From Remote Sensing to Species Distribution Modelling: An Integrated Workflow to Monitor Spreading Species in Key Grassland Habitats

Remote sensing (RS) has been widely adopted as a tool to investigate several biotic and abiotic factors, directly indirectly, related biodiversity conservation. European grasslands are one of the most biodiverse habitats in Europe. Most these subject priority conservation measure, human-induced processes threaten them. The broad expansions few dominant species usually reported drivers loss. In this context, using Sentinel-2 (S2) images, we distribution spreading Central Apennine: Brachypodium genuense. We performed binary Random Forest (RF) classification B. genuense RS images field-sampled presence/absence data. Then, integrate occurrences obtained from into models identify topographic study area. Lastly, impact Natura 2000 (N2k) (Annex I Habitat Directive) was assessed by overlay analysis. RF process detected cover with an overall accuracy 94.79%. model shows that relevant variables influence slope, elevation, solar radiation, wet index (TWI) order importance. analysis 74.04% identified area falls on semi-natural dry grasslands. highlights model’s importance integrated workflow for mapping broad-expansion such coupled techniques presented work should apply other plant communities remotely recognizable characteristics more effective management N2k habitats.