Predicting Opuntia stricta (Haw.) in arid and semi-arid environment of Kenya using Sentinel imagery and ensemble machine learning classifiers

To ensure effective management of Alien plant species especially the invasive demands for knowledge of their spatial availability. The use of satellite remote sensing tools has increasingly provided potential ways to assess spatial availability as compared to the traditional ways that are inadequate to provide similar information in a detailed way. The Copernicus Sentinel satellite images with a high spatial resolution and easy access at no charge provides an opportunity for mapping the spatial variability at a regional scale and in a detailed manner. In this study, we assess the potential of Sentinel 2 images vegetation indices and using ensemble machine learning techniques, map the spatial variability of invasive species (Opuntia stricta) in an arid and semi-arid region of Kenya. To actualize this, we use Sentinel 2 bands and thirty-one vegetation and elevation indices for classification. Field data collected is divided into two (training & validation) and used to get the best model to classify Opuntia stricta and eight other control classes. The best performing model and the highest contributing features are selected for final Opuntia stricta estimation. The random forest algorithm yields the highest accuracy 89% hence is used to classify Opuntia stricta species. Our observation of the overall results indicates that Sentinels in combination with the indices characterized by spatial resolution provide an importance that can be used to discriminate Opuntia stricta species hence providing an opportunity for long term monitoring and management at a fairly acceptable accuracy hence ensuring limited pasture degradation. Therefore, future research should focus on exploring Sentinel time-series images for estimating Opuntia stricta species at a temporal variability.