Publicação

Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach

Ver documento

Detalhes bibliográficos
Resumo:Climate change is affecting global viticulture, increasing heatwaves and drought. Precision irrigation, supported by robust water status indicators (WSIs), is inevitable in most of the Mediterranean basin. One of the most reliable WSIs is the leaf water potential ((Formula presented.)), which is determined via an intrusive and time-consuming method. The aim of this work is to discern the most effective variables that are correlated with plants’ water status and identify the variables that better predict (Formula presented.). Five grapevine varieties grown in the Alentejo region (Portugal) were selected and subjected to three irrigation treatments, starting in 2018: full irrigation (FI), deficit irrigation (DI), and no irrigation (NI). Plant monitoring was performed in 2023. Measurements included stomatal conductance ((Formula presented.)), predawn water potential (Formula presented.), stem water potential ((Formula presented.)), thermal imaging, and meteorological data. The WSIs, namely (Formula presented.) and (Formula presented.), responded differently according to the irrigation treatment. (Formula presented.) measured at mid-morning (MM) and mid-day (MD) proved unable to discern between treatments. MM measurements presented the best correlations between WSIs. (Formula presented.) showed the best correlations between the other WSIs, and consequently the best predictive capability to estimate (Formula presented.). Machine learning regression models were trained on meteorological, thermal, and (Formula presented.) data to predict (Formula presented.), with ensemble models showing a great performance (ExtraTrees: (Formula presented.), (Formula presented.) ; Gradient Boosting: (Formula presented.) ; (Formula presented.)).
Autores principais:Damásio, Miguel
Outros Autores:Barbosa, Miguel; Deus, João; Fernandes, Eduardo; Leitão, André; Albino, Luís; Fonseca, Filipe; Silvestre, José
Assunto:modelling precision irrigation predawn leaf water potential Vitis vinifera water status indicators Ecology, Evolution, Behavior and Systematics Ecology Plant Science SDG 13 - Climate Action
Ano:2023
País:Portugal
Tipo de documento:artigo
Tipo de acesso:acesso aberto
Instituição associada:Universidade Nova de Lisboa
Idioma:inglês
Origem:Repositório Institucional da UNL
_version_ 1868983039493668864
author Damásio, Miguel
author2 Barbosa, Miguel
Deus, João
Fernandes, Eduardo
Leitão, André
Albino, Luís
Fonseca, Filipe
Silvestre, José
author2_role author
author
author
author
author
author
author
author_facet Damásio, Miguel
Barbosa, Miguel
Deus, João
Fernandes, Eduardo
Leitão, André
Albino, Luís
Fonseca, Filipe
Silvestre, José
author_role author
contributor_name_str_mv Bioresources 4 Sustainability (GREEN-IT)
MDPI - Multidisciplinary Digital Publishing Institute
RUN
country_str PT
creators_json_txt [{\"Person.name\":\"Damásio, Miguel\"},{\"Person.name\":\"Barbosa, Miguel\"},{\"Person.name\":\"Deus, João\"},{\"Person.name\":\"Fernandes, Eduardo\"},{\"Person.name\":\"Leitão, André\"},{\"Person.name\":\"Albino, Luís\"},{\"Person.name\":\"Fonseca, Filipe\"},{\"Person.name\":\"Silvestre, José\"}]
datacite.contributors.contributor.contributorName.fl_str_mv Bioresources 4 Sustainability (GREEN-IT)
MDPI - Multidisciplinary Digital Publishing Institute
RUN
