorFlow","author":"Geron A.","year":"2019"}],"container-title":["Advanced Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202100101","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/aisy.202100101","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/aisy.202100101","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T16:15:22Z","timestamp":1759853722000},"score":1,"resource":{"primary":{"URL":"https:\/\/advanced.onlinelibrary.wiley.com\/doi\/10.1002\/aisy.202100101"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,9,16]]},"references-count":47,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2021,11]]}},"alternative-id":["10.1002\/aisy.202100101"],"URL":"https:\/\/doi.org\/10.1002\/aisy.202100101","archive":["Portico"],"relation":{},"ISSN":["2640-4567","2640-4567"],"issn-type":[{"value":"2640-4567","type":"print"},{"value":"2640-4567","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,9,16]]},"assertion":[{"value":"2021-05-22","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-09-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2100101"}}