Year of Award
Master of Science (MS)
Department or School/College
W.A. Franke College of Forestry and Conservation
Marco Maneta, Paul Lukacs
Machine Learning, Aquatic Invasive Species
University of Montana
The urgent decision-making needs of invasive species managers can be better met by the integration of biodiversity big data with large-domain models and environmental data products in the form of new workflows and tools that facilitate data utilization across platforms. Timely risk assessments allow for the spatial prioritization of monitoring that could streamline invasive species management paradigms and invasive species’ ability to prevent irreversible damage, such that decision makers can focus surveillance and intervention efforts where they are likely to be most effective under budgetary and resource constraints. I present a workflow that generates rapid spatial risk assessments on aquatic invasive species by combining occurrence data, spatially explicit environmental data, and an ensemble approach to species distribution modeling using five machine learning algorithms. For proof of concept and validation, I tested this workflow using extensive spatial and temporal occurrence data from Rainbow Trout (RBT; Oncorhynchus mykiss) invasion in the upper Flathead River system in northwestern Montana, USA. Due to this workflow’s high performance against cross-validated datasets (87% accuracy) and congruence with known drivers of RBT invasion, I developed a tool that generates agile risk assessments based on the above workflow and suggest that it can be generalized to broader spatial and taxonomic scales in order to provide data-driven management information for early detection of potential invaders. I then use this tool as technical input for a management framework that provides guidance for users to incorporate and synthesize the component features of the workflow and toolkit to derive actionable insight in an efficient manner.
Carter, Sean C., "FACILITATING AQUATIC INVASIVE SPECIES MANAGEMENT USING SATELLITE REMOTE SENSING AND MACHINE LEARNING FRAMEWORKS" (2022). Graduate Student Theses, Dissertations, & Professional Papers. 11873.
© Copyright 2022 Sean C. Carter