Mapping Invasive Phragmites australis in the Old Woman Creek Estuary Using UAV Remote Sensing and Machine Learning Classifiers

Abstract

Unmanned aerial vehicles (UAV) are increasingly used for spatiotemporal monitoring of invasive plants in coastal wetlands. Early identification of invasive species is necessary in planning, restoring, and managing wetlands. This study assessed the effectiveness of UAV technology to identify invasive Phragmites australis in the Old Woman Creek (OWC) estuary using machine learning (ML) algorithms: Neural network (NN), support vector machine (SVM), and k-nearest neighbor (kNN). The ML algorithms were compared with the parametric maximum likelihood classifier (MLC) using pixel- and object-based methods. Pixel-based NN was identified as the best classifier with an overall accuracy of 94.80% and the lowest error of omission of 1.59%, the outcome desirable for effective eradication of Phragmites. The results were reached combining Sequoia multispectral imagery (green, red, red edge, and near-infrared bands) combined with the canopy height model (CHM) acquired in the mid-growing season and normalized difference vegetation index (NDVI) acquired later in the season. The sensitivity analysis, using various vegetation indices, image texture, CHM, and principal components (PC), demonstrated the impact of various feature layers on the classifiers. The study emphasizes the necessity of a suitable sampling and cross-validation methods, as well as the importance of optimum classification parameters.

Mapping invasive Lupinus polyphyllus Lindl. in semi-natural grasslands using object-based analysis of UAV-borne images

“…This was also proven by other studies that utilised CHM from UAV-borne RS data to map invasive species mapping (i.e. Phragmites australis in estuaries by Abeysinghe et al (2019) and…”

Mapping Invasive Lupinus polyphyllus Lindl. in Semi-natural Grasslands Using Object-Based Image Analysis of UAV-borne Images

“…In grasslands, invasive woody (Mirik et al 2013) and shrubby (Laliberte et al 2004;Ishii and Washitani 2013) species mapping has shown excellent results with satellite and airborne image classification. Meanwhile, using an unmanned aerial vehicle (UAV)-borne remotely sensed (RS) imaging was increasingly applied for invasive species mapping in the recent years in flood plains and coastal regions (de Sá et al 2018;Martin et al 2018;Abeysinghe et al 2019;Jianhui et al 2019). Cost-effectiveness, high spatial and temporal resolution and the increasing availability of various miniature sensors (e.g.…”

“…Object-based image analysis (OBIA) can better be employed when pixels are considerably smaller than the object to be identified (Blaschke 2010). Several studies indicated that OBIA provides substantial advantages for mapping invasive plant species based on UAV-borne RS data (Michez et al 2016;Martin et al 2018;Abeysinghe et al 2019). Typical OBIA employs rules derived from the object's attributes to classify an object, which requires expert knowledge and limits the transferability of the classification model (Belgiu et al 2014).…”

Spatial Dynamics of Invasive Para Grass on a Monsoonal Floodplain, Kakadu National Park, Northern Australia

“…Indeed, RS is often the only source of information readily available to characterise habitats, and monitor and detect weeds or environmental change in such areas [71,72]. Measurements can also be repeated with relative consistency over time, obtained at range of scales and spatially integrated within geographic information systems [73][74][75][76]. However, inherent and sometimes avoidable measurement errors contribute to uncertainty in RS interpretation, which therefore must be validated by finer-scale ground surveys, nested within the landscape.…”