Abstract
Mapping of vegetation from remote sensing is an active area of research since past two decades. Neural networks also successfully applied to such fields. In the present work a Radial basis function Network (RBFN) is trained and tested with the experimentally obtain data sets. Vertical transmitted and vertical received scattering coefficient sigma VV and horizontal transmitted and horizontal received scattering coefficients sigma HH and angle of incidence are used as the inputs of the network. Whereas crop parameters Leaf area index (LAI), Biomass (BM), and plant height and soil moisture parameters are used as the target data sets to train the network. It is noted that retrieved parameters are so close to the experimental results that confirm the potential of RBFNs as estimator. The main advantages of RBFN over other theoretical approaches are that it is less time taking and less complex approach.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call