models

Publications

Leveraging machine learning and accelerometry to classify animal behaviors with uncertainty

Animal-worn sensors, especially accelerometers, are increasingly used with machine-learning models to identify animal behaviors. These tools often struggle with uneven training data, uncertain predictions, and noisy results. To address these issues, Dr. Rafiq and Dr. Abrahms, with their collaborators, developed an open-source method that combines machine learning and statistical techniques to improve behavior classification and to provide “prediction sets,” which […]

, , , ,
An African wild dog looks towards the camera through green leaves.Publications

A spatial capture–recapture model for group-living species

Animals that live in groups can affect their populations and ecosystems in complicated ways, so scientists need good methods to measure how many groups there are, how big they are, and how many individuals live in them. Traditional spatial capture–recapture (SCR) methods can estimate either group density or individual density, but they often give biased results for group-living species because

, , ,
Publications

An integrated path for spatial capture–recapture and animal movement modeling

Ecologists use spatial capture–recapture (SCR) models to study whole animal populations and movement models to study how individual animals behave. Even though individual movement shapes population patterns, these two approaches have mostly been developed separately. Movement models usually focus only on individuals, while SCR models focus on populations but simplify how animals move. The authors argue that combining these two

, ,
Scroll to Top