Bridging data gaps in smart greenhouses: Outdoor-to-indoor mapping for synthetic climate forecasting

[EN] In order to make reliable forecasts of greenhouse climate variables, it is often necessary to have a long history of indoor sensor data, but newly constructed facilities often lack such records. In contrast, multi-year outdoor weather series are usually available. This paper introduces a two-st...

ver descrição completa

Detalhes bibliográficos
Autores: Bonastre-Egea, Juan, Bueno-Crespo, Andres, Morales-García, Juan, Casino-Sánchez, Virginia, Cecilia-Canales, José María|||0000-0001-5648-214X
Formato: artículo
Fecha de publicación:2026
País:España
Recursos:Universitat Politècnica de València (UPV)
Repositorio:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
Idioma:inglés
OAI Identifier:oai:dnet:riunet______::83c138444de483a37459f35322d74419
Acesso em linha:https://riunet.upv.es/handle/10251/234583
Access Level:acceso abierto
Palavra-chave:Smart agriculture
Smart greenhouses
Climate control systems
Data-driven modeling
Multi-model deep learning
id ES_45d1f237b1d7c64d24bf1687f5373766
oai_identifier_str oai:dnet:riunet______::83c138444de483a37459f35322d74419
network_acronym_str ES
network_name_str España
repository_id_str
spelling Bridging data gaps in smart greenhouses: Outdoor-to-indoor mapping for synthetic climate forecastingBonastre-Egea, JuanBueno-Crespo, AndresMorales-García, JuanCasino-Sánchez, VirginiaCecilia-Canales, José María|||0000-0001-5648-214XSmart agricultureSmart greenhousesClimate control systemsData-driven modelingMulti-model deep learning[EN] In order to make reliable forecasts of greenhouse climate variables, it is often necessary to have a long history of indoor sensor data, but newly constructed facilities often lack such records. In contrast, multi-year outdoor weather series are usually available. This paper introduces a two-stage deep learning pipeline to address this data scarcity. First, outdoor-to-indoor mapping models are trained to translate outdoor measurements of temperature, humidity, and radiation into synthetic indoor series. Secondly, these synthetic indoor series are used to train prediction models, which are then compared with their counterparts trained with real indoor data. Experiments conducted on six greenhouses across four countries with six deep learning architectures demonstrate that synthetic indoor climate series, generated from weather records, can effectively substitute for missing sensor histories. This approach enables the rapid deployment of forecasting systems in data-limited greenhouses and provides a practical AIoT strategy to mitigate information gaps in precision agriculture.This work was supported by the SERGIoT project (CPP2023-010458) , funded by MICIU/AEI/10.13039/501100011033 (Spain) and the European Union through FEDER; the SATRAI project (CIGE/2024/199), funded by the Conselleria de Educacion, Cultura, Universidades y Empleo (Generalitat Valenciana); and the AM-DS project (INREED/2024/1 and INREED/2024/7), funded by the Conselleria de Innovacion, Industria, Comercio y Turismo (Generalitat Valenciana) through the GVANEXT programme and the European Union through NextGenerationEU/PRTR.ElsevierDepartamento de Informática de Sistemas y ComputadoresEscuela Técnica Superior de Ingeniería InformáticaGrupo de Redes de ComputadoresEuropean CommissionGeneralitat ValencianaAgencia Estatal de InvestigaciónEuropean Regional Development FundRepositorio Institucional de la Universitat Politècnica de València Riunet20262026-06-01journal articlehttp://purl.org/coar/resource_type/c_6501VoRhttp://purl.org/coar/version/c_970fb48d4fbd8a85info:eu-repo/semantics/articleapplication/pdfhttps://riunet.upv.es/handle/10251/234583reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valénciainstname:Universitat Politècnica de València (UPV)InglésengAgencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 CPP2023-010458 Diseño de una estrategia de gemelos digitales para la gestión eficiente de invernaderos (SERGIoT)European Commission https://doi.org/10.13039/501100000780 INREED%2F2024%2F1European Commission https://doi.org/10.13039/501100000780 INREED%2F2024%2F7Generalitat Valenciana https://doi.org/10.13039/501100003359 CIGE%2F2024%2F199open accesshttp://purl.org/coar/access_right/c_abf2Reconocimiento (by)http://creativecommons.org/licenses/by/4.0/info:eu-repo/semantics/openAccessoai:dnet:riunet______::83c138444de483a37459f35322d744192026-06-13T07:49:27Z
dc.title.none.fl_str_mv Bridging data gaps in smart greenhouses: Outdoor-to-indoor mapping for synthetic climate forecasting
title Bridging data gaps in smart greenhouses: Outdoor-to-indoor mapping for synthetic climate forecasting
spellingShingle Bridging data gaps in smart greenhouses: Outdoor-to-indoor mapping for synthetic climate forecasting
