Sunflower biomass estimation using a scattering model and a neural network algorithm
Abstract:Inversion of biomass for sunflower fields using radar backscattering data has been carried out with neural network algorithms. An electromagnetic model 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.
Document Type: Research Article
Affiliations: 1: Dipartimento di Informatica, Sistemi e Produzione, Università Tor Vergata, Via di Tor Vergata 110, 00133 Roma, Italy 2: Research Laboratory of Electronics, Massachusetts Institute of Technology, Cambridge, MA 02139, USA
Publication date: 2001-05-20