Abstract
Wetland ecosystems straddle both terrestrial and aquatic habitats, performing many ecological functions directly and indirectly benefitting humans. However, global wetland losses are substantial. Satellite remote sensing and classification informs wise wetland management and monitoring. Both pixel- and object-based classification approaches using parametric and non-parametric algorithms may be effectively used in describing wetland structure and habitat, but which approach should one select? We conducted both pixel- and object-based image analyses (OBIA) using parametric (Iterative Self-Organizing Data Analysis Technique, ISODATA, and maximum likelihood, ML) and non-parametric (random forest, RF) approaches in the Barguzin Valley, a large wetland (~500 km2) in the Lake Baikal, Russia, drainage basin. Four Quickbird multispectral bands plus various spatial and spectral metrics (e.g., texture, Non-Differentiated Vegetation Index, slope, aspect, etc.) were analyzed using field-based regions of interest sampled to characterize an initial 18 ISODATA-based classes. Parsimoniously using a three-layer stack (Quickbird band 3, water ratio index (WRI), and mean texture) in the analyses resulted in the highest accuracy, 87.9% with pixel-based RF, followed by OBIA RF (segmentation scale 5, 84.6% overall accuracy), followed by pixel-based ML (83.9% overall accuracy). Increasing the predictors from three to five by adding Quickbird bands 2 and 4 decreased the pixel-based overall accuracy while increasing the OBIA RF accuracy to 90.4%. However, McNemar’s chi-square test confirmed no statistically significant difference in overall accuracy among the classifiers (pixel-based ML, RF, or object-based RF) for either the three- or five-layer analyses. Although potentially useful in some circumstances, the OBIA approach requires substantial resources and user input (such as segmentation scale selection—which was found to substantially affect overall accuracy). Hence, we conclude that pixel-based RF approaches are likely satisfactory for classifying wetland-dominated landscapes.
Highlights
Wetlands are amongst the most productive and biodiverse ecosystems on Earth [1]
As patterns emerge within and between natural systems, we explored the utility of an object-based image analyses (OBIA) classification of the study area using multi-resolution image segmentation in eCognition Developer (Trimble, Inc., Munich, Germany, v. 9.2)
We found the greatest overall accuracy to be achieved with the OBIA and random forest (RF) classifier (~90%) using five predictor variables; this decreased to
Summary
Wetlands are amongst the most productive and biodiverse ecosystems on Earth [1]. they have been lost at prodigious rates across the globe [2], and those that remain are imperiled.Junk et al [3] estimated that 30–90% of global wetlands have been lost, and that climate change and concomitant temperature and sea level rise, along with precipitation pattern changes, will continue to stress the remaining wetlands. Wetlands are amongst the most productive and biodiverse ecosystems on Earth [1]. They have been lost at prodigious rates across the globe [2], and those that remain are imperiled. Davidson [2] reviewed 189 reports of wetland area changes and determined that 64–71% of wetlands have been globally lost since approximately 1900 AD. Wetlands are known areas of high biogeochemical cycling (e.g., [4,5]), groundwater recharge and stormflow attenuation (e.g., [6,7]), and habitat for many biological species (e.g., [8,9,10]). Wetland processes that underlie these functions vary by habitat or vegetation structure.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
