Flow chart of the six hybrid ET models and a pure machine learning model using random forest (RF) algorithms.

<p>The model input variables include soil moisture (SM), vegetation water content (VegWC), fraction of photosynthetically active radiation (FPAR), air temperature (T), relative humidity (<i>RH</i>), CO<sub>2</sub> concentration (<i>CO</i><sub><i>...

وصف كامل

محفوظ في:
التفاصيل البيبلوغرافية
المؤلف الرئيسي: Yeonuk Kim (4589488) (author)
مؤلفون آخرون: Monica Garcia (5507180) (author), T. Andrew Black (1869484) (author), Mark S. Johnson (166934) (author)
منشور في: 2025
الموضوعات:
الوسوم: إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
_version_ 1852018261095350272
author Yeonuk Kim (4589488)
author2 Monica Garcia (5507180)
T. Andrew Black (1869484)
Mark S. Johnson (166934)
author2_role author
author
author
author_facet Yeonuk Kim (4589488)
Monica Garcia (5507180)
T. Andrew Black (1869484)
Mark S. Johnson (166934)
author_role author
dc.creator.none.fl_str_mv Yeonuk Kim (4589488)
Monica Garcia (5507180)
T. Andrew Black (1869484)
Mark S. Johnson (166934)
dc.date.none.fl_str_mv 2025-07-23T17:29:01Z
dc.identifier.none.fl_str_mv 10.1371/journal.pone.0328798.g002
dc.relation.none.fl_str_mv https://figshare.com/articles/figure/Flow_chart_of_the_six_hybrid_ET_models_and_a_pure_machine_learning_model_using_random_forest_RF_algorithms_/29628564
dc.rights.none.fl_str_mv CC BY 4.0
info:eu-repo/semantics/openAccess
dc.subject.none.fl_str_mv Biotechnology
Science Policy
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
tackle challenges inherent
situ meteorological data
satellite remote sensing
relatively stable due
random forest algorithm
novel empirical parameter
estimate terrestrial evapotranspiration
different physical formulations
conventional choices may
constrained evapotranspiration models
scale et observations
div >< p
accurate hybrid model
pure ml model
rmse ), indicating
pure machine learning
hybrid et models
hybrid models
et ),
model error
models employed
machine learning
hybrid approach
et estimates
well understood
study underscores
strong correlation
square error
results imply
mechanisms driving
learned parameters
key advantage
improves performance
improved performance
extreme conditions
domain knowledge
critical role
carbon cycles
atmosphere equilibrium
8 w
dc.title.none.fl_str_mv Flow chart of the six hybrid ET models and a pure machine learning model using random forest (RF) algorithms.
dc.type.none.fl_str_mv Image
Figure
info:eu-repo/semantics/publishedVersion
image
description <p>The model input variables include soil moisture (SM), vegetation water content (VegWC), fraction of photosynthetically active radiation (FPAR), air temperature (T), relative humidity (<i>RH</i>), CO<sub>2</sub> concentration (<i>CO</i><sub><i>2</i></sub>), aerodynamic conductance (<i>g</i><sub><i>aH</i></sub>), global radiation (<i>Rg</i>), and available energy (<i>AE</i>).</p>
eu_rights_str_mv openAccess
id Manara_7ae9f6bc2207d86d9a5a519ff2fd3fce
identifier_str_mv 10.1371/journal.pone.0328798.g002
network_acronym_str Manara
network_name_str ManaraRepo
oai_identifier_str oai:figshare.com:article/29628564
publishDate 2025
repository.mail.fl_str_mv
repository.name.fl_str_mv
repository_id_str
rights_invalid_str_mv CC BY 4.0
spelling Flow chart of the six hybrid ET models and a pure machine learning model using random forest (RF) algorithms.Yeonuk Kim (4589488)Monica Garcia (5507180)T. Andrew Black (1869484)Mark S. Johnson (166934)BiotechnologyScience PolicyEnvironmental Sciences not elsewhere classifiedBiological Sciences not elsewhere classifiedtackle challenges inherentsitu meteorological datasatellite remote sensingrelatively stable duerandom forest algorithmnovel empirical parameterestimate terrestrial evapotranspirationdifferent physical formulationsconventional choices mayconstrained evapotranspiration modelsscale et observationsdiv >< paccurate hybrid modelpure ml modelrmse ), indicatingpure machine learninghybrid et modelshybrid modelset ),model errormodels employedmachine learninghybrid approachet estimateswell understoodstudy underscoresstrong correlationsquare errorresults implymechanisms drivinglearned parameterskey advantageimproves performanceimproved performanceextreme conditionsdomain knowledgecritical rolecarbon cyclesatmosphere equilibrium8 w<p>The model input variables include soil moisture (SM), vegetation water content (VegWC), fraction of photosynthetically active radiation (FPAR), air temperature (T), relative humidity (<i>RH</i>), CO<sub>2</sub> concentration (<i>CO</i><sub><i>2</i></sub>), aerodynamic conductance (<i>g</i><sub><i>aH</i></sub>), global radiation (<i>Rg</i>), and available energy (<i>AE</i>).</p>2025-07-23T17:29:01ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0328798.g002https://figshare.com/articles/figure/Flow_chart_of_the_six_hybrid_ET_models_and_a_pure_machine_learning_model_using_random_forest_RF_algorithms_/29628564CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/296285642025-07-23T17:29:01Z
spellingShingle Flow chart of the six hybrid ET models and a pure machine learning model using random forest (RF) algorithms.
Yeonuk Kim (4589488)
Biotechnology
Science Policy
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
tackle challenges inherent
situ meteorological data
satellite remote sensing
relatively stable due
random forest algorithm
novel empirical parameter
estimate terrestrial evapotranspiration
different physical formulations
conventional choices may
constrained evapotranspiration models
scale et observations
div >< p
accurate hybrid model
pure ml model
rmse ), indicating
pure machine learning
hybrid et models
hybrid models
et ),
model error
models employed
machine learning
hybrid approach
et estimates
well understood
study underscores
strong correlation
square error
results imply
mechanisms driving
learned parameters
key advantage
improves performance
improved performance
extreme conditions
domain knowledge
critical role
carbon cycles
atmosphere equilibrium
8 w
status_str publishedVersion
title Flow chart of the six hybrid ET models and a pure machine learning model using random forest (RF) algorithms.
title_full Flow chart of the six hybrid ET models and a pure machine learning model using random forest (RF) algorithms.
title_fullStr Flow chart of the six hybrid ET models and a pure machine learning model using random forest (RF) algorithms.
title_full_unstemmed Flow chart of the six hybrid ET models and a pure machine learning model using random forest (RF) algorithms.
title_short Flow chart of the six hybrid ET models and a pure machine learning model using random forest (RF) algorithms.
title_sort Flow chart of the six hybrid ET models and a pure machine learning model using random forest (RF) algorithms.
topic Biotechnology
Science Policy
Environmental Sciences not elsewhere classified
Biological Sciences not elsewhere classified
tackle challenges inherent
situ meteorological data
satellite remote sensing
relatively stable due
random forest algorithm
novel empirical parameter
estimate terrestrial evapotranspiration
different physical formulations
conventional choices may
constrained evapotranspiration models
scale et observations
div >< p
accurate hybrid model
pure ml model
rmse ), indicating
pure machine learning
hybrid et models
hybrid models
et ),
model error
models employed
machine learning
hybrid approach
et estimates
well understood
study underscores
strong correlation
square error
results imply
mechanisms driving
learned parameters
key advantage
improves performance
improved performance
extreme conditions
domain knowledge
critical role
carbon cycles
atmosphere equilibrium
8 w