Retrieving forest stand parameters from SAR backscatter data using a neural network trained by a canopy backscatter model

It was possible to retrieve the stand mean dbh (tree trunk diameter at breast height) and stand density from the Jet Propulsion Laboratory (JPL) Airborne Synthetic Aperture Radar (AIRSAR) backscatter data by using three-layered perceptron neural networks (NNs). Two sets of NNs were trained by the Santa Barbara microwave canopy backscatter model. One set of the trained NNs was used to retrieve the stand mean dbh, and the other to retrieve the stand density. Each set of the NNs consisted of seven individual NNs for all possible combinations of one, two, and three radar wavelengths. Ground and multiple-wavelength AIRSAR backscatter data from two ponderosa pine forest stands near Mt. Shasta, California (U.S.A.) were used to evaluate the accuracy of the retrievals. The r.m.s. and relative errors of the retrieval for stand mean dbh were less than or equal to 6 . 1 cm and less than or equal to 15 . 6 per cent for one stand (St2), and less than or equal to 3 . 1 cm and less than or equal to 6 . 7 per cent for the other stand (St11). The r.m.s. and relative errors of the retrieval for stand density were less than or equal to 71 . 2 trees ha(-1) and less than or equal to 23 . 0 per cent for St2, and less than or equal to 49 . 7 trees ha(-1) and less than or equal to 21 . 3 per cent for St11.