Mapping Opuntia stricta in the Arid and Semi-Arid Environment of Kenya Using Sentinel-2 Imagery and Ensemble Machine Learning Classifiers

Globally, grassland biomes form one of the largest terrestrial covers and present critical social–ecological benefits. In Kenya, Arid Semi-arid Lands (ASAL) occupy 80% landscape are for livelihoods millions pastoralists. However, they have been invaded by Invasive Plant Species (IPS) thereby compromising their ecosystem functionality. Opuntia stricta, a well-known IPS, has ASAL in Kenya poses threat to pastoralism, leading livestock mortality land degradation. Thus, identification detailed estimation its cover is essential drawing an effective management strategy. The study aimed at utilizing Sentinel-2 multispectral sensor detect stricta heterogeneous Laikipia County, using ensemble machine learning classifiers. To illustrate potential Sentinel-2, detection was based on only spectral bands as well combination with vegetation topographic indices Extreme Gradient Boost (XGBoost) Random Forest (RF) classifiers abundance. Study results showed that overall accuracies Sentinel 2 were 84.4%, while combined bands, vegetation, 89.2% 92.4% XGBoost RF classifiers, respectively. inclusion enhance characterization biological processes, minimize influence soil effects atmosphere, contributed improving accuracy classification. Qualitatively, spatially found along river banks, flood plains, near settlements but limited forested areas. Our demonstrated sensors effectively map complex ASAL, which can support conservation rangeland policies aim list threatened areas, conserve biodiversity productivity ecosystems.