Mapping mixed vegetation communities in salt marshes using airborne spectral data

Autor: M. P. Stoll, Marco Marani, Massimo Menenti, Cheng Wang, E. Belluco
Rok vydání: 2007
Předmět:
Zdroj: Remote sensing of environment 107 (2007): 559–570.
info:cnr-pdr/source/autori:WANG, C., M. MENENTI, M. P. STOLL, E. BELLUCCO, M. MARANI/titolo:Mapping mixed vegetation communities in salt marshes using airborne spectral data./doi:/rivista:Remote sensing of environment/anno:2007/pagina_da:559/pagina_a:570/intervallo_pagine:559–570/volume:107
ISSN: 0034-4257
DOI: 10.1016/j.rse.2006.10.007
Popis: The aim of this study is to evaluate a new neural network classifier using spectrally sampled image data to map mixed halophytic vegetation in tidal environments. The work is based on the concept of vegetation communities, mixtures of several species, characteristic of salt marshes. The study site is the Venice lagoon, and the material available is a spectrally sampled Compact Airborne Spectral Imager (CASI) image, in conjunction with ground truth for precise characterization of vegetation communities. Detailed observations of vegetation species and of their fractional abundance were collected for 36 Regions Of Interest (ROI): such field polygons are used for classification training and accuracy assessment. To select the most significant spectral channels, the Spectral Reconstruction method was applied to the image data: a set of 6 bands was selected as optimal for classification, out of the 15 available. The spatial heterogeneity of salt-marsh vegetation is significant and even at the spatial resolution of the airborne CASI image data, mixed pixels are observed. The Vegetation Community based Neural Network Classifier (VCNNC) is introduced to cope with a situation where no pure pixels exist, and was applied to the set of 6 selected bands. Both quantitative and qualitative comparisons of classification results of VCNNC with those of conventional Neural Network Classifier (NNC), trained and assessed on exactly the same data sets, shows that VCNNC's accuracy is substantially higher (≈ 91%) than that of NNC (≈ 84%), while the Kappa coefficient is 0.87 for VCNNC and 0.75 for the NNC method.
Databáze: OpenAIRE
Externí odkaz: