{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T06:10:52Z","timestamp":1774332652104,"version":"3.50.1"},"reference-count":44,"publisher":"Walter de Gruyter GmbH","issue":"6","license":[{"start":{"date-parts":[[2025,5,28]],"date-time":"2025-05-28T00:00:00Z","timestamp":1748390400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,26]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>A controller for the air temperature and relative humidity of a greenhouse is presented that relies only on the efficient exploitation of natural ventilation. Due to the difficulty of modeling greenhouse climate from first principles, Neural Predictive Control (NPC) is chosen, which combines the advantages of learning with Model Predictive Control (MPC) under constraints. Feedforward Neural Networks (NNs) are used to obtain a predictive model and a simulation model for the complex nonlinear dynamics of the temperature and humidity inside a greenhouse. The NNs are trained and validated with an 81-day dataset recorded in a Mediterranean greenhouse. The MPC approach applies operational constraints to compute the optimal vent opening. It minimizes temperature and humidity tracking errors, limits control increments to reduce motor wear, and enforces soft bounds on greenhouse temperature and humidity. Hard constraints include vent saturation and a wind speed limit for safety. The NPC strategy was evaluated in simulation with real weather, featuring both sunny and windy conditions. The results show small validation errors of the NNs. The tracking error in the control approach in situations without saturated input is below 3\u202fK and in 81\u2009% of the time the humidity is within the bounds. The presented data-driven control approach is attractive for controller design as data availability in greenhouses is expected to increase in the coming years.<\/jats:p>","DOI":"10.1515\/auto-2024-0163","type":"journal-article","created":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T20:52:17Z","timestamp":1748638337000},"page":"451-465","source":"Crossref","is-referenced-by-count":4,"title":["Learning-based model identification for greenhouse climate control"],"prefix":"10.1515","volume":"73","author":[{"given":"Michael","family":"Fink","sequence":"first","affiliation":[{"name":"Chair for Automatic Control at the Technical University of Munich , Munich , Germany"}]},{"given":"Annalena","family":"Daniels","sequence":"additional","affiliation":[{"name":"Chair for Automatic Control at the Technical University of Munich , Munich , Germany"}]},{"given":"Francisco","family":"Garc\u00eda-Ma\u00f1as","sequence":"additional","affiliation":[{"name":"Department of Informatics , University of Almer\u00eda , CIESOL, ceiA3, 04120 , Almer\u00eda , Spain"}]},{"given":"Francisco","family":"Rodr\u00edguez","sequence":"additional","affiliation":[{"name":"Department of Informatics , University of Almer\u00eda , CIESOL, ceiA3, 04120 , Almer\u00eda , Spain"}]},{"given":"Marion","family":"Leibold","sequence":"additional","affiliation":[{"name":"Chair for Automatic Control at the Technical University of Munich , Munich , Germany"}]},{"given":"Dirk","family":"Wollherr","sequence":"additional","affiliation":[{"name":"Chair for Automatic Control at the Technical University of Munich , Munich , Germany"}]}],"member":"374","published-online":{"date-parts":[[2025,5,28]]},"reference":[{"key":"2025053020521296811_j_auto-2024-0163_ref_001","doi-asserted-by":"crossref","unstructured":"F. Rodr\u00edguez, et al.., Modeling and Control of Greenhouse Crop Growth, Cham, Switzerland, Springer, 2015.","DOI":"10.1007\/978-3-319-11134-6"},{"key":"2025053020521296811_j_auto-2024-0163_ref_002","doi-asserted-by":"crossref","unstructured":"O. K\u00f6rner and H. Challa, \u201cProcess-based humidity control regime for greenhouse crops,\u201d Comput. Electron. Agric., vol.\u00a039, no.\u00a03, pp.\u00a0173\u2013192, 2003, https:\/\/doi.org\/10.1016\/S0168-1699(03)00079-6.","DOI":"10.1016\/S0168-1699(03)00079-6"},{"key":"2025053020521296811_j_auto-2024-0163_ref_003","doi-asserted-by":"crossref","unstructured":"J. P\u00e9rez Parra, et al.., \u201cNatural ventilation of parral greenhouses,\u201d Biosyst. Eng., vol.\u00a087, no.\u00a03, pp.\u00a0355\u2013366, 2004, https:\/\/doi.org\/10.1016\/j.biosystemseng.2003.12.004.","DOI":"10.1016\/j.biosystemseng.2003.12.004"},{"key":"2025053020521296811_j_auto-2024-0163_ref_004","doi-asserted-by":"crossref","unstructured":"C. Kittas, T. Boulard, and G. Papadakis, \u201cNatural ventilation of a greenhouse with ridge and side openings: sensitivity to temperature and wind effects,\u201d Trans. ASME, vol.\u00a040, no.\u00a02, pp.\u00a0415\u2013425, 1997.","DOI":"10.13031\/2013.21268"},{"key":"2025053020521296811_j_auto-2024-0163_ref_005","doi-asserted-by":"crossref","unstructured":"G. Van Straten, et al.., Optimal Control of Greenhouse Cultivation, New York, CRC Press, 2010.","DOI":"10.1201\/b10321"},{"key":"2025053020521296811_j_auto-2024-0163_ref_006","doi-asserted-by":"crossref","unstructured":"M. Zhang, et al.., \u201cEnergy-saving design and control strategy towards modern sustainable greenhouse: a review,\u201d Renew. Sustain. Energy Rev., vol.\u00a0164, p.\u00a0112602, 2022, https:\/\/doi.org\/10.1016\/j.rser.2022.112602.","DOI":"10.1016\/j.rser.2022.112602"},{"key":"2025053020521296811_j_auto-2024-0163_ref_007","doi-asserted-by":"crossref","unstructured":"F. Rodr\u00edguez, M. Berenguel, and M. Arahal, \u201cFeedforward controllers for greenhouse climate control based on physical models,\u201d in 2001 European Control Conference (ECC), Porto, IEEE, 2001, pp. 2158\u20132163.","DOI":"10.23919\/ECC.2001.7076243"},{"key":"2025053020521296811_j_auto-2024-0163_ref_008","doi-asserted-by":"crossref","unstructured":"A. Montoya-R\u00edos, et al.., \u201cSimple tuning rules for feedforward compensators applied to greenhouse daytime temperature control using natural ventilation,\u201d Agronomy, vol.\u00a010, no.\u00a09, p.\u00a01327, 2020, https:\/\/doi.org\/10.3390\/agronomy10091327.","DOI":"10.3390\/agronomy10091327"},{"key":"2025053020521296811_j_auto-2024-0163_ref_009","doi-asserted-by":"crossref","unstructured":"A. Daniels, M. Fink, and D. Wollherr, \u201cHierarchical model-based irrigation control for vertical farms,\u201d IFAC-PapersOnLine, vol.\u00a058, no.\u00a07, pp.\u00a0472\u2013477, 2024, https:\/\/doi.org\/10.1016\/j.ifacol.2024.08.107.","DOI":"10.1016\/j.ifacol.2024.08.107"},{"key":"2025053020521296811_j_auto-2024-0163_ref_010","doi-asserted-by":"crossref","unstructured":"P. Davis, \u201cA technique of adaptive control of the temperature in a greenhouse using ventilator adjustments,\u201d J. Agric. Eng. Res., vol.