Researchers have predicted the population trends of birds worldwide by using the combined power of big data and machine learning and published their study in Ibis.
Machine learning is a type of artificial intelligence wherein the computer itself learns key points about the given data points through training and once done, it can repeat the tasks on completely unknown data points without manual intervention. Scientists predicted population declines for bird species with unknown population trends and used correlation analyses to identify predictors of bird population declines worldwide.
After training and testing their machine learning model on data from 10,163 species with known population trends, the researchers estimated that nearly half (47%) of the 801 bird species with currently unknown population trends are declining.
Correlation analyses suggested that globally, the top predictor associated with bird population declines was a severely fragmented population, with non-migratory birds in South American and Southeast Asian tropical and subtropical forests being particularly vulnerable.
“I see endless possibilities for conservation biology when artificial intelligence is brought into the picture, and we are still not exploring enough,” said lead author Xuan Zhang, of Bird Ecology and Conservation Ontario.
Despite the lack of long-term quantitative population trend data for all species worldwide, our study presents big data and machine learning as a useful tool for informing conservation priorities, lending insight, albeit imperfect, into bird population declines on the global scale for the first time.
