أعرض في EDS

Comparison of machine learning algorithms for mapping mango plantations based on Gaofen-1 imagery

التفاصيل البيبلوغرافية
العنوان: Comparison of machine learning algorithms for mapping mango plantations based on Gaofen-1 imagery
المؤلفون: Xiao-ping Yi, Mao-fen Li, Qian Zheng, Hong-xia Luo, Sheng-pei Dai, Ying-ying Hu, Enping Liu
المصدر: Journal of Integrative Agriculture, Vol 19, Iss 11, Pp 2815-2828 (2020)
بيانات النشر: Elsevier BV, 2020.
سنة النشر: 2020
مصطلحات موضوعية: 0106 biological sciences, SVM, Agriculture (General), Plant Science, Machine learning, computer.software_genre, 01 natural sciences, Biochemistry, S1-972, Food Animals, Feature (machine learning), Mathematics, Ecology, Rural economy, Pixel, business.industry, Homogeneity (statistics), 04 agricultural and veterinary sciences, Variance (accounting), Vegetation, Random forest, Support vector machine, mango plantations, 040103 agronomy & agriculture, RF, 0401 agriculture, forestry, and fisheries, Animal Science and Zoology, Artificial intelligence, business, Agronomy and Crop Science, computer, Algorithm, GLCM texture, GF-1, 010606 plant biology & botany, Food Science
الوصف: Mango is a commercial crop on Hainan Island, China, that is cultivated to develop the tropical rural economy. The development of accurate and up-to-date maps of the spatial distribution of mango plantations is necessary for agricultural monitoring and decision management by the local government. Pixel-based and object-oriented image analysis methods for mapping mango plantations were compared using two machine learning algorithms (support vector machine (SVM) and Random Forest (RF)) based on Chinese high-resolution Gaofen-1 (GF-1) imagery in parts of Hainan Island. To assess the importance of different features on classification accuracy, a combined layer of four original bands, 32 gray-level co-occurrence (GLCM) texture indices, and 10 vegetation indices were used as input features. Then five different sets of variables (5, 10, 20, and 30 input variables and all 46 variables) were classified with the two machine learning algorithms at object-based level. Results of the feature optimization suggested that homogeneity and variance were very important variables for distinguishing mango plantations patches. The object-based classifiers could significantly improve overall accuracy between 2–7% when compared to pixel-based classifiers. When there were 5 and 10 input variables, SVM showed higher classification accuracy than RF, and when the input variables exceeded 20, RF showed better performances. After the accuracy achieved saturation points, there were only slightly classification accuracy improvements along with the numbers of feature increases for both of SVM and RF classifiers. The results indicated that GF-1 imagery can be successfully applied to mango plantation mapping in tropical regions, which would provide a useful framework for accurate tropical agriculture land management.
تدمد: 2095-3119
DOI: 10.1016/s2095-3119(20)63208-7
URL الوصول: https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5181ee78628d18b5e0c360200894ec58
https://doi.org/10.1016/s2095-3119(20)63208-7
Rights: OPEN
رقم الانضمام: edsair.doi.dedup.....5181ee78628d18b5e0c360200894ec58
قاعدة البيانات: OpenAIRE
ResultId 1
Header edsair
OpenAIRE
edsair.doi.dedup.....5181ee78628d18b5e0c360200894ec58
870
3

unknown
869.749389648438
PLink https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsair&AN=edsair.doi.dedup.....5181ee78628d18b5e0c360200894ec58&custid=s6537998&authtype=sso
FullText Array ( [Availability] => 0 )
Array ( [0] => Array ( [Url] => https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5181ee78628d18b5e0c360200894ec58# [Name] => EDS - OpenAIRE [Category] => fullText [Text] => View record in OpenAIRE [MouseOverText] => View record in OpenAIRE ) )
