Academic Journal
Evaluation of Nonparametric Machine-Learning Algorithms for an Optimal Crop Classification Using Big Data Reduction Strategy
| العنوان: | Evaluation of Nonparametric Machine-Learning Algorithms for an Optimal Crop Classification Using Big Data Reduction Strategy |
|---|---|
| المؤلفون: | Al-Awar, B., Awad, M., Jarlan, L., Courault, D. |
| المساهمون: | Centre d'études spatiales de la biosphère (CESBIO), Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP), Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Environnement Méditerranéen et Modélisation des Agro-Hydrosystèmes (EMMAH), Avignon Université (AU)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE), Campus France Cedre project has participated to exchanges between research teams, springer, Campus France, ANR-17-NMED-0002,CHAAMS,Global Change: Assessment and Adaptation to Mediterranean Region Water Scarcity(2017) |
| المصدر: | ISSN: 2520-8195 ; Remote Sensing in Earth Systems Sciences ; https://hal.inrae.fr/hal-04225899 ; Remote Sensing in Earth Systems Sciences, 2022, 5, ⟨10.1007/s41976-022-00072-7⟩. |
| بيانات النشر: | HAL CCSD |
| سنة النشر: | 2022 |
| مصطلحات موضوعية: | Sentinel 2, supervised classification, machine learning, Sentinel 1, lebanon, agriculture, Nonparametric, [SDE]Environmental Sciences, [SDV]Life Sciences [q-bio] |
| الوصف: | International audience ; Accurate crop classification can support analyses of food security, environmental, and climate changes. Most of the current research studies have focused on applying available algorithms to classify dominant crops on the landscape using one source of remotely sensed data due to geoprocessing constraints (e.g., big data access, availability, and processing power). In this research, we compared four classification algorithms, including the support vector machine (SVM), random forest (RF), regression tree (CART), and backpropagation network (BPN), to select a robust and efficient classification algorithm able to classify accurately many crop types. We used multiple sources of satellite images such as Sentinel-1 (S1) and Sentinel-2 (S2) and developed a new cropping classification method for a study site in the Bekaa valley, Lebanon, fully implemented on Google Earth Engine Platform, which minimized those geoprocessing constraints. The algorithm selection was based on their popularity, availability, simplicity, similarity, and diversity. In addition, we adopted different strategies that included changing the number of crops. The first strategy is to reduce the number of collected S2 images thereafter S1; the second strategy is to use S2 images separately and then combining S2 and S1. This study results proved that the RF is the most robust algorithm for crop classification, showing the highest overall accuracy (OA) (95.4%) and a kappa index of 0.94, followed by BPN, SVM, and CART, respectively. The performance of these algorithms based on major crop types such as wheat or potato showed that CART is the highest with OA (98%) followed by RF, SVM, and BPN, respectively. Nevertheless, CART fails to classify other minor crop types. We concluded that RF is the best algorithm for classifying different crop types in the study area, using multiple remote sensing data sources. |
| نوع الوثيقة: | article in journal/newspaper |
| اللغة: | English |
| DOI: | 10.1007/s41976-022-00072-7 |
| الاتاحة: | https://hal.inrae.fr/hal-04225899 https://doi.org/10.1007/s41976-022-00072-7 |
| رقم الانضمام: | edsbas.A3E898CD |
| قاعدة البيانات: | BASE |
| ResultId |
1 |
|---|---|
| Header |
edsbas BASE edsbas.A3E898CD 868 3 Academic Journal academicJournal 867.599182128906 |
| PLink |
https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsbas&AN=edsbas.A3E898CD&custid=s6537998&authtype=sso |
| FullText |
Array
(
[Availability] => 0
)
Array ( [0] => Array ( [Url] => https://hal.inrae.fr/hal-04225899# [Name] => EDS - BASE [Category] => fullText [Text] => View record in BASE [MouseOverText] => View record in BASE ) ) |
| Items |
Array
(
[Name] => Title
[Label] => Title
[Group] => Ti
[Data] => Evaluation of Nonparametric Machine-Learning Algorithms for an Optimal Crop Classification Using Big Data Reduction Strategy
