Hyperspectral-physiological based predictive model for transpiration in greenhouses under CO<sub>2</sub> enrichment

<p dir="ltr">Accurate prediction of transpiration in protected agricultural settings with CO<sub>2</sub> enrichment is of high importance for the deployment of precision irrigation. Several physical and mechanistic based models are deployed for the estimation of transpira...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Ikhlas Ghiat (16932564) (author)
مؤلفون آخرون: Rajesh Govindan (15468857) (author), Amine Bermak (1895947) (author), Yin Yang (35103) (author), Tareq Al-Ansari (9872268) (author)
منشور في: 2023
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1864513529550209024
author Ikhlas Ghiat (16932564)
author2 Rajesh Govindan (15468857)
Amine Bermak (1895947)
Yin Yang (35103)
Tareq Al-Ansari (9872268)
author2_role author
author
author
author
author_facet Ikhlas Ghiat (16932564)
Rajesh Govindan (15468857)
Amine Bermak (1895947)
Yin Yang (35103)
Tareq Al-Ansari (9872268)
author_role author
dc.creator.none.fl_str_mv Ikhlas Ghiat (16932564)
Rajesh Govindan (15468857)
Amine Bermak (1895947)
Yin Yang (35103)
Tareq Al-Ansari (9872268)
dc.date.none.fl_str_mv 2023-10-01T00:00:00Z
dc.identifier.none.fl_str_mv 10.1016/j.compag.2023.108255
dc.relation.none.fl_str_mv https://figshare.com/articles/journal_contribution/Hyperspectral-physiological_based_predictive_model_for_transpiration_in_greenhouses_under_CO_sub_2_sub_enrichment/25018817
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Agricultural, veterinary and food sciences
Agriculture, land and farm management
Information and computing sciences
Data management and data science
Machine learning
Transpiration
Greenhouse
Hyperspectral imaging
Vegetation index
Deep neural networks
Support vector machines
Extreme gradient boosting
Precision irrigation
dc.title.none.fl_str_mv Hyperspectral-physiological based predictive model for transpiration in greenhouses under CO<sub>2</sub> enrichment
dc.type.none.fl_str_mv Text
Journal contribution
info:eu-repo/semantics/publishedVersion
text
contribution to journal
description <p dir="ltr">Accurate prediction of transpiration in protected agricultural settings with CO<sub>2</sub> enrichment is of high importance for the deployment of precision irrigation. Several physical and mechanistic based models are deployed for the estimation of transpiration. However, these models may not accurately explain physiological interactions for greenhouse settings under CO<sub>2</sub> enrichment. Thus, it is necessary to build site-specific and microclimate-targeted models that can accurately estimate transpiration and irrigation water requirements. In this work, a data-driven predictive model is proposed for the estimation of short-term transpiration (mmol/m<sup>2</sup>.s) for cucumber crops grown in greenhouses with CO<sub>2</sub> enrichment. Three machine learning models were investigated for transpiration modelling and prediction: deep neural networks (DNN), extreme gradient boosting (XGBoost), and support vector machine regression (SVR). These predictive models assimilate microclimate, physiological and hyperspectral features with high temporal and spatial resolutions. The results demonstrated the inclusion of hyperspectral-based vegetation indices significantly increased the performance of the three machine learning models in predicting transpiration. The XGBoost model outperformed the DNN and SVR models with higher R<sup>2</sup> of 0.62 – 7.53%, lower RMSE and MAE values of 9.74 – 46.19 mmol/m<sup>2</sup>.s and 13.74 – 39.08 mmol/m<sup>2</sup>.s respectively with microclimate, physiological and hyperspectral based vegetation index inputs. Moreover, the time series prediction with different time steps improved the XGBoost model, achieving an R<sup>2</sup> of up to 99.0%. The XGBoost proved to be the most efficient in predicting transpiration for cucumbers grown in greenhouses under CO<sub>2</sub> enriched environments.</p><h2>Other Information</h2><p dir="ltr">Published in: Computers and Electronics in Agriculture<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.compag.2023.108255" target="_blank">https://dx.doi.org/10.1016/j.compag.2023.108255</a></p>
eu_rights_str_mv openAccess
id Manara2_70f6c0e92e24037e9f343a5eccd00b83
identifier_str_mv 10.1016/j.compag.2023.108255
network_acronym_str Manara2
network_name_str Manara2
oai_identifier_str oai:figshare.com:article/25018817
publishDate 2023
