{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T01:32:57Z","timestamp":1762306377839,"version":"build-2065373602"},"reference-count":50,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T00:00:00Z","timestamp":1747267200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Integrated Computer-Aided Engineering"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:p>\n                    In this paper, we present the MUSONet model, which leverages information from different sources (in this case, wind farms) to perform a multi-step wind speed prediction. The main goal of this approach is improving the global prediction accuracy, specifically at longer prediction horizons. Thus, the proposed model is able to simultaneously predict the wind speed at three different prediction horizons (\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" overflow=\"scroll\">\n                        <mml:mn>6<\/mml:mn>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    h,\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" overflow=\"scroll\">\n                        <mml:mn>12<\/mml:mn>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    h, and\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" overflow=\"scroll\">\n                        <mml:mn>24<\/mml:mn>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    h), across three different wind farms located in Spain. We also evaluate the performance of the presented methodology by considering three different activation functions for hidden neurons in the neural network: Sigmoid, ReLU, and ELUs+2L. The results show that the proposed multi-source approach improves the performance of the single-source counterpart for the longer prediction horizons (\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" overflow=\"scroll\">\n                        <mml:mn>12<\/mml:mn>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    h and\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" overflow=\"scroll\">\n                        <mml:mn>24<\/mml:mn>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    h). In addition, the proposed multi-source method reduces by over\n                    <jats:inline-formula>\n                      <mml:math xmlns:mml=\"http:\/\/www.w3.org\/1998\/Math\/MathML\" display=\"inline\" overflow=\"scroll\">\n                        <mml:mn>30<\/mml:mn>\n                        <mml:mi mathvariant=\"normal\">%<\/mml:mi>\n                      <\/mml:math>\n                    <\/jats:inline-formula>\n                    the number of parameters compared to three single-source models (in this case, one model per wind farm), resulting in a simpler solution for the problem addressed and requiring much lower computational resources.\n                  <\/jats:p>","DOI":"10.1177\/10692509251337224","type":"journal-article","created":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T03:43:46Z","timestamp":1747280626000},"page":"366-378","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":0,"title":["Simultaneous multi-step wind speed prediction on multiple farms using multi-task deep learning"],"prefix":"10.1177","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3024-6194","authenticated-orcid":false,"given":"Rafael","family":"Ayll\u00f3n-Gavil\u00e1n","sequence":"first","affiliation":[{"name":"Department of Clinical-Epidemiological Research in Primary Care, Instituto Maim\u00f3nides de Investigaci\u00f3n Biom\u00e9dica de C\u00f3rdoba, C\u00f3rdoba, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1929-2408","authenticated-orcid":false,"given":"Antonio","family":"Manuel G\u00f3mez-Orellana","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, Universidad de C\u00f3rdoba, C\u00f3rdoba, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0700-275X","authenticated-orcid":false,"given":"V\u00edctor","family":"Manuel Vargas","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, Universidad de C\u00f3rdoba, C\u00f3rdoba, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8035-4057","authenticated-orcid":false,"given":"David","family":"Guijo-Rubio","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, Universidad de C\u00f3rdoba, C\u00f3rdoba, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4456-9886","authenticated-orcid":false,"given":"Jorge","family":"P\u00e9rez-Aracil","sequence":"additional","affiliation":[{"name":"Department of Signal Processing and Communications, Universidad de Alcal\u00e1, Alcal\u00e1 de Henares, Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4048-1676","authenticated-orcid":false,"given":"Sancho","family":"Salcedo-Sanz","sequence":"additional","affiliation":[{"name":"Department of Signal Processing and Communications, Universidad de Alcal\u00e1, Alcal\u00e1 de Henares, Madrid, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2657-776X","authenticated-orcid":false,"given":"Pedro","family":"Antonio Guti\u00e9rrez","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, Universidad de C\u00f3rdoba, C\u00f3rdoba, Spain"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4564-1816","authenticated-orcid":false,"given":"C\u00e9sar","family":"Herv\u00e1s-Mart\u00ednez","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Artificial Intelligence, Universidad de C\u00f3rdoba, C\u00f3rdoba, Spain"}]}],"member":"179","published-online":{"date-parts":[[2025,5,15]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2005.08.004"},{"key":"e_1_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2008.04.017"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2018.05.093"},{"key":"e_1_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2004.08.012"},{"key":"e_1_3_3_6_2","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-150501"},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2018.07.032"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2016.2607179"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2008.02.002"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rser.2014.03.033"},{"key":"e_1_3_3_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2021.117766"},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2011.01.037"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2019.04.157"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2020.115967"},{"key":"e_1_3_3_15_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2008.09.010"},{"key":"e_1_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-019-04359-7"},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2008.10.017"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2010.09.067"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.enconman.2017.06.021"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2015.03.071"},{"key":"e_1_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/TEC.2010.2043436"},{"key":"e_1_3_3_22_2","doi-asserted-by":"crossref","unstructured":"Sergio