Items Array ( [Name] => Title [Label] => Title [Group] => Ti [Data] => Comparison of machine learning algorithms for mapping mango plantations based on Gaofen-1 imagery )
Array ( [Name] => Author [Label] => Authors [Group] => Au [Data] => <searchLink fieldCode="AR" term="%22Xiao-ping+Yi%22">Xiao-ping Yi</searchLink><br /><searchLink fieldCode="AR" term="%22Mao-fen+Li%22">Mao-fen Li</searchLink><br /><searchLink fieldCode="AR" term="%22Qian+Zheng%22">Qian Zheng</searchLink><br /><searchLink fieldCode="AR" term="%22Hong-xia+Luo%22">Hong-xia Luo</searchLink><br /><searchLink fieldCode="AR" term="%22Sheng-pei+Dai%22">Sheng-pei Dai</searchLink><br /><searchLink fieldCode="AR" term="%22Ying-ying+Hu%22">Ying-ying Hu</searchLink><br /><searchLink fieldCode="AR" term="%22Enping+Liu%22">Enping Liu</searchLink> )
Array ( [Name] => TitleSource [Label] => Source [Group] => Src [Data] => Journal of Integrative Agriculture, Vol 19, Iss 11, Pp 2815-2828 (2020) )
Array ( [Name] => Publisher [Label] => Publisher Information [Group] => PubInfo [Data] => Elsevier BV, 2020. )
Array ( [Name] => DatePubCY [Label] => Publication Year [Group] => Date [Data] => 2020 )
Array ( [Name] => Subject [Label] => Subject Terms [Group] => Su [Data] => <searchLink fieldCode="DE" term="%220106+biological+sciences%22">0106 biological sciences</searchLink><br /><searchLink fieldCode="DE" term="%22SVM%22">SVM</searchLink><br /><searchLink fieldCode="DE" term="%22Agriculture+%28General%29%22">Agriculture (General)</searchLink><br /><searchLink fieldCode="DE" term="%22Plant+Science%22">Plant Science</searchLink><br /><searchLink fieldCode="DE" term="%22Machine+learning%22">Machine learning</searchLink><br /><searchLink fieldCode="DE" term="%22computer%2Esoftware%5Fgenre%22">computer.software_genre</searchLink><br /><searchLink fieldCode="DE" term="%2201+natural+sciences%22">01 natural sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Biochemistry%22">Biochemistry</searchLink><br /><searchLink fieldCode="DE" term="%22S1-972%22">S1-972</searchLink><br /><searchLink fieldCode="DE" term="%22Food+Animals%22">Food Animals</searchLink><br /><searchLink fieldCode="DE" term="%22Feature+%28machine+learning%29%22">Feature (machine learning)</searchLink><br /><searchLink fieldCode="DE" term="%22Mathematics%22">Mathematics</searchLink><br /><searchLink fieldCode="DE" term="%22Ecology%22">Ecology</searchLink><br /><searchLink fieldCode="DE" term="%22Rural+economy%22">Rural economy</searchLink><br /><searchLink fieldCode="DE" term="%22Pixel%22">Pixel</searchLink><br /><searchLink fieldCode="DE" term="%22business%2Eindustry%22">business.industry</searchLink><br /><searchLink fieldCode="DE" term="%22Homogeneity+%28statistics%29%22">Homogeneity (statistics)</searchLink><br /><searchLink fieldCode="DE" term="%2204+agricultural+and+veterinary+sciences%22">04 agricultural and veterinary sciences</searchLink><br /><searchLink fieldCode="DE" term="%22Variance+%28accounting%29%22">Variance (accounting)</searchLink><br /><searchLink fieldCode="DE" term="%22Vegetation%22">Vegetation</searchLink><br /><searchLink fieldCode="DE" term="%22Random+forest%22">Random forest</searchLink><br /><searchLink fieldCode="DE" term="%22Support+vector+machine%22">Support vector machine</searchLink><br /><searchLink fieldCode="DE" term="%22mango+plantations%22">mango plantations</searchLink><br /><searchLink fieldCode="DE" term="%22040103+agronomy+%26+agriculture%22">040103 agronomy & agriculture</searchLink><br /><searchLink fieldCode="DE" term="%22RF%22">RF</searchLink><br /><searchLink fieldCode="DE" term="%220401+agriculture%2C+forestry%2C+and+fisheries%22">0401 agriculture, forestry, and fisheries</searchLink><br /><searchLink fieldCode="DE" term="%22Animal+Science+and+Zoology%22">Animal Science and Zoology</searchLink><br /><searchLink fieldCode="DE" term="%22Artificial+intelligence%22">Artificial