No abstract

No abstract

No abstract

The use of unmanned aerial vehicles (UAVs) to map and monitor the environment has increased sharply in the last few years. Many individuals and organizations have purchased consumer-grade UAVs, and commonly acquire aerial photographs to map land cover. The resulting ultra-high-resolution (subdecimeter-resolution) imagery has high information content, but automating the extraction of this information to create accurate, wall-to-wall land-cover maps is quite difficult. We introduce image-processing workflows that are based on open-source software and can be used to create land-cover maps from ultra-high-resolution aerial imagery. We compared four machine-learning workflows for classifying images. Two workflows were based on random forest algorithms. Of these, one used a pixel-by-pixel approach available in ilastik, and the other used image segments and was implemented with R and the Orfeo ToolBox. The other two workflows used fully connected neural networks and convolutional neural networks implemented with Nenetic. We applied the four workflows to aerial photographs acquired in the Great Basin (western USA) at flying heights of 10 m, 45 m and 90 m above ground level. Our focal cover type was cheatgrass (Bromus tectorum), a non-native invasive grass that changes regional fire dynamics. The most accurate workflow for classifying ultra-highresolution imagery depends on diverse factors that are influenced by image resolution and land-cover characteristics, such as contrast, landscape patterns and the spectral texture of the land-cover types being classified. For our application, the ilastik workflow yielded the highest overall accuracy (0.82-0.89) as assessed by pixel-based accuracy.

The concept of ecological integrity has been applied widely to management of aquatic systems, but still is considered by many to be too vague and difficult to quantify to be useful for managing terrestrial systems, particularly across broad areas. Extensive public lands in the western United States are managed for diverse uses such as timber harvest, livestock grazing, energy development, and wildlife conservation, some of which may degrade ecological integrity. We propose a method for assessing ecological integrity on multiple-use lands that identifies the components of integrity and levels in the ecological hierarchy where the assessment will focus, and considers existing policies and management objectives. Both natural reference and societally desired environmental conditions are relevant comparison points. We applied the method to evaluate the ecological integrity of shrublands in Nevada, yielding an assessment based on six indicators of ecosystem structure, function, and composition, including resource- and stressor-based indicators measured at multiple scales. Results varied spatially and among indicators. Invasive plant cover and surface development were highest in shrublands in northwest and southeast Nevada. Departure from reference conditions of shrubland area, composition, patch size, and connectivity was highest in central and northern Nevada. Results may inform efforts to control invasive species and restore shrublands on federal lands in Nevada. We suggest that ecological integrity assessments for multiple-use lands be grounded in existing policies and monitoring programs, incorporate resource- and stressor-based metrics, rely on publicly available data collected at multiple spatial scales, and quantify both natural reference and societally desired resource conditions.