A comparison of airborne hyperspectral-based classifications of emergent wetland vegetation at Lake Balaton, Hungary

Abstract

Earth observation has rapidly evolved into a state-of-the-art technology providing new capabilities and a wide variety of sensors; nevertheless, it is still a challenge for practitioners external to a specialized community of experts to select the appropriate sensor, define the imaging mode requirements, and select the optimal classifier or retrieval method for the task at hand. Especially in wetland mapping, studies have relied largely on vegetation indices and hyperspectral data to capture vegetation attributes. In this study, we investigate the capabilities of a concurrently acquired very high spatial resolution airborne hyperspectral and lidar data set at the peak of aquatic vegetation growth in a nature reserve at Lake Balaton, Hungary. The aim was to examine to what degree the different remote-sensing information sources (i.e. visible and near-infrared hyperspectral, vegetation indices and lidar) are contributing to an accurate aquatic vegetation map. The results indicate that de-noised hyperspectral information in the visible and very near-infrared bands (400-1000 nm) is performing most accurately. Inclusion of lidar information, hyperspectral infrared bands (1000-2500 nm), or extracted vegetation indices does not improve the classification accuracy. Experimental results with algorithmic comparisons show that in most cases, the Support Vector Machine classifier provides a better accuracy than the Maximum Likelihood.

Photophysiology and Spectroscopy of Sun and Shade Leaves of Phragmites australis and the Effect on Patches of Different Densities

“…The steep windward northern shore's sediment consists of dolomite limestone, while the shallow southern shore is dominated by sandy sediment. On the northern shore of the lake the average and maximum depth of water that reed stand can be found is 1.5 m and 2.4 m respectively, while on the southern shore the average depth on the waterward side of reed stands is 1 m [40,41] Lake Balaton has received significant scientific attention due to the reed die-back phenomenon observed (e.g., [40][41][42][43]), the macrophytic traits and species mapping (e.g., [44][45][46][47]) and the dynamic trophic gradient of the water (e.g., [48,49]). The field data for this study were collected at the Kerekedi bay, an oligo-mesotrophic bay at the easternmost basin of Lake Balaton situated at the geographic coordinates 46 • Map of the study area in Lake Balaton (inset) and field sampling points' location in the Kerekedi Bay (main).…”

Joint Classification of Hyperspectral and Multispectral Images for Mapping Coastal Wetlands

“…However, pixel-based classification performance is always limited for complicated landscape with diverse landcover types and their small patch sizes [40]. Moreover, spectral variations cause different species to have similar spectral signatures [41]. Single source of spectral information may not distinguish mixed species composition of wetlands and often leads to low mapping accuracies.…”

Feature and information extraction for regions of Southeast Europe from Corona satellite images acquired in 1968

“…However, there is much more to anticipate from this historic archive; the 0.5-0.9μm spectral domain of the panchromatic layer has been shown to be the most important spectral region for vegetation-related studies (e.g. [14][15][16][17]) and the very high spatial resolution is suitable for small agricultural field parcels delineation [18][19] (if not necessary [20]) which appears to be the norm in Bulgaria of the 1960s.…”