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Hyperspectral-physiological based predictive model for transpiration in greenhouses under CO<sub>2</sub> enrichmentIkhlas Ghiat (16932564)Rajesh Govindan (15468857)Amine Bermak (1895947)Yin Yang (35103)Tareq Al-Ansari (9872268)Agricultural, veterinary and food sciencesAgriculture, land and farm managementInformation and computing sciencesData management and data scienceMachine learningTranspirationGreenhouseHyperspectral imagingVegetation indexDeep neural networksSupport vector machinesExtreme gradient boostingPrecision irrigation<p dir="ltr">Accurate prediction of transpiration in protected agricultural settings with CO<sub>2</sub> enrichment is of high importance for the deployment of precision irrigation. Several physical and mechanistic based models are deployed for the estimation of transpiration. However, these models may not accurately explain physiological interactions for greenhouse settings under CO<sub>2</sub> enrichment. Thus, it is necessary to build site-specific and microclimate-targeted models that can accurately estimate transpiration and irrigation water requirements. In this work, a data-driven predictive model is proposed for the estimation of short-term transpiration (mmol/m<sup>2</sup>.s) for cucumber crops grown in greenhouses with CO<sub>2</sub> enrichment. Three machine learning models were investigated for transpiration modelling and prediction: deep neural networks (DNN), extreme gradient boosting (XGBoost), and support vector machine regression (SVR). These predictive models assimilate microclimate, physiological and hyperspectral features with high temporal and spatial resolutions. The results demonstrated the inclusion of hyperspectral-based vegetation indices significantly increased the performance of the three machine learning models in predicting transpiration. The XGBoost model outperformed the DNN and SVR models with higher R<sup>2</sup> of 0.62 – 7.53%, lower RMSE and MAE values of 9.74 – 46.19 mmol/m<sup>2</sup>.s and 13.74 – 39.08 mmol/m<sup>2</sup>.s respectively with microclimate, physiological and hyperspectral based vegetation index inputs. Moreover, the time series prediction with different time steps improved the XGBoost model, achieving an R<sup>2</sup> of up to 99.0%. The XGBoost proved to be the most efficient in predicting transpiration for cucumbers grown in greenhouses under CO<sub>2</sub> enriched environments.</p><h2>Other Information</h2><p dir="ltr">Published in: Computers and Electronics in Agriculture<br>License: <a href="http://creativecommons.org/licenses/by/4.0/" target="_blank">http://creativecommons.org/licenses/by/4.0/</a><br>See article on publisher's website: <a href="https://dx.doi.org/10.1016/j.compag.2023.108255" target="_blank">https://dx.doi.org/10.1016/j.compag.2023.108255</a></p>2023-10-01T00:00:00ZTextJournal contributioninfo:eu-repo/semantics/publishedVersiontextcontribution to journal10.1016/j.compag.2023.108255https://figshare.com/articles/journal_contribution/Hyperspectral-physiological_based_predictive_model_for_transpiration_in_greenhouses_under_CO_sub_2_sub_enrichment/25018817CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/250188172023-10-01T00:00:00Z
spellingShingle Hyperspectral-physiological based predictive model for transpiration in greenhouses under CO<sub>2</sub> enrichment
Ikhlas Ghiat (16932564)
Agricultural, veterinary and food sciences
Agriculture, land and farm management
Information and computing sciences
Data management and data science
Machine learning
Transpiration
Greenhouse
Hyperspectral imaging
Vegetation index
Deep neural networks
Support vector machines
Extreme gradient boosting
Precision irrigation
status_str publishedVersion
title Hyperspectral-physiological based predictive model for transpiration in greenhouses under CO<sub>2</sub> enrichment
title_full Hyperspectral-physiological based predictive model for transpiration in greenhouses under CO<sub>2</sub> enrichment
title_fullStr Hyperspectral-physiological based predictive model for transpiration in greenhouses under CO<sub>2</sub> enrichment
title_full_unstemmed Hyperspectral-physiological based predictive model for transpiration in greenhouses under CO<sub>2</sub> enrichment
title_short Hyperspectral-physiological based predictive model for transpiration in greenhouses under CO<sub>2</sub> enrichment
title_sort Hyperspectral-physiological based predictive model for transpiration in greenhouses under CO<sub>2</sub> enrichment
topic Agricultural, veterinary and food sciences
Agriculture, land and farm management
Information and computing sciences
Data management and data science
Machine learning
Transpiration
Greenhouse
Hyperspectral imaging
Vegetation index
Deep neural networks
Support vector machines
Extreme gradient boosting
Precision irrigation