Using single-and multi-target regression to estimate biophysical parameters of crops

摘要

Estimation of biophysical parameters based on regression models is of interest for the remote sensing community since it is one of the key elements for agricultural purposes. Numerically, this problem is solved separately for each biophysical parameter such as Leaf Area Index-LAI, soil moisture, crop height and etc. However, this approach ignores tight relationship among the biophysical parameters, which is essential for driving estimation performance with a limited number of in-situ measurements. As an alternative strategy, a multi-target regression, which also learns the relationship among biophysical parameters in regression model, is considered. In order to see how multitarget regression models capture plausible physical relationship between crop's biophysical parameters and polarimetric features, RadarSAT-2 images acquired over agriculture fields in the context of AgriSAR 2009 campaign were used.