NASA Logo

NTRS

NTRS - NASA Technical Reports Server

Back to Results
LAI inversion from optical reflectance using a neural network trained with a multiple scattering modelThe inversion of the leaf area index (LAI) canopy parameter from optical spectral reflectance measurements is obtained using a backpropagation artificial neural network trained using input-output pairs generated by a multiple scattering reflectance model. The problem of LAI estimation over sparse canopies (LAI < 1.0) with varying soil reflectance backgrounds is particularly difficult. Standard multiple regression methods applied to canopies within a single homogeneous soil type yield good results but perform unacceptably when applied across soil boundaries, resulting in absolute percentage errors of >1000 percent for low LAI. Minimization methods applied to merit functions constructed from differences between measured reflectances and predicted reflectances using multiple-scattering models are unacceptably sensitive to a good initial guess for the desired parameter. In contrast, the neural network reported generally yields absolute percentage errors of <30 percent when weighting coefficients trained on one soil type were applied to predicted canopy reflectance at a different soil background.
Document ID
19930063756
Document Type
Conference Paper
Authors
Smith, James A. (NASA Goddard Space Flight Center Greenbelt, MD, United States)
Date Acquired
August 16, 2013
Publication Date
January 1, 1992
Publication Information
Publication: In: IGARSS '92; Proceedings of the 12th Annual International Geoscience and Remote Sensing Symposium, Houston, TX, May 26-29, 1992. Vol. 1 (A93-47551 20-43)
Subject Category
EARTH RESOURCES AND REMOTE SENSING
Distribution Limits
Public
Copyright
Other

Related Records

IDRelationTitle19930063554Analytic PrimaryIGARSS '92; Proceedings of the 12th Annual International Geoscience and Remote Sensing Symposium, Houston, TX, May 26-29, 1992. Vols. 1 & 2