\u00a029, no.\u00a03, pp.\u00a0241\u2013248, 1984, https:\/\/doi.org\/10.1016\/0021-8634(84)90101-X.","DOI":"10.1016\/0021-8634(84)90101-X"},{"key":"2025053020521296811_j_auto-2024-0163_ref_011","doi-asserted-by":"crossref","unstructured":"F. Rodr\u00edguez, et al.., \u201cAdaptive hierarchical control of greenhouse crop production,\u201d Int. J. Adapt. Control Signal Process., vol.\u00a022, no.\u00a02, pp.\u00a0180\u2013197, 2008, https:\/\/doi.org\/10.1002\/acs.974.","DOI":"10.1002\/acs.974"},{"key":"2025053020521296811_j_auto-2024-0163_ref_012","doi-asserted-by":"crossref","unstructured":"F. Garc\u00eda-Ma\u00f1as, et al.., \u201cAdaptive PI control of temperature with natural ventilation in greenhouses using a bat algorithm variant,\u201d IFAC-PapersOnLine, vol.\u00a058, no.\u00a07, pp.\u00a0491\u2013496, 2024, https:\/\/doi.org\/10.1016\/j.ifacol.2024.08.110.","DOI":"10.1016\/j.ifacol.2024.08.110"},{"key":"2025053020521296811_j_auto-2024-0163_ref_013","doi-asserted-by":"crossref","unstructured":"R. Liu, et al.., \u201cSelective temperature and humidity control strategy for a Chinese solar greenhouse with an event-based approach,\u201d Revista Iberoamericana de Autom\u00e1tica e Inform\u00e1tica Industrial, vol.\u00a020, no.\u00a02, pp.\u00a0150\u2013161, 2022, https:\/\/doi.org\/10.4995\/riai.2022.18119.","DOI":"10.4995\/riai.2022.18119"},{"key":"2025053020521296811_j_auto-2024-0163_ref_014","doi-asserted-by":"crossref","unstructured":"Y. Su, L. Xu, and D. Li, \u201cAdaptive fuzzy control of a class of MIMO nonlinear system with actuator saturation for greenhouse climate control problem,\u201d IEEE Trans. Autom. Sci. Eng., vol.\u00a013, no.\u00a02, pp.\u00a0772\u2013788, 2016, https:\/\/doi.org\/10.1109\/TASE.2015.2392161.","DOI":"10.1109\/TASE.2015.2392161"},{"key":"2025053020521296811_j_auto-2024-0163_ref_015","doi-asserted-by":"crossref","unstructured":"G. Pasgianos, et al.., \u201cA nonlinear feedback technique for greenhouse environmental control,\u201d Comput. Electron. Agric., vol.\u00a040, no.\u00a01, pp.\u00a0153\u2013177, 2003, https:\/\/doi.org\/10.1016\/S0168-1699(03)00018-8.","DOI":"10.1016\/S0168-1699(03)00018-8"},{"key":"2025053020521296811_j_auto-2024-0163_ref_016","doi-asserted-by":"crossref","unstructured":"M. Berenguel, et al.., \u201cNonlinear PID-based temperature control techniques in greenhouses using natural ventilation,\u201d IFAC-PapersOnLine, vol.\u00a058, no.\u00a07, pp.\u00a0454\u2013459, 2024, https:\/\/doi.org\/10.1016\/j.ifacol.2024.08.104.","DOI":"10.1016\/j.ifacol.2024.08.104"},{"key":"2025053020521296811_j_auto-2024-0163_ref_017","doi-asserted-by":"crossref","unstructured":"M. El Ghoumari, H.-J. Tantau, and J. Serrano, \u201cNon-linear constrained MPC: real-time implementation of greenhouse air temperature control,\u201d Comput. Electron. Agric., vol.\u00a049, no.\u00a03, pp.\u00a0345\u2013356, 2005, https:\/\/doi.org\/10.1016\/j.compag.2005.08.005.","DOI":"10.1016\/j.compag.2005.08.005"},{"key":"2025053020521296811_j_auto-2024-0163_ref_018","doi-asserted-by":"crossref","unstructured":"J. Gruber, et al.., \u201cNonlinear MPC based on a Volterra series model for greenhouse temperature control using natural ventilation,\u201d Control Eng. Pract., vol.