There are about one million known species of insects – more than for any other group of living organisms. If you need to determine which species an insect belongs to, things get complicated quick. In fact, for distinguishing between certain kinds of species, you might need a well-trained expert in that species, and experts’ time is often better spent on something else. This is where CNNs (convolutional neural networks) come in nowadays, and this paper describes a CNN doing just as well if not better than human experts.
Identifying new species is key to the work of zoologists around the world. It’s an exciting part of research into the natural world, and being the first to discover a new species often grants a scientists naming rights that can create a legacy of one’s work that lasts long into the future.
Traditionally, the work of taxonomy involved capturing and preserving an example of the new species. This is such that it could be classified properly and studied in detail by scientists working now and in the future. However, times are changing, and scientists are beginning to identify new species on the basis of videos and photos instead.