Mapping schools in Sudan using artificial intelligence

Sudan has no centralized information on more than half of its public schools. Conventional methods of gathering information, such as field visits, are costly and time-consuming in such a large country, especially for schools in remote and insecurity-prone areas. To help address this, Giga collaborated with the team behind the world’s biggest open-source artificial intelligence (AI) library, OmdenaLore, to develop a model to identify school locations.

Omdena ran the project as a six-week challenge involving 52 volunteers. Participants were given a geo-diverse, high-resolution satellite image of Sudan and some school location data points. They then trained the AI how to distinguish between schools and other types of building. The resulting model was able to determine the precise location of schools and their boundaries with 95% accuracy – a high rate for this type of model.

Many children in Sudan are not able to enjoy the benefits of online learning as school connectivity levels are very low. Mapping can help address this problem by providing insights for the planning and roll-out of connectivity infrastructure. The Omdena exercise will therefore contribute to improving the state of education in Sudan which is affected by challenges like the high number of out-of-school children, a lack of teaching materials and inadequate facilities.