Tracking Rangeland Degradation from Prosopis Invasion in Kenyan Rangeland: A Multi-Source Approach Combining Remote Sensing, Machine Learning and Citizen Science

The invasion of Prosopis juliflora poses a growing threat to dryland ecosystems and pas-toral livelihoods across East Africa. This study presents an integrative approach that combines satellite remote sensing, machine learning, and participatory GIS (PGIS) to de-tect and map the spatial extent and socio-ecological impacts of Prosopis juliflora in Baringo County, Kenya. We evaluated the performance of three satellite platforms, Sentinel-1, Sentinel-2, and PlanetScope, using a Random Forest classifier trained on field-collected presence–absence data and vegetation indices. Sentinel-2 outperformed the other sensors, achieving a classification accuracy of 90.65%, with key variables including Visible At-mospherically Resistant Index (VARI), Ratio Vegetation Index (RVI) and red-edge bands emerging as the most important predictors. To enhance contextual understanding and validate remote sensing outputs, we conducted PGIS sessions with gender-disaggregated community groups, capturing local perceptions of invasion hotspots and blocked access to grazing routes and water sources. The comparison of satellite-derived maps and PGIS outputs revealed strong spatial congruence, particularly along water bodies, roads, and croplands. Our findings demonstrate the potential of combining Earth observation and citizen science to generate actionable knowledge for managing invasive species in da-ta-scarce dryland environments. This hybrid framework supports inclusive and spatially targeted interventions for rangeland restoration and ecosystem resilience.