\u00a019, no.\u00a04, pp.\u00a0354\u2013366, 2011, https:\/\/doi.org\/10.1016\/j.conengprac.2010.12.004.","DOI":"10.1016\/j.conengprac.2010.12.004"},{"key":"2025053020521296811_j_auto-2024-0163_ref_019","doi-asserted-by":"crossref","unstructured":"K. Ito and T. Tabei, \u201cModel predictive temperature and humidity control of greenhouse with ventilation,\u201d Procedia Comput. Sci., vol.\u00a0192, pp.\u00a0212\u2013221, 2021, https:\/\/doi.org\/10.1016\/j.procs.2021.08.022.","DOI":"10.1016\/j.procs.2021.08.022"},{"key":"2025053020521296811_j_auto-2024-0163_ref_020","doi-asserted-by":"crossref","unstructured":"M. Guesbaya, et al.., \u201cReal-time adaptation of a greenhouse microclimate model using an online parameter estimator based on a bat algorithm variant,\u201d Comput. Electron. Agric., vol.\u00a0192, p.\u00a0106627, 2022, https:\/\/doi.org\/10.1016\/j.compag.2021.106627.","DOI":"10.1016\/j.compag.2021.106627"},{"key":"2025053020521296811_j_auto-2024-0163_ref_021","doi-asserted-by":"crossref","unstructured":"L. Hewing, et al.., \u201cLearning-based model predictive control: toward safe learning in control,\u201d Ann. Rev. Control, Rob., Autonom. Syst., vol.\u00a03, no.\u00a01, pp.\u00a0269\u2013296, 2020, https:\/\/doi.org\/10.1146\/annurev-control-090419-075625.","DOI":"10.1146\/annurev-control-090419-075625"},{"key":"2025053020521296811_j_auto-2024-0163_ref_022","doi-asserted-by":"crossref","unstructured":"T. Salzmann, et al.., \u201cReal-time neural MPC: deep learning model predictive control for quadrotors and agile robotic platforms,\u201d IEEE Rob. Autom. Lett., vol.\u00a08, no.\u00a04, pp.\u00a02397\u20132404, 2023, https:\/\/doi.org\/10.1109\/LRA.2023.3246839.","DOI":"10.1109\/LRA.2023.3246839"},{"key":"2025053020521296811_j_auto-2024-0163_ref_023","doi-asserted-by":"crossref","unstructured":"W.-H. Chen and F. You, \u201cSemiclosed greenhouse climate control under uncertainty via machine learning and data-driven robust model predictive control,\u201d IEEE Trans. Control Syst. Technol., vol.\u00a030, no.\u00a03, pp.\u00a01186\u20131197, 2022, https:\/\/doi.org\/10.1109\/TCST.2021.3094999.","DOI":"10.1109\/TCST.2021.3094999"},{"key":"2025053020521296811_j_auto-2024-0163_ref_024","doi-asserted-by":"crossref","unstructured":"L. Kerkhof and T. Keviczky, \u201cPredictive control of autonomous greenhouses: a data-driven approach,\u201d in 2021 European Control Conference (ECC), Delft, IEEE, 2021, pp. 1229\u20131235.","DOI":"10.23919\/ECC54610.2021.9655228"},{"key":"2025053020521296811_j_auto-2024-0163_ref_025","doi-asserted-by":"crossref","unstructured":"A. Manonmani, et al.., \u201cModelling and control of greenhouse system using neural networks,\u201d Trans. Inst. Meas. Control, vol.\u00a040, no.\u00a03, pp.\u00a0918\u2013929, 2018, https:\/\/doi.org\/10.1177\/0142331216670235.","DOI":"10.1177\/0142331216670235"},{"key":"2025053020521296811_j_auto-2024-0163_ref_026","doi-asserted-by":"crossref","unstructured":"D.-H. Jung, et al.., \u201cModel predictive control via output feedback neural network for improved multi-window greenhouse ventilation control,\u201d Sensors, vol.\u00a020, no.\u00a06, p.