Feasibility of employing artificial neural networks for emergent crop monitoring in SAR systems

An investigation into the feasibility of using high-resolution synthetic aperture radar (SAR) data and artificial neural networks for monitoring the stage of growth of a crop is presented. The high resolution data sets representing an experimentally simulated crop at three different stages of growth are acquired at X-band by means of a ground-based synthetic aperture radar (GB-SAR) system under development at the University of Sheffield. A hybrid classification system, developed in previously, is then applied to these image sets, providing high training and test data accuracy (85.8% and 94.4%, respectively) for differences in growth of the order of a quarter of a wavelength, and acceptable results (79.9% and 71.9%, respectively) for differences of the order of a tenth of a wavelength. The procedures developed for the high-resolution data acquisition are described and the results obtained by applying the hybrid classification system to the acquired data are discussed