Title :
Neural network inversion of bidirectional reflectance
Author :
Smith, J.A. ; Pedelty, J.A. ; Knox, R.G.
Author_Institution :
NASA Goddard Space Flight Center, Greenbelt, MD, USA
Abstract :
A Monte Carlo canopy reflectance model for predicting canopy bidirectional reflectance is coupled to a forest ecosystem dynamics succession model. The combined models are being applied to forest canopies in order to train a back propagation artificial neural network to extract underlying canopy biophysical attributes or forest succession stage. Validation of the modeling approach and neural network inversion performance is carried out for field data collected at the Northern Experimental Forest study site near Howland, Maine, the location of a NASA sponsored Forest Ecosystem Dynamics Multi-sensor Aircraft Campaign
Keywords :
forestry; geophysical signal processing; geophysical techniques; neural nets; remote sensing; Howland; Maine; Monte Carlo canopy reflectance model; Northern Experimental Forest study site; United States USA; backpropagation; bidirectional reflectance spectra; ecology succession stage; ecosystem dynamics succession model; forest forestry; geophysical measurement technique; land surface vegetation; neural net; neural network inversion; optical imaging; remote sensing; visible light scattering; Aircraft; Artificial neural networks; Bidirectional control; Data mining; Ecosystems; Monte Carlo methods; NASA; Neural networks; Predictive models; Reflectivity;
Conference_Titel :
Geoscience and Remote Sensing Symposium, 1994. IGARSS '94. Surface and Atmospheric Remote Sensing: Technologies, Data Analysis and Interpretation., International
Conference_Location :
Pasadena, CA
Print_ISBN :
0-7803-1497-2
DOI :
10.1109/IGARSS.1994.399447
