Accurate maps of canopy height (CH) and aboveground biomass (AGB) are needed for monitoring forests over large regions. Producing such data is particularly challenging over the complex, diverse and dense humid tropical forests of Africa where signal saturation observed from optical and radar satellites and complex responses in LiDAR data require advanced mapping techniques to capture high biomass and tall height values. Here, we trained a deep learning (U-Net) model to generate the first annual maps (2019–2022) of top CH at 10 m resolution over the African dense forest region, using Sentinel-1/-2 images trained on LiDAR-derived height data from the Global Ecosystem Dynamics Investigation mission (GEDI).
It was a privilege to contribute as a panel member at the ECDPM event on “AI for Social Good and Africa’s Strategic Choices”!
It was a critical conversation about balancing AI innovation with the governance and strategic choices necessary for Africa’s equitable development. Thank you to my fellow panelists for the rigorous exchange: Melody Musoni, PhD, Jane Munga, Amb - Prof Bitange Ndemo, and Maja Fjaestad. And special thanks to Chloe Teevan for moderating!
Machine learning data for natural scenes and underrepresented landscapes
We present an analysis ready segmentation dataset of street level images of natural underrepresented landscapes for use in earth observation based products.
BlueGreen Labs position on ChatGPT and the use of Large Language Models (LLM) in science