Coastal saltmarsh and their constituent components and processes are of an interest scientifically due to their ecological function and services. However, heterogeneity and seasonal dynamic of the coastal wetland system makes it challenging to map saltmarshes with remotely sensed data. This study selected four important saltmarsh species Pragmitis australis, Sporobolus virginicus, Ficiona nodosa and Schoeloplectus sp. as well as a Mangrove and Pine tree species, Avecinia and Casuarina sp respectively. High Spatial Resolution Worldview-2 data and Coarse Spatial resolution Landsat 8 imagery were selected in this study. Among the selected vegetation types some patches ware fragmented and close to the spatial resolution of Worldview-2 data while and some patch were larger than the 30 meter resolution of Landsat 8 data. This study aims to test the effectiveness of different classifier for the imagery with various spatial and spectral resolutions. Three different classification algorithm, Maximum Likelihood Classifier (MLC), Support Vector Machine (SVM) and Artificial Neural Network (ANN) were tested and compared with their mapping accuracy of the results derived from both satellite imagery. For Worldview-2 data SVM was giving the higher overall accuracy (92.12%, kappa =0.90) followed by ANN (90.82%, Kappa 0.89) and MLC (90.55%, kappa = 0.88). For Landsat 8 data, MLC (82.04%) showed the highest classification accuracy comparing to SVM (77.31%) and ANN (75.23%). The producer accuracy of the classification results were also presented in the paper.
Saltmarsh is one of the important communities of wetlands, however, due to a range of pressures, it has been declared as an EEC (Ecological Endangered Community) in Australia. In order to correctly identify different saltmarsh species, development of spectral libraries of saltmarsh species is essential to monitor this EEC. Hyperspectral remote sensing, can explore the area of wetland monitoring and mapping. The benefits of Hyperion data to wetland monitoring have been studied at Hunter Wetland Park, NSW, Australia. After exclusion of bad bands from the original data, an atmospheric correction model was applied to minimize atmospheric effect and to retrieve apparent surface reflectance for different land cover. Large data dimensionality was reduced by Forward Minimum Noise Fraction (MNF) algorithm. It was found that first 32 MNF band contains more than 80% information of the image. Pixel Purity Index (PPI) algorithm worked properly to extract pure pixel for water, builtup area and three vegetation Casuarina sp., Phragmitis sp. and green grass. The result showed it was challenging to extract extreme pure pixel for Sporobolus and Sarcocornia from the data due to coarse resolution (30 m) and small patch size (<3 m) of those vegetation on the ground . Spectral Angle Mapper, classified the image into five classes: Casuarina, Saltmarsh (Phragmitis), Green grass, Water and Builtup area with 43.55 % accuracy. This classification also failed to classify Sporobolus as a distinct group due to the same reason. A high spatial resolution airborne hyperspectral data and a new study site with a bigger patch of Sporobolus and Sarcocornia is proposed to overcome the issue.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.