Reproduce “Detecting and Tracking Communal Bird Roosts in Weather Radar Data” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zezhou Cheng, Saadia Gabriel, Pankaj Bhambhani, Daniel Sheldon, Subhransu Maji, Andrew Laughlin, David Winkler
The system detects and tracks bird roost exoduses in weather radar images, modeling annotator-specific box-radius differences with variational EM. It links detections across scans and uses auxiliary data to filter some false positives. Applied to 419,000 scans from 86 eastern-US stations, it maps seasonal roost locations; full-test MAP rises from 44.2% to 45.5%, a modest gain in this case study.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.