skip to content

Department of Computer Science and Technology

Friday, 28 July, 2023 - 13:00 to 14:00
Amandine Debus
FW 11, William Gates Building. Zoom link:


Deforestation rates in sub-Saharan Africa have received less attention than those in other tropical regions, despite evidence for increasing rates in the last twenty years. For example, in Cameroon, forests are threatened by foreign investments in large agro-industrial concessions, the expansion of small-scale agriculture, and increasing mining activity. However, there is a current lack of a detailed and comprehensive automated classification for the land-use changes leading to deforestation, which is crucial to prioritise interventions. Earth observation (EO) and deep learning offer a promising solution for effective monitoring, but, so far, proposed approaches in the Congo Basin have not been able to go beyond ‘broad’ categories of deforestation drivers and are not adapted to country-specific dynamics. In this talk, I present the challenges faced when building a newly-consolidated satellite imagery reference dataset for Cameroon and a new approach to automatically classify direct drivers of deforestation for this case study.

Amandine Debus is a second-year PhD student in the Department of Geography. Amandine’s PhD focuses on using high-resolution optical (e.g. PlanetScope) satellite data, machine learning and deep learning techniques, and socio-economic data (e.g. governance, demographic) to better understand and monitor land-use changes in sub-Saharan Africa. Using Cameroon as a case study, Amandine’s project aims to model the spatial and temporal dynamics of transitions from forest to multiple land-use types, and the socio-economic drivers behind them. She is working with the International Institute for Sustainable Development (IISD) and in-country partners to ensure her models are tailored to maximise their reusability for ongoing policy-making and conservation programmes.


Seminar series: 
Energy and Environment Group