Multi-Level Classification of Urban Green Space Using Multi-Source Remote Sensing and Geospatial Data

Urban Green Spaces (UGSs) monitoring usually focuses on the extraction of vegetation in the physical layer, while neglecting their functional attributes. This renders the monitoring results unable to objectively reflect the rationality of UGS planning. To address these issues, this study proposes a multi-level classification method integrating multi-source remote sensing and geospatial big data to bridge the semantic gap between the physical layer and the functional layer. In this method, a strategy of prior knowledge injection and semantic reconstruction was developed through the fine-tuning of a BERT model with cross-mapping rules. This strategy aims to classify the urban area into 24 functional categories, generating the social-functional basemap in a functional layer, based on Point of Interest (POI), OpenStreetMap (OSM), and Global Urban Boundary (GUB). Meanwhile, a novel deep learning architecture, namely the Multi-Shape and Spectral Aware Network (MSSANet), was designed for precise vegetation classification of UGSs in the physical layer. Finally, a “function-first, vegetation-second” coupling paradigm containing three functional attribute layers, referring to the Code for Classification of UGS in China (CJJ/T 85-2017), was established. This paradigm integrates the social-functional basemap with physical vegetation patches to build a multi-level UGS classification framework, i.e., the 5 major UGS categories, 11 intermediate UGS categories, and 24 fine-grained UGS sub-categories. Experiments conducted in Jinan and Qingdao, China, demonstrate the efficacy of the proposed method for refined multi-level UGS mapping.