\u00a01756, 2020, https:\/\/doi.org\/10.3390\/s20061756.","DOI":"10.3390\/s20061756"},{"key":"2025053020521296811_j_auto-2024-0163_ref_027","doi-asserted-by":"crossref","unstructured":"F. Mahmood, et al.., \u201cData-driven robust model predictive control for greenhouse temperature control and energy utilisation assessment,\u201d Appl. Energy, vol.\u00a0343, p.\u00a0121190, 2023, https:\/\/doi.org\/10.1016\/j.apenergy.2023.121190.","DOI":"10.1016\/j.apenergy.2023.121190"},{"key":"2025053020521296811_j_auto-2024-0163_ref_028","doi-asserted-by":"crossref","unstructured":"C. Maraveas, et al.., \u201cApplications of IoT for optimized greenhouse environment and resources management,\u201d Comput. Electron. Agric., vol.\u00a0198, p.\u00a0106993, 2022, https:\/\/doi.org\/10.1016\/j.compag.2022.106993.","DOI":"10.1016\/j.compag.2022.106993"},{"key":"2025053020521296811_j_auto-2024-0163_ref_029","doi-asserted-by":"crossref","unstructured":"M. Farooq, et al.., \u201cInternet of things in greenhouse agriculture: a survey on enabling technologies, applications, and protocols,\u201d IEEE Access, vol.\u00a010, pp.\u00a053374\u201353397, 2022, https:\/\/doi.org\/10.1109\/ACCESS.2022.3166634.","DOI":"10.1109\/ACCESS.2022.3166634"},{"key":"2025053020521296811_j_auto-2024-0163_ref_030","doi-asserted-by":"crossref","unstructured":"H. Li, et al.., \u201cTowards automated greenhouse: a state of the art review on greenhouse monitoring methods and technologies based on Internet of Things,\u201d in Computers and Electronics in Agriculture, vol. 191, Amsterdam, Elsevier, 2021, p. 106558.","DOI":"10.1016\/j.compag.2021.106558"},{"key":"2025053020521296811_j_auto-2024-0163_ref_031","doi-asserted-by":"crossref","unstructured":"S. J. Pan and Q. Yang, \u201cA survey on transfer learning,\u201d IEEE Trans. Knowl. Data Eng., vol.\u00a022, no.\u00a010, pp.\u00a01345\u20131359, 2009, https:\/\/doi.org\/10.1109\/tkde.2009.191.","DOI":"10.1109\/TKDE.2009.191"},{"key":"2025053020521296811_j_auto-2024-0163_ref_032","unstructured":"C. V. Nguyen, et al.., \u201cVariational continual learning,\u201d arXiv preprint arXiv:1710.10628, 2017."},{"key":"2025053020521296811_j_auto-2024-0163_ref_033","doi-asserted-by":"crossref","unstructured":"L. Gr\u00fcne, \u201cNominal model-predictive control,\u201d in Encyclopedia of Systems and Control, J. Baillieul and T. Samad, Ed., London, Springer London, 2013, pp.\u00a01\u201310.","DOI":"10.1007\/978-1-4471-5102-9_1-1"},{"key":"2025053020521296811_j_auto-2024-0163_ref_034","unstructured":"R. Kohavi, \u201cA study of cross-validation and bootstrap for accuracy estimation and model selection,\u201d in Morgan Kaufman Publishing, Montreal, IJCAI Organization, 1995."},{"key":"2025053020521296811_j_auto-2024-0163_ref_035","doi-asserted-by":"crossref","unstructured":"N. A. Spielberg, M. Brown, and J. C. Gerdes, \u201cNeural network model predictive motion control applied to automated driving with unknown friction,\u201d IEEE Trans. Control Syst. Technol., vol.\u00a030, no.\u00a05, pp.\u00a01934\u20131945, 2022, https:\/\/doi.org\/10.1109\/TCST.2021.3130225.","DOI":"10.1109\/TCST.2021.3130225"},{"key":"2025053020521296811_j_auto-2024-0163_ref_036","unstructured":"P. Kamp and G. J. Timmerman, Computerized Environmental Control in Greenhouses: A Step by Step Approach, Ede, Ball Pub, 1996."