{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T13:00:32Z","timestamp":1789995632494,"version":"4.0.1"},"reference-count":29,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T00:00:00Z","timestamp":1789948800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["analyticalsciencejournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Biotech &amp; Bioengineering"],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>Accurate prediction of bioprocess scale\u2010up is critical for accelerating the deployment of novel and sustainable biomanufacturing systems. However, this remains challenging as multi\u2010scale data is expensive to generate and mechanistic understanding is often incomplete, leading upscaling decisions to rely heavily on empirical expertise. This work proposes a data\u2010efficient strategy that integrates hybrid modelling with transfer learning to construct a high\u2010fidelity model from limited lab scale data and then adapt it using only pilot scale information for industrial scale prediction. A key innovation is the explicit assessment of this framework under small\u2010data scenarios, reflecting the practical constraints of industrial development. Using a real\u2010world yeast fermentation case, the proposed framework achieved accurate industrial scale dynamic predictions with a mean absolute percentage error of 23.2%, demonstrating its high data efficiency. Furthermore, this study reveals that the greyness of hybrid models exerts a decisive influence on its predictive accuracy and the feasibility of transfer learning under data scarcity, and that its optimal level differs from scenarios with abundant data. These findings therefore provide the first guidance on how to exploit hybrid modelling and transfer learning to build scalable digital twins when data are limited, enabling more confident and reliable bioprocess development and upscaling.<\/jats:p>","DOI":"10.1002\/bit.70385","type":"journal-article","created":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T12:01:06Z","timestamp":1789992066000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enabling Bioprocess Upscaling Prediction Through Hybrid Modelling and Transfer Learning Under Small\u2010Data Scenarios"],"prefix":"10.1002","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5749-2667","authenticated-orcid":false,"given":"Harvey","family":"Al\u2010Ramadhan","sequence":"first","affiliation":[{"name":"Department of Chemical Engineering The University of Manchester Manchester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7684-681X","authenticated-orcid":false,"given":"Fernando","family":"Vega\u2010Ramon","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering The University of Manchester Manchester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9055-4781","authenticated-orcid":false,"given":"Keju","family":"Jing","sequence":"additional","affiliation":[{"name":"Department of Chemical and Biochemical Engineering, College of Chemistry and Chemical Engineering Xiamen University Xiamen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5956-4618","authenticated-orcid":false,"given":"Dongda","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Chemical Engineering The University of Manchester Manchester UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,21]]},"reference":[{"key":"e_1_2_7_2_1","volume-title":"Fermentation","author":"Agharafeie R.","year":"2023"},{"key":"e_1_2_7_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-15-0169-2"},{"key":"e_1_2_7_4_1","volume-title":"Marine Drugs","author":"Ambati R. R.","year":"2014"},{"key":"e_1_2_7_5_1","doi-asserted-by":"publisher","DOI":"10.1021\/acs.iecr.0c01176"},{"key":"e_1_2_7_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tibtech.2023.03.002"},{"key":"e_1_2_7_7_1","volume-title":"Frontiers in Chemical Engineering","author":"Gargalo C. L.","year":"2024"},{"key":"e_1_2_7_8_1","doi-asserted-by":"publisher","DOI":"10.1002\/cjce.24276"},{"key":"e_1_2_7_9_1","unstructured":"Han K. andO.Levenspiel1987.Extended Monod Kinetics for Substrate Product and Cell Inhibition."},{"key":"e_1_2_7_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biortech.2023.130246"},{"key":"e_1_2_7_11_1","first-page":"2595","volume-title":"Computer Aided Chemical Engineering","author":"Kay S.","year":"2023"},{"key":"e_1_2_7_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ces.2024.121088"},{"key":"e_1_2_7_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.mec.2020.e00131"},{"key":"e_1_2_7_14_1","volume-title":"Biotechnology and Bioengineering","author":"Mahanty B.","year":"2023"},{"key":"e_1_2_7_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00449-025-03147-z"},{"key":"e_1_2_7_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2004.02.014"},{"key":"e_1_2_7_17_1","doi-asserted-by":"crossref","unstructured":"Psichogios D. C. andL. H.Ungar1992.A Hybrid Neural Network\u2010First Principles Approach to Process Modeling.","DOI":"10.1002\/aic.690381003"},{"key":"e_1_2_7_18_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cej.2025.162018"},{"key":"e_1_2_7_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bej.2022.108761"},{"key":"e_1_2_7_20_1","doi-asserted-by":"publisher","DOI":"10.1002\/bit.27980"},{"key":"e_1_2_7_21_1","unstructured":"Saad M. F.Bangi andJ. S.\u2010I.Kwon2019.Deep Hybrid Modeling of Chemical Process: Application to Hydraulic Fracturing.https:\/\/www.elsevier.com\/open\u2010access\/userlicense\/1.0\/."},{"key":"e_1_2_7_22_1","volume-title":"Chemie Ingenieur Technik","author":"Sch\u00e4fer P.","year":"2020"},{"key":"e_1_2_7_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.dche.2023.100136"},{"key":"e_1_2_7_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00449-016-1557-1"},{"key":"e_1_2_7_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compchemeng.2013.08.008"},{"key":"e_1_2_7_26_1","doi-asserted-by":"publisher","DOI":"10.1002\/bit.27950"},{"key":"e_1_2_7_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12010-022-03868-x"},{"key":"e_1_2_7_28_1","doi-asserted-by":"publisher","DOI":"10.1186\/s12896-024-00928-4"},{"key":"e_1_2_7_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/10_2014_293"},{"key":"e_1_2_7_30_1","doi-asserted-by":"crossref","unstructured":"Zhang D. E.Antonio D.Rio\u2010Chanona P.Petsagkourakis andJ.Wagner2019.Hybrid Physics\u2010Based and Data\u2010Driven Modelling for Bioprocess Online Simulation and Optimisation.","DOI":"10.1002\/bit.27120"}],"container-title":["Biotechnology and Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/bit.70385","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/bit.70385","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/bit.70385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,21]],"date-time":"2026-09-21T12:01:10Z","timestamp":1789992070000},"score":1,"resource":{"primary":{"URL":"https:\/\/analyticalsciencejournals.onlinelibrary.wiley.com\/doi\/10.1002\/bit.70385"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,21]]},"references-count":29,"alternative-id":["10.1002\/bit.70385"],"URL":"https:\/\/doi.org\/10.1002\/bit.70385","archive":["Portico"],"relation":{},"ISSN":["0006-3592","1097-0290"],"issn-type":[{"value":"0006-3592","type":"print"},{"value":"1097-0290","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,21]]},"assertion":[{"value":"2026-06-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"bit.70385"}}