Exploring How Street-level Images Help to Enhance Local Climate Zone Mapping

The local climate zone (LCZ) classification scheme is effective for climatic modelling, and timely and accurate LCZ mapping becomes critical for scientific climate research. Satellite images can efficiently capture the information of large-scale landscapes, while street-level images include critical LCZ scheme-related information, such as building and ground-level details. It is promising to integrate the two different kinds of images. In this study, we explore two important questions: 1) Whether street-level images can help enhance LCZ classification performance compared with using satellite images alone, and how effective are they? 2) How street-level images can help augment the performance