A number of people have been kind enough to ask me about my research, so I thought I'd share a non-technical summary. The challenge with the topic is that it's intersectional, and for the quantitative research aspect, it's very difficult to give an accessibly short answer that doesn't start to talk about convolutional neural networks, knowledge distillation and the properties of edge computing and spectral imaging.
What follows is my pre-research and ethics approval summary designed for a non-specialist audience. It has been included in a scientific poster for use at conferences before results are available.
As an aside, the purple image is the backdrop of a large forest fire in the Pacific North West, colour adjusted to fit UCL branding and used as a backdrop on the scientific poster. The contouring is visual adornment for interest, not an actual cartographic treatment.
Why does wildfire matter?
Climate change has fundamentally altered fire regimes globally, transitioning wildfire from a localised hazard to a systemic global risk. Sub-Saharan Africa (SSA) accounts for 70% of all global burned area.
Emergent next-generation fire-focused satellites now deliver data at resolutions, revisit intervals, and at times of day that were previously impossible. Onboard AI eliminates detection latency, processing wildfire data directly in orbit.
Machine learning models applied to African savanna fires were built elsewhere. Calibrated on different ecologies, fuels and fire intensities – and built, above all, for suppression. In SSA savannas, fire is also integral to landscape management and embedded in traditional cultural practices.
External models not only underperform but misinterpret, producing the wrong governance response.
The problem compounds institutionally. Fire governance across Sub-Saharan Africa was not designed to integrate AI tools, and has historically marginalised local knowledge most relevant to managing fire effectively.