Bonastre-Egea, Juan
Smart agriculture
Smart greenhouses
Climate control systems
Data-driven modeling
Multi-model deep learning
title_short Bridging data gaps in smart greenhouses: Outdoor-to-indoor mapping for synthetic climate forecasting
title_full Bridging data gaps in smart greenhouses: Outdoor-to-indoor mapping for synthetic climate forecasting
title_fullStr Bridging data gaps in smart greenhouses: Outdoor-to-indoor mapping for synthetic climate forecasting
title_full_unstemmed Bridging data gaps in smart greenhouses: Outdoor-to-indoor mapping for synthetic climate forecasting
title_sort Bridging data gaps in smart greenhouses: Outdoor-to-indoor mapping for synthetic climate forecasting
dc.creator.none.fl_str_mv Bonastre-Egea, Juan
Bueno-Crespo, Andres
Morales-García, Juan
Casino-Sánchez, Virginia
Cecilia-Canales, José María|||0000-0001-5648-214X
author Bonastre-Egea, Juan
author_facet Bonastre-Egea, Juan
Bueno-Crespo, Andres
Morales-García, Juan
Casino-Sánchez, Virginia
Cecilia-Canales, José María|||0000-0001-5648-214X
author_role author
author2 Bueno-Crespo, Andres
Morales-García, Juan
Casino-Sánchez, Virginia
Cecilia-Canales, José María|||0000-0001-5648-214X
author2_role author
author
author
author
dc.contributor.none.fl_str_mv Departamento de Informática de Sistemas y Computadores
Escuela Técnica Superior de Ingeniería Informática
Grupo de Redes de Computadores
European Commission
Generalitat Valenciana
Agencia Estatal de Investigación
European Regional Development Fund
Repositorio Institucional de la Universitat Politècnica de València Riunet
dc.subject.none.fl_str_mv Smart agriculture
Smart greenhouses
Climate control systems
Data-driven modeling
Multi-model deep learning
topic Smart agriculture
Smart greenhouses
Climate control systems
Data-driven modeling
Multi-model deep learning
description [EN] In order to make reliable forecasts of greenhouse climate variables, it is often necessary to have a long history of indoor sensor data, but newly constructed facilities often lack such records. In contrast, multi-year outdoor weather series are usually available. This paper introduces a two-stage deep learning pipeline to address this data scarcity. First, outdoor-to-indoor mapping models are trained to translate outdoor measurements of temperature, humidity, and radiation into synthetic indoor series. Secondly, these synthetic indoor series are used to train prediction models, which are then compared with their counterparts trained with real indoor data. Experiments conducted on six greenhouses across four countries with six deep learning architectures demonstrate that synthetic indoor climate series, generated from weather records, can effectively substitute for missing sensor histories. This approach enables the rapid deployment of forecasting systems in data-limited greenhouses and provides a practical AIoT strategy to mitigate information gaps in precision agriculture.
publishDate 2026
dc.date.none.fl_str_mv 2026
2026-06-01
dc.type.none.fl_str_mv journal article
http://purl.org/coar/resource_type/c_6501
VoR
http://purl.org/coar/version/c_970fb48d4fbd8a85
dc.type.openaire.fl_str_mv info:eu-repo/semantics/article
format article
dc.identifier.none.fl_str_mv https://riunet.upv.es/handle/10251/234583
url https://riunet.upv.es/handle/10251/234583
dc.language.none.fl_str_mv Inglés
eng
language_invalid_str_mv Inglés
language eng
dc.relation.none.fl_str_mv Agencia Estatal de Investigación http://dx.doi.org/10.13039/501100011033 Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023 CPP2023-010458 Diseño de una estrategia de gemelos digitales para la gestión eficiente de invernaderos (SERGIoT)
European Commission https://doi.org/10.13039/501100000780 INREED%2F2024%2F1
European Commission https://doi.org/10.13039/501100000780 INREED%2F2024%2F7
Generalitat Valenciana https://doi.org/10.13039/501100003359 CIGE%2F2024%2F199
dc.rights.none.fl_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reconocimiento (by)
http://creativecommons.org/licenses/by/4.0/
dc.rights.openaire.fl_str_mv info:eu-repo/semantics/openAccess
rights_invalid_str_mv open access
http://purl.org/coar/access_right/c_abf2
Reconocimiento (by)
http://creativecommons.org/licenses/by/4.0/
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Elsevier
publisher.none.fl_str_mv Elsevier
dc.source.none.fl_str_mv reponame:RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
instname:Universitat Politècnica de València (UPV)
instname_str Universitat Politècnica de València (UPV)
reponame_str RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
collection RiuNet. Repositorio Institucional de la Universitat Politécnica de Valéncia
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869407186695749632
score 15.198674

Registos relacionados