{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T00:13:32Z","timestamp":1775693612610,"version":"3.50.1"},"reference-count":26,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2022,1,13]],"date-time":"2022-01-13T00:00:00Z","timestamp":1642032000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"European Council - Horizon 2020","award":["814624"],"award-info":[{"award-number":["814624"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>The environmental microclimatic characteristics are often subject to fluctuations of considerable importance, which can cause irreparable damage to art works. We explored the applicability of Artificial Intelligence (AI) techniques to the Cultural Heritage area, with the aim of predicting short-term microclimatic values based on data collected at Rosenborg Castle (Copenhagen), housing the Royal Danish Collection. Specifically, this study applied the NAR (Nonlinear Autoregressive) and NARX (Nonlinear Autoregressive with Exogenous) models to the Rosenborg microclimate time series. Even if the two models were applied to small datasets, they have shown a good adaptive capacity predicting short-time future values. This work explores the use of AI in very short forecasting of microclimate variables in museums as a potential tool for decision-support systems to limit the climate-induced damages of artworks within the scope of their preventive conservation. The proposed model could be a useful support tool for the management of the museums.<\/jats:p>","DOI":"10.3390\/s22020615","type":"journal-article","created":{"date-parts":[[2022,1,14]],"date-time":"2022-01-14T03:14:56Z","timestamp":1642130096000},"page":"615","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":30,"title":["Novel Model Based on Artificial Neural Networks to Predict Short-Term Temperature Evolution in Museum Environment"],"prefix":"10.3390","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4112-2544","authenticated-orcid":false,"given":"Alessandro","family":"Bile","sequence":"first","affiliation":[{"name":"Department of Fundamental and Applied Sciences for Engineering, Sapienza Universit\u00e0 di Roma, via A. Scarpa 16, 00161 Roma, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7724-4538","authenticated-orcid":false,"given":"Hamed","family":"Tari","sequence":"additional","affiliation":[{"name":"Department of Fundamental and Applied Sciences for Engineering, Sapienza Universit\u00e0 di Roma, via A. Scarpa 16, 00161 Roma, Italy"}]},{"given":"Andreas","family":"Grinde","sequence":"additional","affiliation":[{"name":"Royal Danish Collections, \u00d8ster Voldgade 4A, 1355 Copenhagen, Denmark"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9591-5606","authenticated-orcid":false,"given":"Francesca","family":"Frasca","sequence":"additional","affiliation":[{"name":"Department of Physics, Sapienza Universit\u00e0 di Roma, P.le A. Moro 5, 00185 Rome, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7435-1426","authenticated-orcid":false,"given":"Anna Maria","family":"Siani","sequence":"additional","affiliation":[{"name":"Department of Physics, Sapienza Universit\u00e0 di Roma, P.le A. Moro 5, 00185 Rome, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0995-0702","authenticated-orcid":false,"given":"Eugenio","family":"Fazio","sequence":"additional","affiliation":[{"name":"Department of Fundamental and Applied Sciences for Engineering, Sapienza Universit\u00e0 di Roma, via A. Scarpa 16, 00161 Roma, Italy"}]}],"member":"1968","published-online":{"date-parts":[[2022,1,13]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"2548","DOI":"10.1029\/2018MS001351","article-title":"Using Machine Learning to Parameterize Moist Convection: Potential for Modeling of Climate, Climate Change, and Extreme Events","volume":"10","author":"Dwyer","year":"2018","journal-title":"J. Adv. Model. Earth Syst."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"17071","DOI":"10.1007\/s00521-021-06299-7","article-title":"Supervised and Unsupervised learning using a fully-plastic all-optical unit of artificial intelligence based on solitonic waveguides","volume":"33","author":"Bile","year":"2021","journal-title":"Neural Comput. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"045222","DOI":"10.1063\/5.0040674","article-title":"Study of Magnetic Switch for Surface Plasmon Polariton Circuits","volume":"11","author":"Bile","year":"2021","journal-title":"AIP Adv."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Bishop, C. (1995). Neural Networks for Pattern Recognition, Oxford University Press.","DOI":"10.1093\/oso\/9780198538493.001.0001"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1016\/j.ifacol.2015.10.185","article-title":"Machine Learning for Predictive Modelling based on Small Data in Biomedical Engineering","volume":"48","author":"Shaikhina","year":"2015","journal-title":"IFAC-PapersOnLine"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"989","DOI":"10.1109\/72.329697","article-title":"Training Feedforward Networks with the Marquardt Algorithm","volume":"5","author":"Hagan","year":"1994","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_7","unstructured":"Hersbach, H., Bell, B., Berrisford, P., Biavati, G., Hor\u00e1nyi, A., Mu\u00f1oz Sabater, J., Nicolas, J., Peubey, C., Radu, R., and Rozum, I. (2018). ERA5 Hourly Data on Single Levels from 1979 to Present. Copernic. Clim. Chang. Serv. Clim. Data Store, 10."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1253","DOI":"10.1080\/23744731.2019.1642093","article-title":"A method based on environmental monitoring and building dynamic simulation to assess indoor climate control strategies in the preventive conservation within historical buildings","volume":"25","author":"Frasca","year":"2019","journal-title":"Sci. Technol. Built Environ."