Computer vision for assessing species color pattern variation from web-based community science images
Maggie M. Hantak, Robert Guralnick, Alina Zare, Brian J. Stucky
Abstract
). We used an ensemble convolutional neural network model to analyze this polymorphism in 20,318 iNaturalist images. Our model was highly accurate (∼98%) despite image heterogeneity. We used the resulting annotations to document extensive niche overlap between morphs, but wider niche breadth for striped morphs at the range-wide scale. Our work showcases key design principles for using machine learning with heterogeneous community science image data to address questions at an unprecedented scale.
Topics & Concepts
Convolutional neural networkWorkflowComputer scienceData scienceArtificial intelligenceDatabaseSpecies Distribution and Climate ChangeAmphibian and Reptile BiologyWildlife Ecology and Conservation