Machine learning algorithms to assess the thermal behavior of a Moroccan agriculture greenhouse

The objective of this paper is to assess the potential of machine learning algorithms in predicting the indoor air temperature in a greenhouse using the outdoor data. A dataset gathering the main weather data and the indoor air temperature of a greenhouse located in Agadir, Morocco was used for this...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Amine Allouhi, Noureddine Choab, Abderrachid Hamrani, Said Saadeddine
Formato:	article
Lenguaje:	EN
Publicado:	Elsevier 2021
Materias:	Machine learning Regression Greenhouse Indoor temperature Prediction Renewable energy sources TJ807-830 Environmental engineering TA170-171
Acceso en línea:	https://doaj.org/article/15c44c42de524bafbca4b66a66fd668e
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:15c44c42de524bafbca4b66a66fd668e
record_format	dspace
spelling	oai:doaj.org-article:15c44c42de524bafbca4b66a66fd668e2021-12-04T04:36:26ZMachine learning algorithms to assess the thermal behavior of a Moroccan agriculture greenhouse2666-790810.1016/j.clet.2021.100346https://doaj.org/article/15c44c42de524bafbca4b66a66fd668e2021-12-01T00:00:00Zhttp://www.sciencedirect.com/science/article/pii/S2666790821003062https://doaj.org/toc/2666-7908The objective of this paper is to assess the potential of machine learning algorithms in predicting the indoor air temperature in a greenhouse using the outdoor data. A dataset gathering the main weather data and the indoor air temperature of a greenhouse located in Agadir, Morocco was used for this purpose. Machine learning models including support vector machine based-regression, ensemble trees and Gaussian process regression are compared against multiple linear regression models. This comparison was carried out on the basis of a 5-fold cross validation framework and across unseen data. The results show that all predictive models are capable of describing the indoor air temperature of the greenhouse and perform well (R2 > 0.9), with only 10% fraction of the dataset as training data. The Gaussian process regression outperforms all models, with R2 = 0.94 in the 5-fold cross validation test. However, the computational time related to the training of Gaussian process regression model is slightly higher than other machine learning models.Amine AllouhiNoureddine ChoabAbderrachid HamraniSaid SaadeddineElsevierarticleMachine learningRegressionGreenhouseIndoor temperaturePredictionRenewable energy sourcesTJ807-830Environmental engineeringTA170-171ENCleaner Engineering and Technology, Vol 5, Iss , Pp 100346- (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Machine learning Regression Greenhouse Indoor temperature Prediction Renewable energy sources TJ807-830 Environmental engineering TA170-171
spellingShingle	Machine learning Regression Greenhouse Indoor temperature Prediction Renewable energy sources TJ807-830 Environmental engineering TA170-171 Amine Allouhi Noureddine Choab Abderrachid Hamrani Said Saadeddine Machine learning algorithms to assess the thermal behavior of a Moroccan agriculture greenhouse
description	The objective of this paper is to assess the potential of machine learning algorithms in predicting the indoor air temperature in a greenhouse using the outdoor data. A dataset gathering the main weather data and the indoor air temperature of a greenhouse located in Agadir, Morocco was used for this purpose. Machine learning models including support vector machine based-regression, ensemble trees and Gaussian process regression are compared against multiple linear regression models. This comparison was carried out on the basis of a 5-fold cross validation framework and across unseen data. The results show that all predictive models are capable of describing the indoor air temperature of the greenhouse and perform well (R2 > 0.9), with only 10% fraction of the dataset as training data. The Gaussian process regression outperforms all models, with R2 = 0.94 in the 5-fold cross validation test. However, the computational time related to the training of Gaussian process regression model is slightly higher than other machine learning models.
format	article
author	Amine Allouhi Noureddine Choab Abderrachid Hamrani Said Saadeddine
author_facet	Amine Allouhi Noureddine Choab Abderrachid Hamrani Said Saadeddine
author_sort	Amine Allouhi
title	Machine learning algorithms to assess the thermal behavior of a Moroccan agriculture greenhouse
title_short	Machine learning algorithms to assess the thermal behavior of a Moroccan agriculture greenhouse
title_full	Machine learning algorithms to assess the thermal behavior of a Moroccan agriculture greenhouse
title_fullStr	Machine learning algorithms to assess the thermal behavior of a Moroccan agriculture greenhouse
title_full_unstemmed	Machine learning algorithms to assess the thermal behavior of a Moroccan agriculture greenhouse
title_sort	machine learning algorithms to assess the thermal behavior of a moroccan agriculture greenhouse
publisher	Elsevier
publishDate	2021
url	https://doaj.org/article/15c44c42de524bafbca4b66a66fd668e
work_keys_str_mv	AT amineallouhi machinelearningalgorithmstoassessthethermalbehaviorofamoroccanagriculturegreenhouse AT noureddinechoab machinelearningalgorithmstoassessthethermalbehaviorofamoroccanagriculturegreenhouse AT abderrachidhamrani machinelearningalgorithmstoassessthethermalbehaviorofamoroccanagriculturegreenhouse AT saidsaadeddine machinelearningalgorithmstoassessthethermalbehaviorofamoroccanagriculturegreenhouse
_version_	1718372895267225600

Machine learning algorithms to assess the thermal behavior of a Moroccan agriculture greenhouse

Ejemplares similares