},{"key":"2025053020521296811_j_auto-2024-0163_ref_037","unstructured":"N. Srivastava, et al.., \u201cDropout: a simple way to prevent neural networks from overfitting,\u201d J. Mach. Learn. Res., vol.\u00a015, no.\u00a01, pp.\u00a01929\u20131958, 2014."},{"key":"2025053020521296811_j_auto-2024-0163_ref_038","unstructured":"D. P. Kingma, \u201cAdam: a method for stochastic optimization,\u201d arXiv preprint arXiv:1412.6980, 2014."},{"key":"2025053020521296811_j_auto-2024-0163_ref_039","doi-asserted-by":"crossref","unstructured":"T. Akiba, et al.., \u201cOptuna: a next-generation hyperparameter optimization framework,\u201d in Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Ithaca, NY, arXiv, 2019, pp. 2623\u20132631.","DOI":"10.1145\/3292500.3330701"},{"key":"2025053020521296811_j_auto-2024-0163_ref_040","unstructured":"A. Paszke, et al.., \u201cPyTorch: an imperative style, high-performance deep learning library,\u201d in Advances in Neural Information Processing Systems 32, Vancouver, Curran Associates, Inc., 2019, pp. 8024\u20138035."},{"key":"2025053020521296811_j_auto-2024-0163_ref_041","doi-asserted-by":"crossref","unstructured":"J. Andersson, et al.., \u201cCasADi: a software framework for nonlinear optimization and optimal control,\u201d Math. Program. Comput., vol.\u00a011, no.\u00a01, pp.\u00a01\u201336, 2019, https:\/\/doi.org\/10.1007\/s12532-018-0139-4.","DOI":"10.1007\/s12532-018-0139-4"},{"key":"2025053020521296811_j_auto-2024-0163_ref_042","unstructured":"T. Salzmann, et al.., \u201cLearning for CasADi: data-driven models in numerical optimization,\u201d in Proceedings of the 6th Annual Learning for Dynamics & Control Conference, vol. 242, A. Abate, Ed., et al.., Oxford, PMLR, 2024, pp. 541\u2013553."},{"key":"2025053020521296811_j_auto-2024-0163_ref_043","doi-asserted-by":"crossref","unstructured":"A. Daniels, et al.., \u201cOptimal control for indoor vertical farms based on crop growth,\u201d IFAC-PapersOnLine, vol.\u00a056, no.\u00a02, pp.\u00a09887\u20139893, 2023, https:\/\/doi.org\/10.1016\/j.ifacol.2023.10.666.","DOI":"10.1016\/j.ifacol.2023.10.666"},{"key":"2025053020521296811_j_auto-2024-0163_ref_044","doi-asserted-by":"crossref","unstructured":"M. Fink, et al.., \u201cComparison of dynamic tomato growth models for optimal control in greenhouses,\u201d in 2023 IEEE International Conference on Agrosystem Engineering, Technology & Applications (AGRETA), Kuala Lumpur, IEEE, 2023, pp. 28\u201333.","DOI":"10.1109\/AGRETA57740.2023.10262422"}],"container-title":["at - Automatisierungstechnik"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/auto-2024-0163\/xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/auto-2024-0163\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T20:52:54Z","timestamp":1748638374000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.degruyterbrill.com\/document\/doi\/10.1515\/auto-2024-0163\/html"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,28]]},"references-count":44,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,5,29]]},"published-print":{"date-parts":[[2025,6,26]]}},"alternative-id":["10.1515\/auto-2024-0163"],"URL":"https:\/\/doi.org\/10.1515\/auto-2024-0163","relation":{},"ISSN":["0178-2312","2196-677X"],"issn-type":[{"value":"0178-2312","type":"print"},{"value":"2196-677X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,28]]}}}