Camera trap based small rodent monitoring: Data from Norwegian alpine tundra

The images are processed using the semi-automatic workflow established by Böhner et al. (2023). We use a pre-trained machine learning algorithm to automatically classify all images.

Images classified with low confidence or from species/species groups that are challenging are manually annotated. Abundance indices can be estimated following temporal and spatial aggregation of detection events following Kleiven et al. 2023. Data have been standardized to Darwin Core using the camtrapdp R package and only include observations (and associated media) of animals.