Spatio-temporal assessment of Toumeyella parvicornis spread in mediterranean coastal pine forests through sentinel-2 data
Description
Mediterranean coastal pine forests provide important ecological and cultural benefits but are increasingly threatened by climate change, urbanization, and invasive pests. This study develops an interpretable remote sensing framework to monitor Toumeyella parvicornis infestation in Pinus pinea forests across Campania, Italy, from 2017 to 2025. Multitemporal Sentinel-2 composites and spectral indices were combined with spatial and temporal predictors in Google Earth Engine. Random Forest models and SHAP interpretation were used to assess infestation dynamics, vulnerability, and risk. The attack-transition and risk models achieved AUC values of 0.79 and 0.80, respectively. The framework supports scalable monitoring and operational prediction of pest spread.