Do Red Edge and Texture Attributes from High-Resolution Satellite Data Improve Wood Volume Estimation in a Semi-Arid Mountainous Region?
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Do Red Edge and Texture Attributes from High-Resolution Satellite Data Improve Wood Volume Estimation in a Semi-Arid Mountainous Region? / Schumacher, Paul; Mislimshoeva, Bunafsha; Brenning, Alexander; Zandler, Harald; Brandt, Martin Stefan; Samimi, Cyrus; Koellner, Thomas.
In: Remote Sensing, Vol. 8, No. 7, 540, 2016.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Do Red Edge and Texture Attributes from High-Resolution Satellite Data Improve Wood Volume Estimation in a Semi-Arid Mountainous Region?
AU - Schumacher, Paul
AU - Mislimshoeva, Bunafsha
AU - Brenning, Alexander
AU - Zandler, Harald
AU - Brandt, Martin Stefan
AU - Samimi, Cyrus
AU - Koellner, Thomas
PY - 2016
Y1 - 2016
N2 - Remote sensing-based woody biomass quantification in sparsely-vegetated areas is oftenlimited when using only common broadband vegetation indices as input data for correlation withground-based measured biomass information. Red edge indices and texture attributes are oftensuggested as a means to overcome this issue. However, clear recommendations on the suitability ofspecific proxies to provide accurate biomass information in semi-arid to arid environments are stilllacking. This study contributes to the understanding of using multispectral high-resolution satellitedata (RapidEye), specifically red edge and texture attributes, to estimate wood volume in semi-aridecosystems characterized by scarce vegetation. LASSO (Least Absolute Shrinkage and SelectionOperator) and random forest were used as predictive models relating in situ-measured abovegroundstanding wood volume to satellite data. Model performance was evaluated based on cross-validationbias, standard deviation and Root Mean Square Error (RMSE) at the logarithmic and non-logarithmicscales. Both models achieved rather limited performances in wood volume prediction. Nonetheless,model performance increased with red edge indices and texture attributes, which shows that theyplay an important role in semi-arid regions with sparse vegetation.
AB - Remote sensing-based woody biomass quantification in sparsely-vegetated areas is oftenlimited when using only common broadband vegetation indices as input data for correlation withground-based measured biomass information. Red edge indices and texture attributes are oftensuggested as a means to overcome this issue. However, clear recommendations on the suitability ofspecific proxies to provide accurate biomass information in semi-arid to arid environments are stilllacking. This study contributes to the understanding of using multispectral high-resolution satellitedata (RapidEye), specifically red edge and texture attributes, to estimate wood volume in semi-aridecosystems characterized by scarce vegetation. LASSO (Least Absolute Shrinkage and SelectionOperator) and random forest were used as predictive models relating in situ-measured abovegroundstanding wood volume to satellite data. Model performance was evaluated based on cross-validationbias, standard deviation and Root Mean Square Error (RMSE) at the logarithmic and non-logarithmicscales. Both models achieved rather limited performances in wood volume prediction. Nonetheless,model performance increased with red edge indices and texture attributes, which shows that theyplay an important role in semi-arid regions with sparse vegetation.
U2 - 10.3390/rs8070540
DO - 10.3390/rs8070540
M3 - Journal article
VL - 8
JO - Remote Sensing
JF - Remote Sensing
SN - 2072-4292
IS - 7
M1 - 540
ER -
ID: 165842624