After being nearly hunted to extinction, followed by decades of sanctioned trapping, beavers are now increasingly recognized as solutions to a number of sustainability challenges – from water storage to fire and flood suppression to biodiversity. However, the massive growth in beaver populations is not without risk. In addition to nuisance flooding and infrastructure damage, beavers alter the hydrology of river corridors in complex ways that may change the water balance (increased evapotranspiration) and impact water quality (increased stream temperatures and metal release). Thus, although beavers are profound ecological engineers, they are not always compatible with human infrastructure. This project will address the role of North American beaver as a sustainable ecological solution by adapting approaches from computer vision to (1) recognize the ecological patterns (networks of channels, ponds, lodges, vegetation structure) of beaver activity and (2) distinguish legacy structures from recent activity using patterns of roughness, brightness, continuity and vegetation. If the ecological patterns can be learned, then we can advance to the next stage of evaluating the beaver as a tool for fostering sustainable waterways.

Luwen Wan
Luwen Wan
Postdoctoral Fellow

I am passionate about using data science, process-based modeling, remote sensing and machine/deep learning to explore how land use, climate change, and management impact water sustainability across diverse landscapes, and from watershed, regional to global scales.