Urban greenspace is an important component of infrastructure providing essential eco-services to the urban community with rapid growth population, in particular, in the context of climate change. Thus, it is necessary to ensure that urban greenspaces are sufficient with proper monitoring and management. In this study, we present urban greenspace mapping in the northern Taiwan derived from the Sentinel-2B imagery. Urban greenspace is classified with support of Google Earth Engine using classification and regression trees for Machine Learning (CART). 360 points were used for training and validation. Land cover is classified into four classes, including 1) dense tree cover, 2) tree cover, 3) water body, and 4) miscellaneous. Later, urban greenspace was further extracted and classified into roadside tree, park, and shrub or grassland. Overall accuracy of classification is 88.6 % with mean kappa coefficient of 0.84. The vulnerability map was generated and ranked into five levels to distinguish the risk patterns and levels of urban greenspace in the northern Taiwan to typhoons. Results further indicate the applicability of Sentinel-2 MSI data as an effective dataset to study urban greenspace at city scale.