Characterization of Vegetation Physiognomic Types Using Bidirectional Reflectance Data

Abstract

Listen

Translate article

This paper presents an assessment of the bidirectional reflectance features for the classification and characterization of vegetation physiognomic types at a national scale. The bidirectional reflectance data at multiple illumination and viewing geometries were generated by simulating the Moderate Resolution Imaging Spectroradiometer (MODIS) Bidirectional Reflectance Distribution Function (BRDF) model parameters with Ross-Thick Li-Sparse-Reciprocal (RT-LSR) kernel weights. This research dealt with the classification and characterization of six vegetation physiognomic types—evergreen coniferous forest, evergreen broadleaf forest, deciduous coniferous forest, deciduous broadleaf forest, shrubs, and herbaceous—which are distributed all over the country. The supervised classification approach was used by employing four machine learning classifiers—k-Nearest Neighbors (KNN), Random Forests (RF), Support Vector Machines (SVM), and Multilayer Perceptron Neural Networks (NN)—with the support of ground truth data. The confusion matrix, overall accuracy, and kappa coefficient were calculated through a 10-fold cross-validation approach, and were also used as the metrics for quantitative evaluation. Among the classifiers tested, the accuracy metrics did not vary much with the classifiers; however, the Random Forests (RF; Overall accuracy = 0.76, Kappa coefficient = 0.72) and Support Vector Machines (SVM; Overall accuracy = 0.76, Kappa coefficient = 0.71) classifiers performed slightly better than other classifiers. The bidirectional reflectance spectra did not only vary with the vegetation physiognomic types, it also showed a pronounced difference between the backward and forward scattering directions. Thus, the bidirectional reflectance data provides additional features for improving the classification and characterization of vegetation physiognomic types at the broad scale.