DeltaSense: Africa's remote sensing guardian of landscape degradation

Land degradation in East Africa poses significant challenges to ecosystem resilience and human wellbeing. While traditional monitoring approaches focus on direct land-use changes, we present DeltaSense, an innovative remote sensing tool that utilises inland lake deltas as sensitive indicators of regional landscape degradation. This newly funded project aims to expand the tool's coverage across the Democratic Republic of the Congo, Uganda, Rwanda, Burundi, Tanzania, and Mozambique, building upon a pilot study in the Lake Kivu region.

Our approach combines satellite time series analysis with ground-truth data to detect and monitor environmental changes across multiple spatial and temporal scales. Through collaboration with key regional institutions, including the Observatoire Volcanologique de Goma (OVG), Université catholique de Bukavu (UCB), Rwanda Water Resources Board (RWB), Mountains of the Moon University (MMU), and the Nelson Mandela-African Institute of Science and Technology (NM-AIST), the project will establish a comprehensive monitoring network throughout the Great Lakes region. This multi-institutional approach ensures robust local expertise and sustainable implementation across the target countries.

By analysing delta dynamics over 40 years, DeltaSense provides insights into the spatiotemporal patterns of land degradation. The tool integrates multiple satellite data sources with field measurements, including UAV imagery and bathymetric surveys, to validate and calibrate degradation assessments. This methodology enables the identification of degradation hotspots and evaluation of remediation practices.

Initial results from the Lake Kivu region demonstrate the tool's capability to detect various degradation drivers, including deforestation, agricultural expansion, violent conflicts and mining activities. The open-source platform facilitates collaboration between researchers, government agencies, and local communities, promoting evidence-based environmental management decisions.

This research represents a significant advancement in environmental monitoring by providing near real-time, actionable data for sustainable resource management. The approach's scalability and adaptability make it particularly valuable for regions facing similar environmental challenges globally, with potential applications extending beyond East Africa.