DrivenData is hosting the Open AI Caribbean Challenge now through December 23, 2019.
Azavea partnered with the World Bank and WeRobotics to create a dataset of aerial drone imagery of buildings across the Caribbean annotated with characteristics that matter to building inspectors. Many parts of the Caribbean contain houses and buildings that are not up to modern construction standards. Residents of these areas are especially vulnerable to risk from natural disasters.
The challenge is to use machine learning on this dataset to classify roof construction material on the identified buildings in St. Lucia, Guatemala, and Colombia. Using machine learning models to accurately map disaster risk from drone imagery would save precious time and millions of dollars, and enable experts to quickly and effectively target resources for disaster preparation where they will have the most impact.