Conifer species recognition: An exploratory analysis of in situ hyperspectral data

In situ hyperspectral data measured above sunlit and shaded sides of canopies using a high spectral resolution radiometer were analyzed for identification of six conifer tree species. An artificial neural network algorithm was assessed for the identification purpose. Linear discrimination analysis was compared with the neural network algorithm. The hyperspectral with the neural data were further processed to smoothed reflectance and first derivative spectra and were separately used in tree species identification. Tree species recognition with data collected front six study sites was tested in seven experiments. The average accuracy of species recognition was obtained at every site. The overall performance of the neural network algorithm was better than that of linear discriminant analysis for species recognition when the same number of training samples and test samples were used. The discriminant analysis produced better accuracy than neural network at one site where many samples (10) were taken from six individual trees. Use of the average spectra of all samples for a particular tree species in training may not result in higher accuracy than use of individual spectral samples in training. Use of sunlit samples alone resulted in an overall accuracy of greater than 91%. The effects of site background including illuminating conditions on tree species specra were large. Neural networks are sensitive to subtle spectral details and can be trained to separate samples front the same species at different sites. Our experiments indicate that the discriminating power of visible bands is stronger than that of near-infrared bands. Higher recognition accuracies can be obtained in the blue to green or the red-edge spectral region as compared with four other spectral regions. A smaller set of selected bands can generate more accurate identification than all spectral bands.

[1]  Alfredo Huete,et al.  Effects of standing litter on the biophysical interpretation of plant canopies with spectral indices , 1996 .

[2]  D. H. Card,et al.  Prediction of leaf chemistry by the use of visible and near infrared reflectance spectroscopy , 1988 .

[3]  Alan H. Strahler,et al.  An analytic BRDF model of canopy radiative transfer and its inversion , 1993, IEEE Trans. Geosci. Remote. Sens..

[4]  Jiyou Wu,et al.  Seasonal patterns in leaf reflectance red-edge characteristics , 1991 .

[5]  M. S. Moran,et al.  Normalization of sun/view angle effects using spectral albedo-based vegetation indices , 1995 .

[6]  S. Goward,et al.  Visible-near infrared spectral reflectance of landscape components in western Oregon , 1994 .

[7]  Craig S. T. Daughtry,et al.  A new technique to measure the spectral properties of conifer needles , 1989 .

[8]  Michael D. Steven,et al.  High resolution derivative spectra in remote sensing , 1990 .

[9]  R. Jackson,et al.  Spectral response of a plant canopy with different soil backgrounds , 1985 .

[10]  P. Curran.  Remote sensing of foliar chemistry , 1989 .

[11]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[12]  Darrel L. Williams.  A comparison of spectral reflectance properties at the needle, branch, and canopy level for selected Conifer species , 1991 .

[13]  A F Goetz,et al.  Imaging Spectrometry for Earth Remote Sensing , 1985, Science.

[14]  Yoh-Han Pao,et al.  Adaptive pattern recognition and neural networks , 1989 .

[15]  Xiaomei Xu,et al.  Applying neural net technology for multi-objective land use planning , 1991 .

[16]  John R. Miller,et al.  Correlating leaf area index of Ponderosa pine with hyperspectral casi data , 1992 .

[17]  Ruiliang Pu,et al.  Coniferous forest leaf area index estimation along the Oregon transect using compact airborne spectrographic imager data , 1995 .

[18]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[19]  Michael D. McCormack,et al.  FIRST-BREAK REFRACTION EVENT PICKING AND SEISMIC DATA TRACE EDITING USING NEURAL NETWORKS , 1993 .

[20]  John R. Miller,et al.  Forest canopy closure from classification and spectral unmixing of scene components-multisensor evaluation of an open canopy , 1994, IEEE Trans. Geosci. Remote. Sens..

[21]  David L. Peterson,et al.  Multivariate analysis of AVIRIS data for canopy biochemical estimation along the oregon transect , 1994 .

[22]  B. Leblon,et al.  Effects of shadowing types on ground-measured visible and near-infrared shadow reflectances , 1996 .

[23]  P. Gong,et al.  Integrated Analysis of Spatial Data from Multiple Sources: Using Evidential Reasoning and Artificial Neural Network Techniques for Geological Mapping , 1996 .

[24]  P. Gong,et al.  Mapping Ecological Land Systems and Classification Uncertainties from Digital Elevation and Forest-Cover Data Using Neural Networks , 1996 .