Journal
GISCIENCE & REMOTE SENSING
Volume 56, Issue 1, Pages 68-86Publisher
TAYLOR & FRANCIS LTD
DOI: 10.1080/15481603.2018.1492213
Keywords
accuracy; ecosystems; canopy storage capacity; regression ensembles; soil water; water balance
Categories
Funding
- South African Research Chairs Initiative (SARChI)/UKZN/Rural Agronomy [86893]
Ask authors/readers for more resources
This study assessed the strength of Sentinel-2 multispectral instrument (MSI) derived Red Edge (RE) bands in estimating Leaf Area Index (LAI) and mapping canopy storage capacity (CSC) for hydrological applications in wattle infested ecosystems. To accomplish this objective, this study compared the estimation strength of models derived, using standard bands (all bands excluding the RE band) with those including RE bands, as well as different vegetation indices. Sparse Partial Least Squares (SPLSR) and Partial Least Squares Regression (PLSR) ensembles were used in this study. Results showed that the RE spectrum covered by the Sentinel-2 MSI satellite reduced the estimation error by a magnitude of 0.125 based on simple ratio (RE SR) vegetation indices from 0.157m(2)m(-2) based on standard bands, and by 0.078m(2)m(-2) based on red edge normalised difference vegetation (NDVI-RE). The optimal models for estimating LAI to map CSC were obtained based on the RE bands centered at 705nm (Band 5), 740nm (Band 6), 783nm (Band 7) as well as 865nm (Band 8a). A root mean square error of prediction (RMSEP) of 0.507m(2)m(-2) a relative root mean square error of prediction (RRMSEP) of 11.3% and R-2 of 0.91 for LAI and a RMSEP of 0.246m(2)/m(2) (RRMSEP=7.9%) and R-2 of 0.91 for CSC were obtained. Overall, the findings of this study underscore the relevance of the new copernicus satellite product in rapid monitoring of ecosystems that are invaded by alien invasive species.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available