globalchange  > 气候变化事实与影响
DOI: 10.1016/j.jag.2014.08.008
Scopus记录号: 2-s2.0-84920656982
论文题名:
Evaluating the robustness of models developed from field spectral data in predicting African grass foliar nitrogen concentration using WorldView-2 image as an independent test dataset
作者: Mutanga O; , Adam E; , Adjorloloa C; , Abdel-Rahmanw E; M
刊名: International Journal of Applied Earth Observation and Geoinformation
ISSN: 15698432
出版年: 2015
卷: 34, 期:1
起始页码: 178
结束页码: 187
语种: 英语
英文关键词: Field spectral data ; Grassland nitrogen ; Spectral resampling ; WorldView-2
Scopus关键词: grassland ; multispectral image ; NDVI ; nitrogen ; numerical model ; satellite imagery ; spectral analysis ; spectral reflectance ; WorldView ; Africa
英文摘要: In this paper, we evaluate the extent to which the resampled field spectra compare with the actual image spectra of the new generation multispectral WorldView-2 (WV-2) satellite. This was achieved by developing models from resampled field spectra data and testing them on an actual WV-2 image of the study area. We evaluated the performance of reflectance ratios (RI), normalized difference indices(NDI) and random forest (RF) regression model in predicting foliar nitrogen concentration in a grassland environment. The field measured spectra were used to calibrate the RF model using a randomly selected training (n = 70%) nitrogen data set. The model developed from the field spectra resampled to WV-2 wavebands was validated on an independent field spectral test dataset as well as on the actual WV-2 image of the same area (n = 30%, bootstrapped a 100 times). The results show that the model developed using RI could predict nitrogen with a mean R2of 0.74 and 0.65 on an independent field spectral test data set and on the actual WV-2 image, respectively. The root mean square error of prediction (RMSE %) was 0.17 and 0.22 for the field test data set and the WV-2 image, respectively. Results provide an insight on the magnitude of errors that are expected when up-scaling field spectral models to airborne or satellite image data. The prediction also indicates the unceasing relevance of field spectroscopy studies to better understand the spectral models critical for vegetation quality assessment. © 2014 Elsevier B.V.
Citation statistics:
资源类型: 期刊论文
标识符: http://119.78.100.158/handle/2HF3EXSE/79516
Appears in Collections:气候变化事实与影响

Files in This Item:

There are no files associated with this item.


作者单位: University of KwaZulu-Natal, School of Agricultural, Earth and Environmental Sciences, P. Bag X01, Scottsville, Pietermaritzburg, South Africa; University of the Witwatersrand, School of Geography, Archaeology and Environmental Studies, P. Bag 3, Wits, Johannesburg, South Africa; South African National Space Agency (SANSA), SANSA Earth Observation, 0087, P.O Box 484, Pretoria, Silverton, South Africa

Recommended Citation:
Mutanga O,, Adam E,, Adjorloloa C,et al. Evaluating the robustness of models developed from field spectral data in predicting African grass foliar nitrogen concentration using WorldView-2 image as an independent test dataset[J]. International Journal of Applied Earth Observation and Geoinformation,2015-01-01,34(1)
Service
Recommend this item
Sava as my favorate item
Show this item's statistics
Export Endnote File
Google Scholar
Similar articles in Google Scholar
[Mutanga O]'s Articles
[, Adam E]'s Articles
[, Adjorloloa C]'s Articles
百度学术
Similar articles in Baidu Scholar
[Mutanga O]'s Articles
[, Adam E]'s Articles
[, Adjorloloa C]'s Articles
CSDL cross search
Similar articles in CSDL Cross Search
[Mutanga O]‘s Articles
[, Adam E]‘s Articles
[, Adjorloloa C]‘s Articles
Related Copyright Policies
Null
收藏/分享
所有评论 (0)
暂无评论
 

Items in IR are protected by copyright, with all rights reserved, unless otherwise indicated.