AutoLCZ: Towards Automatized Local Climate Zone Mapping from Rule-Based Remote Sensing
This addresses the scalability and labor-intensive labeling issues in urban climate studies for researchers and planners, though it appears incremental as it builds on existing RS-based methods with a rule-based approach.
The paper tackled the problem of automating Local Climate Zone (LCZ) mapping from remote sensing data by proposing AutoLCZ, a rule-based framework that uses LiDAR to model geometric and surface cover properties, reducing the need for manual labels. In a proof-of-concept for New York City, it successfully distinguished 10 LCZ types using 4 features, showing potential for large-scale applications.
Local climate zones (LCZs) established a standard classification system to categorize the landscape universe for improved urban climate studies. Existing LCZ mapping is guided by human interaction with geographic information systems (GIS) or modelled from remote sensing (RS) data. GIS-based methods do not scale to large areas. However, RS-based methods leverage machine learning techniques to automatize LCZ classification from RS. Yet, RS-based methods require huge amounts of manual labels for training. We propose a novel LCZ mapping framework, termed AutoLCZ, to extract the LCZ classification features from high-resolution RS modalities. We study the definition of numerical rules designed to mimic the LCZ definitions. Those rules model geometric and surface cover properties from LiDAR data. Correspondingly, we enable LCZ classification from RS data in a GIS-based scheme. The proposed AutoLCZ method has potential to reduce the human labor to acquire accurate metadata. At the same time, AutoLCZ sheds light on the physical interpretability of RS-based methods. In a proof-of-concept for New York City (NYC) we leverage airborne LiDAR surveys to model 4 LCZ features to distinguish 10 LCZ types. The results indicate the potential of AutoLCZ as promising avenue for large-scale LCZ mapping from RS data.