AT Ludermir TB. deep learning for wind speed forecasting in northeastern region of brazil. In: 2015 Brazilian conference on intelligent systems (BRACIS) 2015 pp.322\u2013327. IEEE Natal Brazil.","DOI":"10.1109\/BRACIS.2015.40"},{"key":"e_1_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2012.02.042"},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-230717"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.3233\/ICA-240734"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1111\/mice.13221"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.renene.2021.11.122"},{"key":"e_1_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.oceaneng.2020.108089"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jclepro.2020.125577"},{"key":"e_1_3_3_30_2","doi-asserted-by":"crossref","unstructured":"Dorado-Moreno M Dur\u00e1n-Rosal AM Guijo-Rubio D et al. Multiclass prediction of wind power ramp events combining reservoir computing and support vector machines. In: Advances in artificial intelligence: 17th conference of the spanish association for artificial intelligence CAEPIA 2016 Salamanca Spain September 14-16 2016. Proceedings 17 2016 pp.300\u2013309. Springer.","DOI":"10.1007\/978-3-319-44636-3_28"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.12.017"},{"key":"e_1_3_3_33_2","doi-asserted-by":"crossref","unstructured":"G\u00f3mez-Orellana AM Vargas VM Guijo-Rubio D et al. Medium-and long-term wind speed prediction using the multi-task learning paradigm. In: International work-conference on the interplay between natural and artificial computation 2024 pp. 293\u2013302. Springer.","DOI":"10.1007\/978-3-031-61137-7_27"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2022.119672"},{"key":"e_1_3_3_35_2","doi-asserted-by":"crossref","unstructured":"Lencione GR Von Zuben FJ. Wind speed forecasting via multi-task learning. In: 2021 International joint conference on neural networks (IJCNN) 2021 pp. 1\u20138. IEEE.","DOI":"10.1109\/IJCNN52387.2021.9534047"},{"key":"e_1_3_3_36_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijepes.2023.109073"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2023.127864"},{"key":"e_1_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2024.131058"},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.energy.2024.131787"},{"key":"e_1_3_3_40_2","first-page":"10","article-title":"A description of the advanced research WRF version 3","volume":"475","author":"Skamarock WC","year":"2008","unstructured":"Skamarock WC, Klemp JB, Dudhia J, et al. A description of the advanced research WRF version 3. NCAR Tech Note 2008; 475: 10\u20135065.","journal-title":"NCAR Tech Note"},{"key":"e_1_3_3_41_2","doi-asserted-by":"crossref","unstructured":"Szegedy C Liu W Jia Y et al. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition 2015 pp.1\u20139.","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_3_42_2","doi-asserted-by":"crossref","unstructured":"Scholz M Fraunholz M Selbig J. Nonlinear principal component analysis: neural network models and applications. In: Principal manifolds for data visualization and dimension reduction 2008 pp.44\u201367. Springer.","DOI":"10.1007\/978-3-540-73750-6_2"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102299"},{"key":"e_1_3_3_44_2","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_3_45_2","unstructured":"Glorot X Bengio Y. Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the thirteenth international conference on artificial intelligence and statistics 2010 pp.249\u2013256. JMLR Workshop and Conference Proceedings."},{"key":"e_1_3_3_46_2","unstructured":"Krizhevsky A Sutskever I Hinton GE. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems 2012 pp.1097\u20131105."},{"key":"e_1_3_3_47_2","doi-asserted-by":"crossref","unstructured":"Vargas VM Guijo-Rubio D Guti\u00e9rrez PA et al. Relu-based activations: Analysis and experimental study for deep learning. In: Conference of the spanish association for artificial intelligence 2021 pp.33\u201343. Springer.","DOI":"10.1007\/978-3-030-85713-4_4"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3105444"},{"key":"e_1_3_3_49_2","unstructured":"Clevert D-A Unterthiner T Hochreiter S. Fast and accurate deep network learning by exponential linear units (elus). arXiv preprint arXiv:1511.07289."},{"key":"e_1_3_3_50_2","first-page":"472","article-title":"Incorporating second-order functional knowledge for better option pricing","author":"Dugas C","unstructured":"Dugas C, Bengio Y, B\u00e9lisle F, et al. Incorporating second-order functional knowledge for better option pricing. Adv Neural Inf Process Syst: 472\u2013478.","journal-title":"Adv Neural Inf Process Syst"},{"key":"e_1_3_3_51_2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9868.2005.00503.x"}],"container-title":["Integrated Computer-Aided Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10692509251337224","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.1177\/10692509251337224","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.1177\/10692509251337224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T01:30:36Z","timestamp":1762306236000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.1177\/10692509251337224"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,15]]},"references-count":50,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["10.1177\/10692509251337224"],"URL":"https:\/\/doi.org\/10.1177\/10692509251337224","relation":{},"ISSN":["1069-2509","1875-8835"],"issn-type":[{"type":"print","value":"1069-2509"},{"type":"electronic","value":"1875-8835"}],"subject":[],"published":{"date-parts":[[2025,5,15]]}}}