Project

Partner Story

Client Success Story: McGovern Foundation

DevGlobal’s Jeff Pituch and James Haithcoat recently lead an effort to capture the processes and lessons learned by each grant partner organization of the Patrick J. McGovern Foundation’s 2022 Climate + Data Accelerator Program.

Photo of city taken from multistory building
Geospatial

Producing Global Training Dataset Labels

The ramp project is working with the World Health Organization to map healthcare buildings, a tool that will support humanitarian emergency response teams in the likelihood of the next pandemic. In this blog post, we discuss the labeling process, answering a fundamental question: How can we ensure generating high-quality labels working with remote teams?

Top-down drone-captured image of African town with computer generated rectangles over building rooftops
Geospatial

A Perfect Machine Learning Training Data Set?

“What is good enough” is a living question that has evolved over the span of the ramp project. It starts at the end, in defining our use case and engaging end-users as advisors to get an idea of how the model outputs will be utilized. Working backward in this way has allowed us to craft our approach to establishing training data guidance and quality assurance . . .