Use of Unmanned Aircraft Systems to Delineate Fine-Scale Wetland Vegetation Communities

Abstract

Remote sensing of wetlands has primarily focused on delineating wetlands within a non-wetland matrix. However, within-wetland changes are arguably just as important as loss of wetland area, particularly in a time of accelerated climate change. Remote sensing is a critical source of data for ecological models that explain and predict landscape changes, but data specifications, including spatial and temporal resolution, must be appropriate for applications. Unmanned Aircraft Systems (UASs) can be used to collect fine spatial resolution data with a temporal resolution more tailored to application need, instead of satellite orbital times or flight schedules. We used data collected from an UAS to acquire true color data within a wetland landscape and tested our ability to automatically classify plant communities from fine-resolution data. Classification accuracies were low for certain classes when nine vegetation communities were mapped, but the overall accuracy was on par with other remote sensing analyses. We demonstrate that classification data derived from UAS fine-resolution imagery is reasonably accurate and discuss the benefits and challenges of using UAS for wetland mapping.

Wetland Assessment Using Unmanned Aerial Vehicle (Uav) Photogrammetry

“…This research studied the broader characteristic attributes of a wetland to meet the requirements of the wetland delineation (DWAF, 2008) and classification (Kotze et al, 2005). Existing UAV photogrammetry literature such as Li et al (2010), Thamm et al (2013), Marcaccio et al (2015) and Zweig et al (2015) mostly focussed on wetland vegetation classification. The findings of this study are comparable to the results of these studies in terms of identification and mapping of dominant wetland vegetation from the HROs although this research used products such as the 0.038 m point cloud and DEM in combination with the HROs to assist with the mapping which proved to be highly accurate.…”

“…The technology has been applied successfully for mining (Peterman and Mesarič, 2012), ecological applications (Anderson and Gatson, 2013) and other constantly changing environments such as rivers (Rathinam et al, 2007, Ahmad et al, 2013, Flener et al, 2013, Ouédraogo et al, 2014. UAV photography can provide high spatial details needed by scientists (Li et al, 2010, Shahbazi et al, 2014 and is not constrained by orbital times or flight schedules (Zweig et al, 2015). Progress in computer vision and computing power has led to the advancement of UAV photogrammetry.…”

“…Highresolution orthophotos derived through low-altitude UAV photogrammetry can also generate information of physiological and ecological characteristics of plant communities such as texture and color (Li et al, 2010). Complex wetland vegetation information at a community scale can be identified (Li et al, 2010, Lechner et al, 2012, delineated and classified (Marcaccio et al, 2015, Zweig et al, 2015. However, wetlands present a different challenge to remote sensing application compared to other ecosystems that have received a great deal of attention in the remote sensing community.…”

High-Resolution Vegetation Mapping in Japan by Combining Sentinel-2 and Landsat 8 Based Multi-Temporal Datasets through Machine Learning and Cross-Validation Approach

“…Different types of remote sensing data: multi-spectral, hyper-spectral, radar, or LiDAR obtained from satellites or aircrafts have been exploited for the detection and mapping of vegetation at local or large scale [8][9][10][11][12][13][14][15][16][17][18][19]. Major techniques used for the detection, classification, and mapping of vegetation using remote sensing imagery are vegetation indices [20,21], spectral mixture analysis [22], temporal image-fusion [23,24], texture based measures [25], and supervised classification using machine learning classifiers such as maximum likelihood [26], random forests [27,28], decision trees [29], support vector machines [30], fuzzy learning [31], and neural networks [32][33][34].…”

Wetland Assessment Using Unmanned Aerial Vehicle (Uav) Photogrammetry

“…Ecosystems such as wetlands are often complex because of the way people use wetlands and the different benefits that people receive from these ecosystems . Remote sensing provides critical data to delineate, explain and predict changes in wetland ecosystems especially where a high spatial resolution is needed (Zweig et al, 2015). The advent of photogrammetry using UAV has proved a cost effective and efficient alternative to traditional remote sensing techniques (Shabazi et al, 2014).…”