intelligence</searchLink><br /><searchLink fieldCode="DE" term="%22business%22">business</searchLink><br /><searchLink fieldCode="DE" term="%22Agronomy+and+Crop+Science%22">Agronomy and Crop Science</searchLink><br /><searchLink fieldCode="DE" term="%22computer%22">computer</searchLink><br /><searchLink fieldCode="DE" term="%22Algorithm%22">Algorithm</searchLink><br /><searchLink fieldCode="DE" term="%22GLCM+texture%22">GLCM texture</searchLink><br /><searchLink fieldCode="DE" term="%22GF-1%22">GF-1</searchLink><br /><searchLink fieldCode="DE" term="%22010606+plant+biology+%26+botany%22">010606 plant biology & botany</searchLink><br /><searchLink fieldCode="DE" term="%22Food+Science%22">Food Science</searchLink> )
Array ( [Name] => Abstract [Label] => Description [Group] => Ab [Data] => Mango is a commercial crop on Hainan Island, China, that is cultivated to develop the tropical rural economy. The development of accurate and up-to-date maps of the spatial distribution of mango plantations is necessary for agricultural monitoring and decision management by the local government. Pixel-based and object-oriented image analysis methods for mapping mango plantations were compared using two machine learning algorithms (support vector machine (SVM) and Random Forest (RF)) based on Chinese high-resolution Gaofen-1 (GF-1) imagery in parts of Hainan Island. To assess the importance of different features on classification accuracy, a combined layer of four original bands, 32 gray-level co-occurrence (GLCM) texture indices, and 10 vegetation indices were used as input features. Then five different sets of variables (5, 10, 20, and 30 input variables and all 46 variables) were classified with the two machine learning algorithms at object-based level. Results of the feature optimization suggested that homogeneity and variance were very important variables for distinguishing mango plantations patches. The object-based classifiers could significantly improve overall accuracy between 2–7% when compared to pixel-based classifiers. When there were 5 and 10 input variables, SVM showed higher classification accuracy than RF, and when the input variables exceeded 20, RF showed better performances. After the accuracy achieved saturation points, there were only slightly classification accuracy improvements along with the numbers of feature increases for both of SVM and RF classifiers. The results indicated that GF-1 imagery can be successfully applied to mango plantation mapping in tropical regions, which would provide a useful framework for accurate tropical agriculture land management. )
Array ( [Name] => ISSN [Label] => ISSN [Group] => ISSN [Data] => 2095-3119 )
Array ( [Name] => DOI [Label] => DOI [Group] => ID [Data] => 10.1016/s2095-3119(20)63208-7 )
Array ( [Name] => URL [Label] => Access URL [Group] => URL [Data] => <link linkTarget="URL" linkTerm="https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5181ee78628d18b5e0c360200894ec58" linkWindow="_blank">https://explore.openaire.eu/search/publication?articleId=doi_dedup___::5181ee78628d18b5e0c360200894ec58</link><br /><link linkTarget="URL" linkTerm="https://doi.org/10.1016/s2095-3119(20)63208-7" linkWindow="_blank">https://doi.org/10.1016/s2095-3119(20)63208-7</link> )
Array ( [Name] => Copyright [Label] => Rights [Group] => Cpyrght [Data] => OPEN )
Array ( [Name] => AN [Label] => Accession Number [Group] => ID [Data] => edsair.doi.dedup.....5181ee78628d18b5e0c360200894ec58 )
