Radiant Earth Foundation and RCMRD to Develop Joint Capacity Building Program focused on Machine Learning for Earth Observation in Africa

Radiant Earth and the Regional Centre for Mapping of Resources for Development (RCMRD) partnership aims to strengthen local geospatial and machine learning expertise for addressing global challenges in Africa.

Radiant Earth
Radiant Earth Insights
3 min readNov 8, 2021

--

Radiant Earth Foundation today announced a new partnership with the Regional Centre for Mapping of Resources for Development (RCMRD). This partnership will establish capacity building opportunities in geospatial analysis and machine learning (ML) for entities within RCMRD’s twenty Member States in Eastern and Southern Africa.

Radiant Earth is the leading nonprofit dedicated to open Earth observation (EO) training data, standards, and tools. They deliver an ecosystem of high-quality data on an open repository, Radiant MLHub, to advance the application of ML techniques on satellite imagery in addressing global challenges. Radiant also provides resources around Radiant MLHub, such as best practices, tutorials, data competitions, and training programs to demonstrate applying the data and building solutions. RCMRD, an intergovernmental organization supported by the African Union, seeks to strengthen Member States’ capacity to adopt geoscience and allied technologies for sustainable development.

Big Earth data derived from satellites can leverage the advances of artificial intelligence (AI) to effectively measure and monitor the Sustainable Developments Goals (SDGs). Various examples showcase how these technologies can predict crop yield (Goal 2, Zero Hunger) or identify wildfire risk areas for mitigation purposes (Goal 13, Climate Action), to name a few only. But a geographical data divide, availability and access to ML-ready training data, and a critical mass of localized expertise remain barriers to the effective use of satellite data with AI. Based on a recent report that captures best practices for collaboration on data in the agriculture sector, developing skills to use big data and new technologies is one of the key drivers to create effective data ecosystems locally.

Earlier this year, Radiant Earth and Makerere University successfully led a virtual training of trainers bootcamp for participants in Africa, teaching how to use ML with satellite data technologies to deploy innovative applications. Feedback from participants reinforced the need to expose and share data and tools with practitioners worldwide, especially with those in regions underrepresented on the global stage. Providing hands-on training and setting up a community of practice around ML for EO in Africa was applauded. The GIZ FAIR Forward program sponsored this bootcamp.

“We’re pleased to partner with RCMRD to expand ML for EO skills and knowledge in Africa,” says Hamed Alemohammad, Executive Director and Chief Data Scientist at Radiant Earth. “Improving the ability of more individuals and organizations to adopt and use geospatial data with ML algorithms is an effective way to building hubs of local expertise that can collaborate and innovate on deploying solutions for development challenges. This partnership builds upon our efforts of connecting local and international experts in support of the SDGs.”

Kenneth Kasera, user engagement lead at RCMRD is quoted saying, “Harnessing the potential in big data — both spatial and non-spatial — is critical in making sense out of the Earth systems and the interactions thereof. With data being collected and analyzed for various applications geared towards improving the quality of life, many aspects always focus on the workflows. Therefore, building the capacity of institutions and individuals in machine learning is considered a plus as we all forge ahead within the context of the 4th Industrial Revolution.”

For updates on the capacity building program, sign up for Radiant Earth’s quarterly email newsletter or follow us on Twitter, LinkedIn, and Medium.

--

--

Radiant Earth
Radiant Earth Insights

Increasing shared understanding of our world by expanding access to geospatial data and machine learning models.