Search

Beavers are ecosystem engineers that create and maintain riparian wetland ecosystems in a variety of ecologic, climatic, and physical settings. Despite the large‐scale implications of ongoing beaver conservation and range expansion, relatively few landscape‐scale studies have been conducted, due in part to the significant time required to manually locate beaver dams at scale. To address this need, we developed EEAGER—an image recognition machine learning model that detects beaver complexes in aerial and satellite imagery. We developed the model in the western United States using 13,344 known beaver dam locations and 56,728 nearby locations without beaver dams. Performance assessment was performed in twelve held out evaluation polygons of known beaver occupancy but previously unmapped dam locations. These polygons represented regions similar to the training data as well as more novel landscape settings. Our model performed well overall (accuracy = 98.5%, recall = 63.03%, precision = 25.83%) in these areas, with stronger performance in regions similar to where the model had been trained. We favored recall over precision, which results in a more complete catalog of beaver dams found but also a higher incidence of false positives to be manually removed during quality control. These results have far‐reaching implications for monitoring of beaver‐based river restoration, as well as potential applications detecting other complex landforms. Plain Language Summary: Beavers are ecosystem engineers that can dramatically change the shape of the landscape and how water moves through it. They create and maintain wetland environments across North America in a wide variety of places, including mountains, deserts, coasts, forests, grasslands, shrublands, etc. Despite their large influence on the landscape, there are very few programs that monitor them at the landscape scale. This is partially due to how much time it takes to find and identify beaver dams in satellite and aerial images. To make it easier for us to find and understand the influence of beavers at larger scales, we built a model that can automatically find beaver dams in satellite and aerial imagery. While our model is trained to find beaver dams, this type of model has promise for finding other landscape features too. Key Points: Tracking the distribution and range of ecosystem engineers like beavers is increasingly important under a changing climateA neural network machine learning model can be trained to find and identify beaver dams in aerial and satellite imagery automaticallyThis type of machine learning model may have applications for finding other landforms where geospatial context is an important input [ABSTRACT FROM AUTHOR]

• Beaver are unique and important forest disturbance agents in eastern North America. • Harvest impacts decrease exponentially with distance from active beaver ponds. • Beaver select more strongly for stem size than stem species. • Probability of stem harvest can be predicted by distance from impoundment and size class. The North American beaver (Castor canadensis) is a classic ecosystem engineer, creating and expanding wetlands throughout their vast range. As important as their impacts on aquatic ecosystems, beaver as central place foragers restructure the surrounding forest community by their selective cutting of preferred woody species and size classes. These effects, which have been studied in several regions of North America, are still poorly understood within forests of the northeastern United States, where beaver populations are rebounding following regional extirpation. Here, beaver represent a key disturbance agent in a region where other drivers such as fire and timber cutting have been greatly reduced over the last century. Understanding their specific impacts on forest composition and structure is needed to manage these forests and their multiple ecosystem services. In this context, we assessed beaver foraging preferences throughout New York's Adirondack State Park, a vast northern wooded region, to model their impacts on forest structure and composition. Across 19 sites distributed throughout the Park, beavers preferentially harvested stems < 10 cm diameter, with the 2–5 cm size class most preferred overall. Mixed-effects logistic regression models showed greater probability of harvest for stems closer to the impoundment for all species and taxonomic groups modeled, consistent with central place foraging theory. Broadleaf deciduous tree species were browsed at rates 33% greater than coniferous species, with American beech (Fagus grandifolia) among the most utilized species, contrary to other regions where it is typically avoided. Though stem diameter preferences and spatial gradients of foraging intensity were consistent with those found in other regions, species preferences differed greatly, suggesting that selectivity for a deciduous species expressed on the landscape is primarily a function of the size distribution of its available stems. [ABSTRACT FROM AUTHOR]

In recent decades, ecological restoration and landscape architecture have focused on reintegrating ecological processes in the urban environment to support greater habitat complexity and increase biodiversity. As these values are more broadly recognized, new approaches are being investigated to increase ecosystem services and ecological benefits in urban areas. Ecosystem engineers, such as the North American beaver (Castor canadensis), can create complex habitat and influence ecological processes in natural environments. Through dam building and wetland formation, beaver can create fish habitat, diversify vegetation in riparian zones, and aggrade sediment to increase stream productivity. As beaver populations have increased in urban areas across North America, their presence presents challenges and opportunities. Beaver can be integrated into the design of new and established urban green spaces to improve ecosystem functions. If managed properly, the conflicts that beaver sometimes create can be minimized. In this paper, we examine how landscape architects and restoration ecologists are anticipating the geomorphic and hydrological implications of beaver reintroduction in the design of wetlands and urban natural areas at regional and site levels. We present an urban beaver map and three case studies in Seattle, WA, USA, to identify various approaches, successes, and management strategies for integrating the actions of beaver into project designs. We make recommendations for how designers can capitalize on the benefits of beaver by identifying sites with increased likelihood of colonization, leveraging ecosystem engineers in design conception, designing site features to reduce constraints for the reintroduction and establishment of beaver, and anticipating and managing impacts. This article is categorized under: Water and Life > Conservation, Management, and AwarenessEngineering Water > Planning Water Urban beaver impact a designed wetland at Golden Gardens Park in Seattle, Washington, USA. [ABSTRACT FROM AUTHOR]