When artificial intelligence (AI) is paired with today’s smartphone applications, it can do things like identify plant species with high accuracy and help detect ecological change. All of this can be done by anybody, so there is no need for specialized training, and it provides us with more opportunities to gather information on environmental conditions.
Researchers from the German Centre for Integrative Biodiversity Research (iDiv), the Remote Sensing Centre for Earth System Research (RSC4Earth) of Leipzig University (UL) and Helmholtz Centre for Environmental Research (UFZ), the Max Planck Institute of Biogeochemistry (MPI-BGC) and Technical University IImenau set out to determine the reliability of this data.
The researchers collected and analyzed data from the mobile app Flora Incognita in Germany and compared it to the FlorKart database of the German Federal Agency for Nature Conservation (BfN), which contains data collected by more than 5,000 floristic experts over 70 years.
Detecting Macroecological Patterns
According to the researchers, they were able to uncover macroecological patterns in Germany with the collected data, and it was similar to the data of German flora inventory data. When the researchers compared the two data sets, however, they found major differences between the Flora Incognita data and the long-term inventory data in regions that have a low human population density.
Dr. Jana Wäldchen is lead author from MPI-BGC and one of the developers of the mobile app.
“Of course, how much data is collected in a region strongly depends on the number of smartphone users in that region,” said Wäldchen.
Because of this, there were deviations in the data depending on where it came from, such as rural areas and tourist destinations.
Another impacting factor is user behavior, which influenced the types of plant species recorded by the app.
“The plant observations carried out with the app reflect what users see and what they are interested in,” Wäldchen continued.
Users have the tendency to record common and conspicuous species more often than rare ones, but despite that being the case, the researchers could still reconstruct familiar biogeographical patterns due to the amount of plant observations. The researchers looked at a total of more than 900,000 data entries.
Biodiversity and Environmental Research
The new development could have big implications for biodiversity and environmental research.
Miguel Mahecha is first author and professor at UL. He is also an iDiv member.
“We are convinced that automated species recognition bears much greater potential than previously thought and that it can contribute to a rapid detection of biodiversity changes,” said Mahecha.
According to the team, apps such as Flora Incognita could enable the detection and analysis of ecological changes all around the globe in real time.
Patrick Mäder is co-author and professor at TU IImenau.
“When we developed Flora Incognita, we realized there was a huge potential and growing interest in improved technologies for the detection of biodiversity data. As computer scientists we are happy to see how our technologies make an important contribution to biodiversity research,” Mäder said.