datacite.creators.creator.creatorName.fl_str_mv Damásio, Miguel
Barbosa, Miguel
Deus, João
Fernandes, Eduardo
Leitão, André
Albino, Luís
Fonseca, Filipe
Silvestre, José
datacite.date.Accepted.fl_str_mv 2023-12-01T00:00:00Z
datacite.date.available.fl_str_mv 2024-04-02T23:46:48Z
datacite.date.embargoed.fl_str_mv 2024-04-02T23:46:48Z
datacite.rights.fl_str_mv http://purl.org/coar/access_right/c_abf2
datacite.subjects.subject.fl_str_mv modelling
precision irrigation
predawn leaf water potential
Vitis vinifera
water status indicators
Ecology, Evolution, Behavior and Systematics
Ecology
Plant Science
SDG 13 - Climate Action
datacite.titles.title.fl_str_mv Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
dc.contributor.none.fl_str_mv Bioresources 4 Sustainability (GREEN-IT)
MDPI - Multidisciplinary Digital Publishing Institute
RUN
dc.creator.none.fl_str_mv Damásio, Miguel
Barbosa, Miguel
Deus, João
Fernandes, Eduardo
Leitão, André
Albino, Luís
Fonseca, Filipe
Silvestre, José
dc.date.Accepted.fl_str_mv 2023-12-01T00:00:00Z
dc.date.available.fl_str_mv 2024-04-02T23:46:48Z
dc.date.embargoed.fl_str_mv 2024-04-02T23:46:48Z
dc.format.none.fl_str_mv application/pdf
dc.identifier.none.fl_str_mv http://hdl.handle.net/10362/165723
dc.language.none.fl_str_mv eng
dc.rights.none.fl_str_mv http://purl.org/coar/access_right/c_abf2
dc.subject.none.fl_str_mv modelling
precision irrigation
predawn leaf water potential
Vitis vinifera
water status indicators
Ecology, Evolution, Behavior and Systematics
Ecology
Plant Science
SDG 13 - Climate Action
dc.title.fl_str_mv Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
dc.type.none.fl_str_mv http://purl.org/coar/resource_type/c_6501
description Climate change is affecting global viticulture, increasing heatwaves and drought. Precision irrigation, supported by robust water status indicators (WSIs), is inevitable in most of the Mediterranean basin. One of the most reliable WSIs is the leaf water potential ((Formula presented.)), which is determined via an intrusive and time-consuming method. The aim of this work is to discern the most effective variables that are correlated with plants’ water status and identify the variables that better predict (Formula presented.). Five grapevine varieties grown in the Alentejo region (Portugal) were selected and subjected to three irrigation treatments, starting in 2018: full irrigation (FI), deficit irrigation (DI), and no irrigation (NI). Plant monitoring was performed in 2023. Measurements included stomatal conductance ((Formula presented.)), predawn water potential (Formula presented.), stem water potential ((Formula presented.)), thermal imaging, and meteorological data. The WSIs, namely (Formula presented.) and (Formula presented.), responded differently according to the irrigation treatment. (Formula presented.) measured at mid-morning (MM) and mid-day (MD) proved unable to discern between treatments. MM measurements presented the best correlations between WSIs. (Formula presented.) showed the best correlations between the other WSIs, and consequently the best predictive capability to estimate (Formula presented.). Machine learning regression models were trained on meteorological, thermal, and (Formula presented.) data to predict (Formula presented.), with ensemble models showing a great performance (ExtraTrees: (Formula presented.), (Formula presented.) ; Gradient Boosting: (Formula presented.) ; (Formula presented.)).
