Developing a Predictive and Dynamic Moose-vehicle Collisions Model in Maine

• Main Author: Yu, Yue
• Format: Text
• Language: unknown
• Published: Digital Commons @ Colby 2019
• Subjects: Moose-vehicle Collisions; Maine; Moose (Alces alces); Maxent; Logistic Regression; Natural Resources and Conservation; Alces alces
• Online Access: https://digitalcommons.colby.edu/honorstheses/992; https://digitalcommons.colby.edu/context/honorstheses/article/1987/viewcontent/YuY_Honors_2019.pdf

Wildlife-vehicle collisions are a major form of human-wildlife conflict. Predictive animal-vehicle collision models have been developed to identify collision hotspots in Maine and guide mitigation strategies. However, most current models are static and unable to produce dynamic forecasts that incorporate changing climate and weather. The goal of my study was to develop a predictive and dynamic model of animal-vehicle collisions in Maine, USA. More than 6,700 moose-vehicle collisions (MVC) occurred from 2003 to 2017 in Maine, raising road safety, socio-economic, and wildlife conservation concerns. I sought to identify factors that contribute to a higher probability of MVCs by comparing two methodological approaches. I obtained 14 years of moose-vehicle collision data from Maine Department of Transportation. I developed a spatial MVC model using static spatial data. I then collaborated with the Bigelow Laboratory for Ocean Sciences to import temporal data in a Maximum Entropy (MaxEnt) model and create dynamic hourly MVC forecasts. My models show that MVCs in Maine are more likely to happen on roads with intermediate to high speed limits and volumes, in or near forest cover, and close to wetlands. Sunlight, snow depth, humidity, and soil moisture were also significantly associated with MVC probabilities. The result of this study suggests that predictive and dynamic MVC models can be developed to inform drivers of crash hotspots in Maine. Effectively applying these models allows for a more proactive, timely, and diagnostic response to MVCs and provides a novel approach to more comprehensively understand and predict human-wildlife conflicts.