Location
https://www.kennesaw.edu/ccse/events/computing-showcase/sp25-cday-program.php
Streaming Media
Document Type
Event
Start Date
15-4-2025 4:00 PM
Description
This project examines the impact of climate change on bird migration patterns by integrating bird observation data from eBird with climate data from the NOAA Global Historical Climate Network (GHCN). Focusing on species such as the Arctic Tern, the study analyzes changes in migration timing, routes, and population trends over recent decades. Migration paths were visualized using QGIS, while MODIS land cover data helped assess habitat changes along these routes. Temporal analysis revealed noticeable shifts in migration timing, with earlier arrivals in some regions correlating with rising temperatures and changing precipitation patterns. For future predictions, CHELSA climate data was combined with machine learning models, including Gradient Boosting and Random Forest, to forecast migration behavior under different climate scenarios. The results highlight critical stopover sites increasingly threatened by habitat loss, emphasizing the need for targeted conservation efforts to support migratory species adapting to a changing climate.
Included in
GRM-118 Analysis of Climate Change Effects on Bird Migration Patterns Using Long-Term Data
https://www.kennesaw.edu/ccse/events/computing-showcase/sp25-cday-program.php
This project examines the impact of climate change on bird migration patterns by integrating bird observation data from eBird with climate data from the NOAA Global Historical Climate Network (GHCN). Focusing on species such as the Arctic Tern, the study analyzes changes in migration timing, routes, and population trends over recent decades. Migration paths were visualized using QGIS, while MODIS land cover data helped assess habitat changes along these routes. Temporal analysis revealed noticeable shifts in migration timing, with earlier arrivals in some regions correlating with rising temperatures and changing precipitation patterns. For future predictions, CHELSA climate data was combined with machine learning models, including Gradient Boosting and Random Forest, to forecast migration behavior under different climate scenarios. The results highlight critical stopover sites increasingly threatened by habitat loss, emphasizing the need for targeted conservation efforts to support migratory species adapting to a changing climate.
