Sunflower biomass estimation using a scattering model and a neural networkalgorithm

Inversion of biomass for sunflower fields using radar backscattering data h as been carried out with neural network algorithms. An electromagnetic mode l is used to generate the scattering coefficients for training and testing of the net. The model is validated with experimental data obtained from the Montespertoli test site during the Remote Sensing Campaign Mac-Europe 91. The inversion results show that the neural network is capable of performing the retrieval with good accuracy. By optimizing the structural complexity of the net, a better inversion result is obtained.