)
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Al-Awar%2C+B%2E%22">Al-Awar, B.</searchLink><br /><searchLink fieldCode="AR" term="%22Awad%2C+M%2E%22">Awad, M.</searchLink><br /><searchLink fieldCode="AR" term="%22Jarlan%2C+L%2E%22">Jarlan, L.</searchLink><br /><searchLink fieldCode="AR" term="%22Courault%2C+D%2E%22">Courault, D.</searchLink> ) Array ( [Name] => Author [Label] => Contributors [Group] => Au [Data] => Centre d'études spatiales de la biosphère (CESBIO)<br />Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3)<br />Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP)<br />Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)<br />Environnement Méditerranéen et Modélisation des Agro-Hydrosystèmes (EMMAH)<br />Avignon Université (AU)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)<br />Campus France Cedre project has participated to exchanges between research teams<br />springer<br />Campus France<br />ANR-17-NMED-0002,CHAAMS,Global Change: Assessment and Adaptation to Mediterranean Region Water Scarcity(2017) ) Array ( [Name] => TitleSource [Label] => Source [Group] => Src [Data] => <i>ISSN: 2520-8195 ; Remote Sensing in Earth Systems Sciences ; https://hal.inrae.fr/hal-04225899 ; Remote Sensing in Earth Systems Sciences, 2022, 5, ⟨10.1007/s41976-022-00072-7⟩</i>. ) Array ( [Name] => Publisher [Label] => Publisher Information [Group] => PubInfo [Data] => HAL CCSD ) Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2022 ) Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%22Sentinel+2%22">Sentinel 2</searchLink><br /><searchLink fieldCode="DE" term="%22supervised+classification%22">supervised classification</searchLink><br /><searchLink fieldCode="DE" term="%22machine+learning%22">machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22Sentinel+1%22">Sentinel 1</searchLink><br /><searchLink fieldCode="DE" term="%22lebanon%22">lebanon</searchLink><br /><searchLink fieldCode="DE" term="%22agriculture%22">agriculture</searchLink><br /><searchLink fieldCode="DE" term="%22Nonparametric%22">Nonparametric</searchLink><br /><searchLink fieldCode="DE" term="%22[SDE]Environmental+Sciences%22">[SDE]Environmental Sciences</searchLink><br /><searchLink fieldCode="DE" term="%22[SDV]Life+Sciences+[q-bio]%22">[SDV]Life Sciences [q-bio]</searchLink> ) Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => International audience ; Accurate crop classification can support analyses of food security, environmental, and climate changes. Most of the current research studies have focused on applying available algorithms to classify dominant crops on the landscape using one source of remotely sensed data due to geoprocessing constraints (e.g., big data access, availability, and processing power). In this research, we compared four classification algorithms, including the support vector machine (SVM), random forest (RF), regression tree (CART), and backpropagation network (BPN), to select a robust and efficient classification algorithm able to classify accurately many crop types. We used multiple sources of satellite images such as Sentinel-1 (S1) and Sentinel-2 (S2) and developed a new cropping classification method for a study site in the Bekaa valley, Lebanon, fully implemented on Google Earth Engine Platform, which minimized those geoprocessing constraints. The algorithm selection was based on their popularity, availability, simplicity, similarity, and diversity. In addition, we adopted different strategies that included changing the number of crops. The first strategy is to reduce the number of collected S2 images thereafter S1; the second strategy is to use S2 images separately and then combining S2 and S1. This study results proved that the RF is the most robust algorithm for crop classification, showing the highest overall accuracy (OA) (95.4%) and a kappa index of 0.94, followed by BPN, SVM, and CART, respectively. The performance of these algorithms based on major crop types such as wheat or potato showed that CART is the highest with OA (98%) followed by RF, SVM, and BPN, respectively. Nevertheless, CART fails to classify other minor crop types. We concluded that RF is the