Below is a press release about the Methods in Ecology and Evolution article ‘Identifying animal species in camera trap images using deep learning and citizen science‘ taken from the University of Minnesota-Twin Cities.
The computer’s accuracy rates for identifying specific species, like this warthog, are between 88.7 percent and 92.7 percent. ©Panthera
For more than a decade, citizen science projects have helped researchers use the power of thousands of volunteers who help sort through datasets that are too large for a small research team. Previously, this data generally couldn’t be processed by computers because the work required skills that only humans could accomplish.
Now, computer machine learning techniques that teach the computer specific image recognition skills can be used in crowdsourcing projects to deal with massively increasing amounts of data—making computers a surprising new partner in citizen science projects.
Species Surveys: New Opportunities and Ongoing Data Challenges
Technologies, such as drones, open new opportunities for wildlife monitoring ©J. Lahoz-Monfort, UMelb.
Monitoring is a fundamental step in the management of any species. The collection and careful analysis of species data allows us to make informed decisions about management priorities and to critically evaluate our actions. There are many aspects of a natural system that we can measure and, when it comes to monitoring the status of species, occurrence is a commonly used metric.
Ecologists have a long history of collecting species occurrence data from systematic surveys and our ability to gather species data is only going to grow! This is partly enabled by the fact that citizen science programs are starting to gain a prominent role in wildlife monitoring. There’s a growing recognition that well-managed citizen science surveys can produce useful data, while scaling up monitoring effort thanks to the increased human-power from large numbers of committed volunteers. Continue reading