dirty 0
eu_rights_str_mv openAccess
format article
fulltext.url.fl_str_mv https://run.unl.pt/bitstreams/1e25b75c-11d6-4ab4-8b4a-44fbe9296f03/download
id run_b67af07401bbefa22292a67d8940ac21
identifier.url.fl_str_mv http://hdl.handle.net/10362/165723
inst_facet_str urn:organizationAcronym:unl{{{_:::_}}}Universidade Nova de Lisboa
instacron_str unl
institution Universidade Nova de Lisboa
instname_str Universidade Nova de Lisboa
language eng
network_acronym_str run
network_name_str Repositório Institucional da UNL
oai_identifier_str oai:run.unl.pt:10362/165723
organization_str_mv urn:organizationAcronym:unl
person_str_mv Damásio, Miguel
Barbosa, Miguel
Deus, João
Fernandes, Eduardo
Leitão, André
Albino, Luís
Fonseca, Filipe
Silvestre, José
publishDate 2023
repo_facet_str urn:repositoryAcronym:run{{{_:::_}}}Repositório Institucional da UNL
reponame_str Repositório Institucional da UNL
repository_id_str urn:repositoryAcronym:run
service_str_mv urn:repositoryAcronym:run
spelling engenClimate change is affecting global viticulture, increasing heatwaves and drought. Precision irrigation, supported by robust water status indicators (WSIs), is inevitable in most of the Mediterranean basin. One of the most reliable WSIs is the leaf water potential ((Formula presented.)), which is determined via an intrusive and time-consuming method. The aim of this work is to discern the most effective variables that are correlated with plants’ water status and identify the variables that better predict (Formula presented.). Five grapevine varieties grown in the Alentejo region (Portugal) were selected and subjected to three irrigation treatments, starting in 2018: full irrigation (FI), deficit irrigation (DI), and no irrigation (NI). Plant monitoring was performed in 2023. Measurements included stomatal conductance ((Formula presented.)), predawn water potential (Formula presented.), stem water potential ((Formula presented.)), thermal imaging, and meteorological data. The WSIs, namely (Formula presented.) and (Formula presented.), responded differently according to the irrigation treatment. (Formula presented.) measured at mid-morning (MM) and mid-day (MD) proved unable to discern between treatments. MM measurements presented the best correlations between WSIs. (Formula presented.) showed the best correlations between the other WSIs, and consequently the best predictive capability to estimate (Formula presented.). Machine learning regression models were trained on meteorological, thermal, and (Formula presented.) data to predict (Formula presented.), with ensemble models showing a great performance (ExtraTrees: (Formula presented.), (Formula presented.) ; Gradient Boosting: (Formula presented.) ; (Formula presented.)).application/pdfenCan Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning ApproachDamásio, MiguelBarbosa, MiguelDeus, JoãoFernandes, EduardoLeitão, AndréAlbino, LuísFonseca, FilipeSilvestre, JoséBioresources 4 Sustainability (GREEN-IT)MDPI - Multidisciplinary Digital Publishing InstituteHostingInstitutionOrganizationalRUNe-mailmailto:run@unl.ptrun@unl.ptISSNIsPartOf2223-7747URNIsPartOfPURE: 83537371URNIsPartOfPURE UUID: 4837d3f1-fe2e-45e8-b166-9a4018927200URNIsPartOfScopus: 85180671980DOIIsPartOf10.3390/plants122441422024-04-02T23:46:48Z2023-122023-12-01T00:00:00ZHandlehttp://hdl.handle.net/10362/165723http://purl.org/coar/access_right/c_abf2open accessmodellingprecision irrigationpredawn leaf water potentialVitis viniferawater status indicatorsEcology, Evolution, Behavior and SystematicsEcologyPlant ScienceSDG 13 - Climate Action2789023 bytesliteraturehttp://purl.org/coar/resource_type/c_6501journal articlehttp://purl.org/coar/access_right/c_abf2application/pdffulltexthttps://run.unl.pt/bitstreams/1e25b75c-11d6-4ab4-8b4a-44fbe9296f03/download
spellingShingle Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
Damásio, Miguel
modelling
precision irrigation
predawn leaf water potential
Vitis vinifera
water status indicators
Ecology, Evolution, Behavior and Systematics
Ecology
Plant Science
SDG 13 - Climate Action
status SINGLETON
subject.fl_str_mv modelling
precision irrigation
predawn leaf water potential
Vitis vinifera
water status indicators
Ecology, Evolution, Behavior and Systematics
Ecology
Plant Science
SDG 13 - Climate Action
title Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
title_full Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
title_fullStr Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
title_full_unstemmed Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
title_short Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
title_sort Can Grapevine Leaf Water Potential Be Modelled from Physiological and Meteorological Variables? A Machine Learning Approach
topic modelling
precision irrigation
predawn leaf water potential
Vitis vinifera
water status indicators
Ecology, Evolution, Behavior and Systematics
Ecology
Plant Science
SDG 13 - Climate Action
topic_facet modelling
precision irrigation
predawn leaf water potential
Vitis vinifera
water status indicators
Ecology, Evolution, Behavior and Systematics
Ecology
Plant Science
SDG 13 - Climate Action
url http://hdl.handle.net/10362/165723
visible 1