best algorithm for classifying different crop types in the study area, using multiple remote sensing data sources. ) Array ( [Name] => TypeDocument [Label] => Document Type [Group] => TypDoc [Data] => article in journal/newspaper ) Array ( [Name] => Language [Label] => Language [Group] => Lang [Data] => English ) Array ( [Name] => DOI [Label] => DOI [Group] => ID [Data] => 10.1007/s41976-022-00072-7 ) Array ( [Name] => URL [Label] => Availability [Group] => URL [Data] => https://hal.inrae.fr/hal-04225899<br />https://doi.org/10.1007/s41976-022-00072-7 ) Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsbas.A3E898CD ) |
| RecordInfo |
Array
(
[BibEntity] => Array
(
[Identifiers] => Array
(
[0] => Array
(
[Type] => doi
[Value] => 10.1007/s41976-022-00072-7
)
)
[Languages] => Array
(
[0] => Array
(
[Text] => English
)
)
[Subjects] => Array
(
[0] => Array
(
[SubjectFull] => Sentinel 2
[Type] => general
)
[1] => Array
(
[SubjectFull] => supervised classification
[Type] => general
)
[2] => Array
(
[SubjectFull] => machine learning
[Type] => general
)
[3] => Array
(
[SubjectFull] => Sentinel 1
[Type] => general
)
[4] => Array
(
[SubjectFull] => lebanon
[Type] => general
)
[5] => Array
(
[SubjectFull] => agriculture
[Type] => general
)
[6] => Array
(
[SubjectFull] => Nonparametric
[Type] => general
)
[7] => Array
(
[SubjectFull] => [SDE]Environmental Sciences
[Type] => general
)
[8] => Array
(
[SubjectFull] => [SDV]Life Sciences [q-bio]
[Type] => general
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => Evaluation of Nonparametric Machine-Learning Algorithms for an Optimal Crop Classification Using Big Data Reduction Strategy
[Type] => main
)
)
)
[BibRelationships] => Array
(
[HasContributorRelationships] => Array
(
[0] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Al-Awar, B.
)
)
)
[1] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Awad, M.
)
)
)
[2] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Jarlan, L.
)
)
)
[3] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Courault, D.
)
)
)
[4] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Centre d'études spatiales de la biosphère (CESBIO)
)
)
)
[5] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Institut de Recherche pour le Développement (IRD)-Université Toulouse III - Paul Sabatier (UT3)
)
)
)
[6] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Observatoire Midi-Pyrénées (OMP)
)
)
)
[7] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Université de Toulouse (UT)-Université de Toulouse (UT)-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Institut national des sciences de l'Univers (INSU - CNRS)-Centre National d'Études Spatiales Toulouse (CNES)-Centre National de la Recherche Scientifique (CNRS)-Météo-France-Centre National de la Recherche Scientifique (CNRS)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)
)
)
)
[8] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Environnement Méditerranéen et Modélisation des Agro-Hydrosystèmes (EMMAH)
)
)
)
[9] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Avignon Université (AU)-Institut National de Recherche pour l’Agriculture, l’Alimentation et l’Environnement (INRAE)
)
)
)
[10] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Campus France Cedre project has participated to exchanges between research teams
)
)
)
[11] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => springer
)
)
)
[12] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => Campus France
)
)
)
[13] => Array
(
[PersonEntity] => Array
(
[Name] => Array
(
[NameFull] => ANR-17-NMED-0002,CHAAMS,Global Change: Assessment and Adaptation to Mediterranean Region Water Scarcity(2017)
)
)
)
)
[IsPartOfRelationships] => Array
(
[0] => Array
(
[BibEntity] => Array
(
[Dates] => Array
(
[0] => Array
(
[D] => 01
[M] => 01
[Type] => published
[Y] => 2022
)
)
[Identifiers] => Array
(
[0] => Array
(
[Type] => issn-locals
[Value] => edsbas
)
)
[Titles] => Array
(
[0] => Array
(
[TitleFull] => ISSN: 2520-8195 ; Remote Sensing in Earth Systems Sciences ; https://hal.inrae.fr/hal-04225899 ; Remote Sensing in Earth Systems Sciences, 2022, 5, ⟨10.1007/s41976-022-00072-7⟩
[Type] => main
)
)
)
)
)
)
)
|
| IllustrationInfo |