Kernel based simplification of canopy reflectance model using partial least square regression

Yingjie Yu; Xihan Mu; Qiang Liu; Zhigang Liu; Yuanyuan Wang; Guangjian Yan

doi:10.1117/12.760659

Translator Disclaimer

8 August 2007 Kernel based simplification of canopy reflectance model using partial least square regression

Yingjie Yu, Xihan Mu, Qiang Liu, Zhigang Liu, Yuanyuan Wang, Guangjian Yan

Author Affiliations +

Proceedings Volume 6752, Geoinformatics 2007: Remotely Sensed Data and Information; 675214 (2007) https://doi.org/10.1117/12.760659
Event: Geoinformatics 2007, 2007, Nanjing, China

Abstract

Inversion is an important process in remote sensing. In order to improve the stability and accuracy of inversion, in this article, we applied kernel forms of AMBRALS (Algorithm for Model Bidirectional Reflectance Anisotropies of the Land Surface) and PLS (Partial Least Square) regression technique to simplify a canopy reflectance model SAILH (Scattering by Arbitrarily Inclined Leaves, with Hotspot effect). PLS is a statistical method used for regression highly collinear variable data. Kernel-driven model is a semi-empirical model with linearity form of "kernels", and these kernels can be explained in physics. We generated 24 typical canopy cover scenes by combining the canopy parameters of SAILH model. For each scene, we used PLS regression to estimate the coefficients of our new model. The results suggest the new model is acceptable in stability and accuracy. Base on the new model, we defined sensitivity matrix to assess the correlations of directional observations data, which can help to choose appropriate directions when inversion.

Citation Download Citation

Yingjie Yu, Xihan Mu, Qiang Liu, Zhigang Liu, Yuanyuan Wang, and Guangjian Yan "Kernel based simplification of canopy reflectance model using partial least square regression", Proc. SPIE 6752, Geoinformatics 2007: Remotely Sensed Data and Information, 675214 (8 August 2007); https://doi.org/10.1117/12.760659

ACCESS THE FULL ARTICLE