RecordInfo Array ( [BibEntity] => Array ( [Identifiers] => Array ( [0] => Array ( [Type] => doi [Value] => 10.1016/s2095-3119(20)63208-7 ) ) [Languages] => Array ( [0] => Array ( [Text] => Undetermined ) ) [PhysicalDescription] => Array ( [Pagination] => Array ( [PageCount] => 14 [StartPage] => 2815 ) ) [Subjects] => Array ( [0] => Array ( [SubjectFull] => 0106 biological sciences [Type] => general ) [1] => Array ( [SubjectFull] => SVM [Type] => general ) [2] => Array ( [SubjectFull] => Agriculture (General) [Type] => general ) [3] => Array ( [SubjectFull] => Plant Science [Type] => general ) [4] => Array ( [SubjectFull] => Machine learning [Type] => general ) [5] => Array ( [SubjectFull] => computer.software_genre [Type] => general ) [6] => Array ( [SubjectFull] => 01 natural sciences [Type] => general ) [7] => Array ( [SubjectFull] => Biochemistry [Type] => general ) [8] => Array ( [SubjectFull] => S1-972 [Type] => general ) [9] => Array ( [SubjectFull] => Food Animals [Type] => general ) [10] => Array ( [SubjectFull] => Feature (machine learning) [Type] => general ) [11] => Array ( [SubjectFull] => Mathematics [Type] => general ) [12] => Array ( [SubjectFull] => Ecology [Type] => general ) [13] => Array ( [SubjectFull] => Rural economy [Type] => general ) [14] => Array ( [SubjectFull] => Pixel [Type] => general ) [15] => Array ( [SubjectFull] => business.industry [Type] => general ) [16] => Array ( [SubjectFull] => Homogeneity (statistics) [Type] => general ) [17] => Array ( [SubjectFull] => 04 agricultural and veterinary sciences [Type] => general ) [18] => Array ( [SubjectFull] => Variance (accounting) [Type] => general ) [19] => Array ( [SubjectFull] => Vegetation [Type] => general ) [20] => Array ( [SubjectFull] => Random forest [Type] => general ) [21] => Array ( [SubjectFull] => Support vector machine [Type] => general ) [22] => Array ( [SubjectFull] => mango plantations [Type] => general ) [23] => Array ( [SubjectFull] => 040103 agronomy & agriculture [Type] => general ) [24] => Array ( [SubjectFull] => RF [Type] => general ) [25] => Array ( [SubjectFull] => 0401 agriculture, forestry, and fisheries [Type] => general ) [26] => Array ( [SubjectFull] => Animal Science and Zoology [Type] => general ) [27] => Array ( [SubjectFull] => Artificial intelligence [Type] => general ) [28] => Array ( [SubjectFull] => business [Type] => general ) [29] => Array ( [SubjectFull] => Agronomy and Crop Science [Type] => general ) [30] => Array ( [SubjectFull] => computer [Type] => general ) [31] => Array ( [SubjectFull] => Algorithm [Type] => general ) [32] => Array ( [SubjectFull] => GLCM texture [Type] => general ) [33] => Array ( [SubjectFull] => GF-1 [Type] => general ) [34] => Array ( [SubjectFull] => 010606 plant biology & botany [Type] => general ) [35] => Array ( [SubjectFull] => Food Science [Type] => general ) ) [Titles] => Array ( [0] => Array ( [TitleFull] => Comparison of machine learning algorithms for mapping mango plantations based on Gaofen-1 imagery [Type] => main ) ) ) [BibRelationships] => Array ( [HasContributorRelationships] => Array ( [0] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Xiao-ping Yi ) ) ) [1] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Mao-fen Li ) ) ) [2] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Qian Zheng ) ) ) [3] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Hong-xia Luo ) ) ) [4] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Sheng-pei Dai ) ) ) [5] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Ying-ying Hu ) ) ) [6] => Array ( [PersonEntity] => Array ( [Name] => Array ( [NameFull] => Enping Liu ) ) ) ) [IsPartOfRelationships] => Array ( [0] => Array ( [BibEntity] => Array ( [Dates] => Array ( [0] => Array ( [D] => 01 [M] => 11 [Type] => published [Y] => 2020 ) ) [Identifiers] => Array ( [0] => Array ( [Type] => issn-print [Value] => 20953119 ) [1] => Array ( [Type] => issn-locals [Value] => edsair ) [2] => Array ( [Type] => issn-locals [Value] => edsairFT ) ) [Numbering] => Array ( [0] => Array ( [Type] => volume [Value] => 19 ) ) [Titles] => Array ( [0] => Array ( [TitleFull] => Journal of Integrative Agriculture [Type] => main ) ) ) ) ) ) )
IllustrationInfo