GeoPython2019 speaker: Freja Hunt
My academic background is in machine learning for climate and meteorology, but I have applied my knowledge to develop commercial data products for sectors as varied as online advertising, agri-food, satellite communications, landfill management, and now humanitarian aid as part of the team at the Flowminder Foundation.
Automating the definition and optimization of census sampling areas
Traditionally, census sampling area definition is done by manually digitising small geographic units on high-resolution satellite imagery or by physically walking the boundaries of sample areas; methods which are highly time, cost and labour intensive. This presentation focuses on a method implemented in Python to automate the definition and optimization of census sampling areas using digitized natural and man-made geographic features and high-resolution gridded population estimates.