Please use this identifier to cite or link to this item:
|Title:||Predicting soil organic carbon content in Cyprus using remote sensing and earth observation data|
|Authors:||BALLABIO CRISTIANO; PANAGOS Panagiotis; MONTANARELLA Luca|
|Citation:||PROCEEDINGS OF SPIE - THE INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING vol. 9229 p. 92290F|
|Publisher:||S P I E - INTERNATIONAL SOCIETY FOR OPTICAL ENGINEERING|
|Type:||Articles in periodicals and books|
|Abstract:||The LUCAS database currently contains about 20 thousand topsoil samples of 15 soil properties. This is the largest harmonized soil survey field database at the moment available for Europe. Soil Organic Carbon (SOC) levels have been successfully determined using reflectance spectroscopy, both proximal and airborne/spaceborne. In this paper, Cyprus was selected as a study area estimating SOC content from multispectral remotely sensed data. The estimation of SOC was derived by relating field measurements with a set of spatially exhaustive covariates including DEM derived terrain features, MODIS Vegetation indices (16 days) and Landsat ETM+ data. In particular, the SOC levels in the LUCAS database were related with the covariates values in the collocated pixels and their 8 surrounding neighbours. The regression model adopted made use of Support Vector Machines (SVM) regression. The SVM regression proved to be very efficient in mapping SOC with a fitting R2 of 0.81 and a k-fold cross-validation R2 of 0.68. This study proves that the inference of SOC levels is possible at regional or continental scales using already available remote sensing data and earth observations.|
|JRC Directorate:||Sustainable Resources|
Files in This Item:
There are no files associated with this item.
Items in repository are protected by copyright, with all rights reserved, unless otherwise indicated.