Tag
This paper presents the first machine learning study for crop yield forecasting in Sierra Leone, finding that combining freely available satellite climate data (CHIRPS, NASA POWER) with national crop statistics reduces forecast error by a third compared to persistence, though crop statistics alone are insufficient.
Google DeepMind's study in Sierra Leone shows that using Gemini as a pedagogical tool improved math scores and student engagement, with students increasingly using AI to understand concepts rather than just find answers.
Google DeepMind's latest research explores how AI can support educators in Sierra Leone, where a growing student population outstrips available teachers, aiming to amplify teachers' reach without replacing their expertise.
A pre-registered trial in Sierra Leone found that AI-powered Guided Learning significantly improved math scores, achieving 1.2 to 1.7 years of progress in eight weeks, while teachers reported enhanced professional growth and a shift toward facilitation roles.