Species classification data identifies and records the plant and animal species found in the wild.
Both professionals and laypeople contribute to species classification data with images from various sources. Professionals may use high-tech images from satellites, LiDAR, and more. Lay people, meanwhile, submit images from ordinary cameras and smartphones to public, open-source databases.
Species classification data consists of images and the data about them, especially date, location, and species. Either humans or machine learning programs can assign this information to the images.
Animal and plant classification data has a wide range of uses, including education, entertainment, research, and conservation.
The main concerns with species classification data is image quality and the lack of images for certain less-common species. For both humans and machine learning programs, the smaller numbers of uncommon species images for training samples leads to greater rates of incorrect identification.
An additional concern for machine learning programs is that the sub-field of image recognition is still new and not without problems.
iNaturalist
GBIF: Global Biodiversity Information Facility
Social media sites now make up a major source of the publication of newly discovered species. These users of these sites also monitor the behavior and life cycles of these species, much like professionals track wildlife. Furthermore, scientists have begun “creating programs to answer questions about spiders and recruit volunteers to find bumblebees or collect forest pests.”
The Conversation: The next invasion of insect pests will be discovered via social media
However, during the past two decades, a variety of commercial satellites have begun to collect data at a higher spatial resolution, capable of capturing ground objects measuring one square metre or less. This resolution improvement places the field of terrestrial remote sensing on the threshold of a fundamental leap forward: from focusing on aggregate landscape-scale measurements to having the potential to map the location and canopy size of every tree over large regional or global scales. This revolution in observational capabilities will undoubtedly drive fundamental changes in how we think about, monitor, model and manage global terrestrial ecosystems.