Non-Parametric Retrieval of Aboveground Biomass in Siberian Boreal Forests with ALOS PALSAR Interferometric Coherence and Backscatter Intensity

Journal of Imaging

Martyna A. Stelmaszczuk-Górska²  Pedro Rodriguez-Veiga¹  Nicolas Ackermann³  Christian Thiel²  Heiko Balzter¹  Christiane Schmullius²  Francisco Rovira-Más⁴ 

[1] Centre for Landscape and Climate Research, University of Leicester, Bennett Building, University Road, Leicester LE1 7RH, UK;Department of Earth Observation, Friedrich-Schiller-University Jena, Loebdergraben 32, Jena D-07743, Germany;Gamaya AG, Bâtiment C, EPFL Innovation Park, Lausanne 1015, Switzerland;;Department of Earth Observation, Friedrich-Schiller-University Jena, Loebdergraben 32, Jena D-07743, Germany

关键词: SAR;    MaxEnt;    random forests;    estimation error;    forest;    biomass;    carbon;   

DOI  :  10.3390/jimaging2010001

来源: mdpi

【 摘 要 】

The main objective of this paper is to investigate the effectiveness of two recently popular non-parametric models for aboveground biomass (AGB) retrieval from Synthetic Aperture Radar (SAR) L-band backscatter intensity and coherence images. An area in Siberian boreal forests was selected for this study. The results demonstrated that relatively high estimation accuracy can be obtained at a spatial resolution of 50 m using the MaxEnt and the Random Forests machine learning algorithms. Overall, the AGB estimation errors were similar for both tested models (approximately 35 t∙ha⁻¹). The retrieval accuracy slightly increased, by approximately 1%, when the filtered backscatter intensity was used. Random Forests underestimated the AGB values, whereas MaxEnt overestimated the AGB values.

【 授权许可】

CC BY   
© 2015 by the authors; licensee MDPI, Basel, Switzerland.