干旱区生态环境知识资源中心(Arid): Reducing the effects of vegetation phenology on change detection in tropical seasonal biomes

Arid

DOI	10.1080/15481603.2018.1550245
	Reducing the effects of vegetation phenology on change detection in tropical seasonal biomes
	de Oliveira Silveira, Eduarda Martiniano 1; Espirito-Santo, Fernando Del Bon 2; Acerbi-Junior, Fausto Weimar 1; Galvao, Lenio Soares 3; Withey, Kieran Daniel 4; Blackburn, George Alan 4; de Mello, Jose Marcio 1; Shimabukuro, Yosio Edemir 3; Domingues, Tomas 5; Soares Scolforo, Jose Roberto 1
通讯作者	de Oliveira Silveira, Eduarda Martiniano
来源期刊	GISCIENCE & REMOTE SENSING
ISSN	1548-1603
EISSN	1943-7226
出版年	2019
卷号	56 期号:5 页码:699-717
英文摘要	Tropical seasonal biomes (TSBs), such as the savannas (Cerrado) and semi-arid woodlands (Caatinga) of Brazil, are vulnerable ecosystems to human-induced disturbances. Remote sensing can detect disturbances such as deforestation and fires, but the analysis of change detection in TSBs is affected by seasonal modifications in vegetation indices due to phenology. To reduce the effects of vegetation phenology on changes caused by deforestation and fires, we developed a novel object-based change detection method. The approach combines both the spatial and spectral domains of the normalized difference vegetation index (NDVI), using a pair of Operational Land Imager (OLI)/Landsat-8 images acquired in 2015 and 2016. We used semivariogram indices (SIs) as spatial features and descriptive statistics as spectral features (SFs). We tested the performance of the method using three machine-learning algorithms: support vector machine (SVM), artificial neural network (ANN) and random forest (RF). The results showed that the combination of spatial and spectral information improved change detection by correctly classifying areas with seasonal changes in NDVI caused by vegetation phenology and areas with NDVI changes caused by human-induced disturbances. The use of semivariogram indices reduced the effects of vegetation phenology on change detection. The performance of the classifiers was generally comparable, but the SVM presented the highest overall classification accuracy (92.27%) when using the hybrid set of NDVI-derived spectral-spatial features. From the vegetated areas, 18.71% of changes were caused by human-induced disturbances between 2015 and 2016. The method is particularly useful for TSBs where vegetation exhibits strong seasonality and regularly spaced time series of satellite images are difficult to obtain due to persistent cloud cover.
英文关键词	remote sensing geostatistics seasonality LULCC
类型	Article
语种	英语
国家	Brazil ; England
开放获取类型	Green Accepted
收录类别	SCI-E
WOS记录号	WOS:000467394600003
WOS关键词	LANDSAT TIME-SERIES ; IMAGE CLASSIFICATION ; FOREST DISTURBANCE ; BRAZILIAN CERRADO ; ALGORITHMS ; CAATINGA ; MACHINE ; AREA ; SEMIVARIOGRAMS ; DEFORESTATION
WOS类目	Geography, Physical ; Remote Sensing
WOS研究方向	Physical Geography ; Remote Sensing
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/216056
作者单位	1.Fed Univ Lavras UFLA, Forest Sci Dept, BR-3037 Lavras, Brazil; 2.Univ Leicester, Sch Geog Geol & Environm, Leicester LE1 7RH, Leics, England; 3.Natl Inst Space Res INPE, Remote Sensing Dept, BR-3037 Sao Jose Dos Campos, Brazil; 4.Univ Lancaster, LEC, Lancaster LA1 4YQ, England; 5.Univ Sao Paulo, FFCLRP, Biol Dept, Ribeirao Preto, Brazil
推荐引用方式 GB/T 7714	de Oliveira Silveira, Eduarda Martiniano,Espirito-Santo, Fernando Del Bon,Acerbi-Junior, Fausto Weimar,et al. Reducing the effects of vegetation phenology on change detection in tropical seasonal biomes[J],2019,56(5):699-717.
APA	de Oliveira Silveira, Eduarda Martiniano.,Espirito-Santo, Fernando Del Bon.,Acerbi-Junior, Fausto Weimar.,Galvao, Lenio Soares.,Withey, Kieran Daniel.,...&Soares Scolforo, Jose Roberto.(2019).Reducing the effects of vegetation phenology on change detection in tropical seasonal biomes.GISCIENCE & REMOTE SENSING,56(5),699-717.
MLA	de Oliveira Silveira, Eduarda Martiniano,et al."Reducing the effects of vegetation phenology on change detection in tropical seasonal biomes".GISCIENCE & REMOTE SENSING 56.5(2019):699-717.