{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T04:20:26Z","timestamp":1773894026174,"version":"3.50.1"},"reference-count":64,"publisher":"Wiley","issue":"4","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100001871","name":"Funda\u00e7\u00e3o para a Ci\u00eancia e a Tecnologia","doi-asserted-by":"publisher","award":["2022.06822.PTDC"],"award-info":[{"award-number":["2022.06822.PTDC"]}],"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\/154311\/2022"],"award-info":[{"award-number":["PRT\/BD\/154311\/2022"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Expert Systems"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>\n                    The growing reliance on fossil fuels for energy generation has raised concerns about their significant contribution to global warming and the associated risks of supply instability. Anaerobic Digestion (AD) within Wastewater Treatment Plants (WWTPs) offers a renewable alternative by producing biogas, while effective operational optimisation requires accurate forecasting of biogas yields under varying conditions. This study addresses this challenge by developing, tuning and evaluating five Deep Learning (DL) architectures for biogas production prediction: one\u2010dimensional Convolutional Neural Network (1D\u2010CNN), Long Short\u2010Term Memory (LSTM), Gated Recurrent Unit (GRU), Transformers and Residual Encoding. Among these, the GRU model demonstrated superior performance, achieving a Root Mean Square Error (RMSE) of 139.1\u2009m\n                    <jats:sup>3<\/jats:sup>\n                    \/day and a Mean Absolute Error (MAE) of 135.9\u2009m\n                    <jats:sup>3<\/jats:sup>\n                    \/day. The adaptability of the GRU model to different datasets was examined through Transfer Learning (TL), revealing a clear difference in performance depending on the TL approach used: the retrained model achieved a RMSE of 230.1\u2009m\n                    <jats:sup>3<\/jats:sup>\n                    \/day and a MAE of 229.9\u2009m\n                    <jats:sup>3<\/jats:sup>\n                    \/day, whereas the model without retraining exhibited higher errors of 358.7 and 358.8\u2009m\n                    <jats:sup>3<\/jats:sup>\n                    \/day, respectively. A key contribution of this work lies in its comprehensive Explainable Artificial Intelligence (XAI) analysis, which applied both ante hoc attention mechanisms and post hoc interpretability techniques such as SHAP and LIME. The XAI methods consistently identified biogas production, the study's target variable, as the most influential feature in the model's predictions. Among the remaining features, some changes were observed in their impact on model predictions. Moreover, the study highlighted how TL affects prediction performance and the stability and consistency of feature importance, thereby improving the transparency and trustworthiness of the forecasting models.\n                  <\/jats:p>","DOI":"10.1111\/exsy.70235","type":"journal-article","created":{"date-parts":[[2026,3,8]],"date-time":"2026-03-08T16:14:45Z","timestamp":1772986485000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Exploring Transfer Learning's Impact on the Explainability of Deep Learning Models for Wastewater Treatment Plants' Biogas Production"],"prefix":"10.1111","volume":"43","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7143-5413","authenticated-orcid":false,"given":"Pedro","family":"Oliveira","sequence":"first","affiliation":[{"name":"ALGORITMI\/LASI Centre University of Minho  Braga Portugal"}]},{"given":"Afonso","family":"Bessa","sequence":"additional","affiliation":[{"name":"ALGORITMI\/LASI Centre University of Minho  Braga Portugal"}]},{"given":"Jo\u00e3o","family":"Pereira","sequence":"additional","affiliation":[{"name":"ALGORITMI\/LASI Centre University of Minho  Braga Portugal"}]},{"given":"S\u00e9rgio","family":"Silva","sequence":"additional","affiliation":[{"name":"LABBELS Associate Laboratory University of Minho  Braga Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4645-908X","authenticated-orcid":false,"given":"Maria Salom\u00e9","family":"Duarte","sequence":"additional","affiliation":[{"name":"LABBELS Associate Laboratory University of Minho  Braga Portugal"}]},{"given":"Dalila","family":"Dur\u00e3es","sequence":"additional","affiliation":[{"name":"ALGORITMI\/LASI Centre University of Minho  Braga Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3549-0754","authenticated-orcid":false,"given":"Paulo","family":"Novais","sequence":"additional","affiliation":[{"name":"ALGORITMI\/LASI Centre University of Minho  Braga Portugal"}]}],"member":"311","published-online":{"date-parts":[[2026,3,6]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0181142"},{"key":"e_1_2_11_4_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2022.01.011"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"e_1_2_11_6_1","unstructured":"Bahdanau D. K.Cho andY.Bengio.\u201cNeural Machine Translation by Jointly Learning to Align and Translate.\u201darXiv preprint arXiv:1409.0473.2014."},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ceja.2025.100722"},{"key":"e_1_2_11_8_1","doi-asserted-by":"publisher","DOI":"10.3390\/info14110598"},{"key":"e_1_2_11_9_1","volume-title":"The Mythos of Model Interpretability","author":"Chase L. Z.","year":"2016"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2023.06.036"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2019.134574"},{"key":"e_1_2_11_12_1","first-page":"248","volume-title":"Imagenet: A Large\u2010Scale Hierarchical Image Database","author":"Deng J.","year":"2009"},{"key":"e_1_2_11_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/microorganisms9020324"},{"key":"e_1_2_11_14_1","unstructured":"European Biogas Association.\u201c22 Bcm of Biogases Were Produced in Europe in 2023 According to a New Report Released Today.\u201d14th Edition of the Statistical Report.2024.https:\/\/surl.li\/ypogaw."},{"key":"e_1_2_11_15_1","unstructured":"European Commission.\u201cCommunication From the Commission to the European Parliament and the Council \u2013 European Research Area Policy Agenda: Overview of Actions for the Period 2022\u20132024.