Radiant Earth Foundation, a nonprofit empowering organizations with open geospatial training data, models, and metadata standards, has been supporting the ramp project’s labeling efforts for building rooftops. Producing building footprint data is a methodical task that requires polygons to be labeled over satellite and drone imagery, usually by hand on a computer, to provide context or confirm the details of each polygon. The labels paired with the imagery become the training data inputs for a building footprint extraction model. 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?

How Radiant MLHub strengthens the data collection to analytics pipeline for agriculture projects.

Radiant Earth Foundation is strengthening geospatial machine learning (ML) workflows for organizations working on agriculture projects by streamlining the process, from ground reference data collection to insight analytics, through Radiant MLHub.

Radiant MLHub is an open-access library dedicated to geospatial training data and ML models. Since its inception in 2019, Radiant has focused on developing and aggregating geo-diverse benchmark data that practitioners can use to create applications and enable data-driven policies that impact lives worldwide. The datasets vary from…

Describing ML Models with the Geospatial Machine Learning Model Catalog (GMLMC).
During the height of the COVID-19 pandemic, the government of Togo launched a program to “boost national food production in response to the COVID-19 crisis by distributing aid to farmers”1. To accomplish this, the government needed accurate information about the distribution of smallholder farmers throughout the country. This kind of cropland map did not exist for the country, so they worked with NASA Harvest to rapidly develop a cropland map using AI. Finding enough high-resolution labeled training data to train the machine learning model was also a significant challenge, so the team combined global and local crowdsourced labels collected using the Geo-Wiki platform2 with hand-labeled imagery in targeted areas to train a new model for predicting crop areas.