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Fazio, E., Bonacquisti, V., Di Michele, M., Frasca, F., Chianese, A., and Siani, A.M. (2017). CleAir Monitoring System for Particulate Matter: A Case in the Napoleonic Museum in Rome. Sensors, 17.","DOI":"10.3390\/s17092076"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"5155","DOI":"10.1109\/TIE.2015.2412519","article-title":"A control-oriented model of a PEM fuel cell stack based on NARX and NOE neural networks","volume":"62","author":"Watanabe","year":"2015","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_11","unstructured":"MathWorks (2020). MATLAB Deep Learning Toolbox Release 2020a, MathWorks."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.epsr.2012.04.009","article-title":"Application of SOM neural networks to short-term load forecasting: The Spanish electricity market case study","volume":"91","author":"Valero","year":"2012","journal-title":"Electr. Power Syst. Res."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1016\/j.apor.2018.10.016","article-title":"Wave prediction using wave rider position measurements and NARX network in wave energy conversion","volume":"82","author":"Desouky","year":"2019","journal-title":"Appl. Ocean Res."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Ruiz, L., Cu\u00e9llar, M., Calvo-Flores, M., and Jim\u00e9nez, M. (2016). An application of non-linear autoregressive neural networks to predict energy consumption in public buildings. Energies, 9.","DOI":"10.3390\/en9090684"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1137\/0111030","article-title":"An Algorithm for Least-Squares Estimation of Nonlinear Parameters","volume":"11","author":"Marquardt","year":"1963","journal-title":"J. Soc. Ind. Appl. Math."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1865","DOI":"10.1007\/s10040-013-1029-5","article-title":"Groundwater-level prediction using multiple linear regression and artificial neural network techniques: A comparative assessment","volume":"21","author":"Sahoo","year":"2013","journal-title":"Hydrogeol. J."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"6403081","DOI":"10.1155\/2019\/6403081","article-title":"A Comparative Study of Activation Functions of NAR and NARX Neural Networks for Long-Term Wind Speed Forecasting in Malaysia","volume":"2019","author":"Sarkar","year":"2019","journal-title":"Math. Probl. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Taherdangkoo, R., Tatomir, A., Taherdangkoo, M., Qiu, P., and Sauter, M. (2020). Nonlinear Autoregressive Neural Networks to Predict Hydraulic Fracturing Fluid Leakage into Shallow Groundwater. Water, 12.","DOI":"10.5194\/egusphere-egu2020-1536"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.fss.2004.09.015","article-title":"NARMAX time series model prediction: Feedforward and recurrent fuzzy neural network approaches","volume":"150","author":"Gao","year":"2005","journal-title":"Fuzzy Sets Syst."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"3625","DOI":"10.1016\/j.egypro.2009.02.158","article-title":"Numerical simulation of CO2 leakage through abandoned wells: Model for an abandoned site with observed gas migration in Alberta, Canada","volume":"1","author":"Pawar","year":"2009","journal-title":"Energy Procedia"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"306","DOI":"10.1016\/j.rser.2012.11.057","article-title":"Potential challenges of integrating large-scale wind energy into the power grid\u2014A review","volume":"20","author":"Shafullah","year":"2013","journal-title":"Renew. Sustain. Energy Rev."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"191","DOI":"10.1016\/j.renene.2021.02.103","article-title":"Ultra-short-term exogenous forecasting of photovoltaic power production using genetically optimized non-linear auto-regressive recurrent neural networks","volume":"171","author":"Hassan","year":"2021","journal-title":"Renew. Energy"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Di Nunno, F., de Marinis, G., Gargano, R., and Granata, F. (2021). Tide Prediction in the Venice Lagoon Using Nonlinear Autoregressive Exogenous (NARX) Neural Netowrk. Water, 13.","DOI":"10.3390\/w13091173"},{"key":"ref_24","first-page":"1329","article-title":"Learning long-term dependencies in NARX recurrent neural networks","volume":"10","author":"Lin","year":"1996","journal-title":"IEEE Trans. Neural Netw."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1118","DOI":"10.1017\/S0950268816003216","article-title":"Hybrid methodology for tuberculosis incidence time-series forecasting based on ARIMA and a NAR neural network","volume":"145","author":"Wang","year":"2017","journal-title":"Epidemiol. Infect."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"241","DOI":"10.1016\/j.renene.2011.06.023","article-title":"Multistep forecasting for wind speed using a modifed EMD-based artifcial neural network model","volume":"37","author":"Guo","year":"2012","journal-title":"J. Renew. Energy"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/2\/615\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T13:39:39Z","timestamp":1760362779000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/22\/2\/615"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,13]]},"references-count":26,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2022,1]]}},"alternative-id":["s22020615"],"URL":"https:\/\/doi.org\/10.3390\/s22020615","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,13]]}}}