Mapping Lantana camara and Leucaena leucocephala in Protected Areas of Pakistan: A Geo-Spatial Approach

Invasive alien plants are considered as one of the major causes loss native biodiversity around world. Remote sensing provides an opportunity to identify and map invasive species using accurate spectral information. The current study was aimed evaluate PlanetScope (3 m) Sentinel (10 datasets for mapping distribution in two protected areas Pakistan, machine learning (ML) algorithms. multispectral data were analysed with following four ML algorithms (classifiers)—random forest (RF), Gaussian mixture model (GMM), k-nearest neighbour (KNN), support vector (SVM)—to classify species, Lantana camara L. (common lantana) Leucaena leucocephala (Ipil-ipil) Dzetsaka plugin QGIS used these all RF, GMM, SVM more at detecting both when imagery rather than Sentinel. Random produced highest accuracy 64% data. most dominating plant 23% cover, represented thematic maps. leucocpehala by 7% cover mainly distributed southern end Jindi Reserve Forest (Jhelum). It not possible discriminate Dodonea viscosa Jacq. (Snatha) classifier Overall, slightly better term discrimination. These findings provide a reliable estimation status would be helpful land managers prioritize invaded their effective management.