A new report in the journal Ecological Informatics presents the findings of a team of scientists at the University of Alaska Fairbanks who applied machine learning techniques to shed light on changes in the habitat of short-billed gulls.

Gulls are usually found on seashores and near waterways such as lakes and rivers, where they hunt for insects, small rodents, fish or birds. The researchers observed that between May and August, short-billed gulls entered areas usually visited by opportunistic crows. These birds have adapted to urban environments and are often seen in grocery store and food court parking lots, around man-made areas such as gravel construction sites, and near trash cans.

A Machine Learning Study Has Shown That Seagulls Are Changing Their Natural Habitat To An Urban OneThis ground-breaking study collected a dataset over three years using community-provided observations that recorded the abundance of seagulls, along with other birds, found on the arctic fringes of Alaska’s cities. The findings highlight how these birds moved into urban settings. Lead author and UAF professor Falk Hüttmann and his group used predictive machine learning algorithms with location-dependent environmental variables to obtain information about sightings of these gulls. This innovative approach is based on previous studies of the habitat conditions of the great gray owl.

Important to this analysis were US Census data and local city statistics, which included measures of proximity to freeways, restaurants, bodies of water, and waste management facilities. “Combining economic and demographic data, as in the US Census, is a significant advance,” said Maurice Steiner, Ph.D. candidate under Gutman. “This allows us to create mappings that are closer to real-life conditions by integrating these factors into our predictive models.”

The study’s findings suggest that seagulls are flocking to urban landscapes, lured by the presence of human-related food and the changes caused by urban development. “These birds use excess human waste,” confirmed Hettmann of UAF’s Arctic Biology Institute.

Short-billed gulls, which were previously considered unclean gulls until they were reclassified in 2021, are versatile and able to adjust their diet. Although they can find plenty of food in garbage dumps and excavation sites, such food can shorten their lives or even be fatal. Eating readily available junk, especially from fast food restaurants, puts their health at risk due to high levels of sodium, fat, sweets, oil and pollutants. Seagulls can signal health problems in an ecosystem because they carry diseases.

The study recorded an increase in the number of pathogens where these gulls gather, sometimes observing groups of up to 200 individuals, especially during the summer season. Diseases such as bird flu and salmonellosis can be spread by seagulls, some strains of which are contagious to humans. Historical evidence from an independent investigation indicates that a salmonella outbreak linked to seagulls began in 1959 in North America in Ketchikan.

Seagulls became the main carriers of diseases. “Our results essentially reflect disease pools that overlap with areas of human activity,” said Gutmann, also a professor in the UAF College of Science and Mathematics. According to Guttman, these discoveries highlight the transient nature of “wilderness.” “Findings like these offer a broader understanding of the impact of human actions on the environment, affecting what we traditionally think of as ‘natural.’ Hopefully, the use of advanced data analysis, such as machine learning, can contribute to conservation,” said Gettmann.

Other posts

  • Best Practices for Labeling Your Training Data
  • An Evolutionary Model Of Mental State Transition Improves Emotion Tracking In Machine Learning Algorithms
  • The Role Of Gradient Boosting Machines In State-Of-The-Art Machine Learning
  • Phishing Campaign Simulation: Enhancing Cybersecurity Preparedness
  • Machine Learning In Sentiment Analysis
  • Adaptive Learning
  • Humorists Check LLM Joke Writing Skills
  • Sony Introduces An AI Tool For Single-Instrument Accompaniment While Creating Music
  • What Is Autoencoder In Machine Learning
  • AI Stability Introduces A New Model Of Sound Generation