Approximately 80 percent of the world’s species are insects. Insects are the most diverse group of animals on Earth and just parts of it has been found across the Earth. Scientists are combing artificial intelligence and advanced computer technology to identify insects across the Earth.
It is important to classify and count a lot of insects to study the biology of each species and its interactions with other species. This is a very time-consuming process that has largely limited scientists’ ability to gain insights into how insect life is influenced by external factors.
A paper published in the Proceedings of the National Academy of Sciences shows how insects can be classified and counted rapidly and effectively by advanced computer technology and artificial intelligence. For scientists, it is a big step forward to be able to understand how this essential community of insects evolves over time; for example, in response to habitat loss and climate change.
“With the help of advanced camera technology, we can now collect millions of photos at our field sites. When we, at the same time, teach the computer to tell the different species apart, the computer can quickly identify the different species in the images and count how many it found of each of them. It is a game-changer compared to having a person with binoculars in the field or in front of the microscope in the lab who manually identifies and counts the animals,” explains senior scientist Toke T. Høye from the Department of Bioscience and Arctic Research Centre at Aarhus University, who headed the new study.
The methods discussed in the paper refer to the umbrella term deep learning and are types of artificial intelligence often used in other fields of research, such as driverless car development. However, researchers have now shown how technology can be an alternative to the laborious task of manually studying insects in their natural habitat, as well as the tasks of sorting and identifying insect samples.
“We can use deep learning to find the needle in the hay stack so to speak — the specimen of a rare or undescribed species among all the specimens of widespread and common species. In the future, all the trivial work can be done by the computer and we can focus on the most demanding tasks, such as describing new species, which until now was unknown to the computer, and to interpret the wealth of new results we will have” says Toke T. Høye.
One thing is the lack of good databases to compare unknown species with those that have already been identified. The researchers hope to be able to advance knowledge about insects rapidly with deep learning.
Futhermore, observations are needed to be made in the same place and in the same way for a long period of time to understand how insect populations evolve over time.
Mounting cameras in the same place and taking pictures of the same local area is a simple process. Cameras can take a photo every minute. This will include stacks of data that will educate people over the years about how insects respond to warmer temperatures or the changes caused by land management. These knowledges may become an essential instrument for maintaining a proper balance between human use and protection of natural resources.
Image Source: GreenBiz