\u201dCOM(2022) 230 final May 10.2022.https:\/\/eur\u2010lex.europa.eu\/legal\u2010content\/EN\/TXT\/?uri=celex:52022DC0230."},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2024.143936"},{"key":"e_1_2_11_17_1","doi-asserted-by":"publisher","DOI":"10.3390\/s22239517"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3236009"},{"key":"e_1_2_11_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/toxics11010051"},{"key":"e_1_2_11_20_1","doi-asserted-by":"publisher","DOI":"10.3389\/ffgc.2023.1249300"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010024\u201068906\u20106"},{"key":"e_1_2_11_22_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598\u2010025\u201091329\u2010w"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.3390\/w16192870"},{"key":"e_1_2_11_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.biortech.2022.128468"},{"key":"e_1_2_11_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.esr.2025.101669"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.3390\/atmos15121432"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.3390\/toxics13040254"},{"key":"e_1_2_11_28_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.watres.2021.117697"},{"key":"e_1_2_11_29_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4176670"},{"key":"e_1_2_11_30_1","doi-asserted-by":"crossref","unstructured":"Jiahao H. andY.Bao.2025.\u201cRethinking Transformers for Efficiency and Scalability.\u201dAvailable at SSRN 5161897.https:\/\/doi.org\/10.2139\/ssrn.5161897.","DOI":"10.2139\/ssrn.5161897"},{"key":"e_1_2_11_31_1","unstructured":"Johnsen F. N.2024.\u201cExplaining Individual Predictions of the Cross\u2010Disease Attention Network.\u201dMaster's Thesis NTNU."},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21217191"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559\u2010024\u201010272\u20106"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/en17236084"},{"key":"e_1_2_11_35_1","volume-title":"To Transfer or Not to Transfer","author":"Marx M. R. Z.","year":"2005"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhydene.2024.12.396"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1002\/wer.11136"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scitotenv.2020.142753"},{"key":"e_1_2_11_39_1","doi-asserted-by":"publisher","DOI":"10.3390\/ELECTRONICS10101149"},{"key":"e_1_2_11_40_1","first-page":"325","volume-title":"Employing Explainable AI Techniques for Air Pollution: An Ante\u2010Hoc and Post\u2010Hoc Approach in Dioxide Nitrogen Forecasting","author":"Oliveira P.","year":"2024"},{"key":"e_1_2_11_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.3390\/info14040242"},{"key":"e_1_2_11_43_1","doi-asserted-by":"publisher","DOI":"10.3390\/en15082940"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCECE53908.2022.9793213"},{"key":"e_1_2_11_45_1","unstructured":"Pliatsika V. J.Fonseca T.Wang andJ.Stoyanovich.\u201cSharp: Explaining Rankings With Shapley Values.\u201darXiv preprint arXiv:2401.16744.2024.https:\/\/doi.org\/10.48550\/arXiv.2401.16744."},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.egyr.2025.04.015"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939778"},{"key":"e_1_2_11_48_1","unstructured":"Rojat T. R.Puget D.Filliat J.Del Ser R.Gelin andN.D\u00edaz\u2010Rodr\u00edguez.2021.\u201cExplainable Artificial Intelligence (Xai) on Timeseries Data: A Survey.\u201darXiv preprint arXiv:2104.00950.https:\/\/doi.org\/10.48550\/arXiv.2104.00950."},{"key":"e_1_2_11_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijhydene.2023.04.143"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1021\/acsestengg.3c00435"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263\u2010019\u201001228\u20107"},{"key":"e_1_2_11_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cej.2024.155582"},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.1561\/116.00000123"},{"key":"e_1_2_11_54_1","first-page":"3319","volume-title":"International Conference on Machine Learning","author":"Sundararajan M.","year":"2017"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01424-7_27"},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.1039\/D0GC01918F"},{"key":"e_1_2_11_57_1","article-title":"Attention Is All You Need","volume":"30","author":"Vaswani A.","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_58_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40708\u2010024\u201000222\u20101"},{"key":"e_1_2_11_59_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537\u2010016\u20100043\u20106"},{"key":"e_1_2_11_60_1","doi-asserted-by":"publisher","DOI":"10.1190\/geo2022\u20100448.1"},{"key":"e_1_2_11_61_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"e_1_2_11_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3443876"},{"key":"e_1_2_11_63_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107617"},{"key":"e_1_2_11_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jwpe.2024.105267"},{"issue":"1","key":"e_1_2_11_65_1","article-title":"Interpreting CNN Knowledge via an Explanatory Graph","volume":"32","author":"Zhang Q.","year":"2018","journal-title":"Proceedings of The AAAI Conference on Artificial Intelligence"}],"container-title":["Expert Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70235","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/exsy.70235","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/exsy.70235","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,19]],"date-time":"2026-03-19T02:01:53Z","timestamp":1773885713000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/exsy.70235"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":64,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["10.1111\/exsy.70235"],"URL":"https:\/\/doi.org\/10.1111\/exsy.70235","archive":["Portico"],"relation":{},"ISSN":["0266-4720","1468-0394"],"issn-type":[{"value":"0266-4720","type":"print"},{"value":"1468-0394","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,6]]},"assertion":[{"value":"2025-05-16","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-21","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-03-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70235"}}