Abstract
Recent studies have enhanced the mapping performance of the local climate zone (LCZ), a standard framework for evaluating urban form and function for urban heat island research, through remote sensing (RS) images and deep learning classifiers such as convolutional neural networks (CNNs). The accuracy in the urban-type LCZ (LCZ1-10), however, remains relatively low because RS data cannot provide vertical or horizontal building components in detail. Geographic information system (GIS)-based building datasets can be used as primary sources in LCZ classification, but there is a limit to using them as input data for CNN due to their incompleteness. This study proposes novel methods to classify LCZ using Sentinel 2 images and incomplete building data based on a CNN classifier. We designed three schemes (S1, S2, and a scheme fusion; SF) for mapping 50 m LCZs in two megacities: Berlin and Seoul. S1 used only RS images, and S2 used RS and building components such as area and height (or the number of stories). SF combined two schemes (S1 and S2) based on three conditions, mainly focusing on the confidence level of the CNN classifier. When compared to S1, the overall accuracies for all LCZ classes (OA) and the urban-type LCZ (OAurb) of SF increased by about 4% and 7–9%, respectively, for the two study areas. This study shows that SF can compensate for the imperfections in the building data, which causes misclassifications in S2. The suggested approach can be excellent guidance to produce a high accuracy LCZ map for cities where building databases can be obtained, even if they are incomplete.
Highlights
Due to the rapid growth of urbanization since 1950, over 55 percent of the world’s population resides in urban areas, as of 2018 [1]
The increase in the accuracy was much larger than that of Qiu et al [17], who reported that using OSM binary building data together with Sentinel reflectance in residual convolutional neural networks (CNNs) (ResNet) did not improve local climate zone (LCZ) classification accuracy significantly compared to that only using Sentinel datasets
It should be noted that scheme 2 (S2) of Berlin showed a slight increase in overall accuracy (OA) (1%), a slight decrease in OAurb (1.1%), but a significant decrease in OAu (7%), when compared to scheme 1 (S1) (Table 4)
Summary
Due to the rapid growth of urbanization since 1950, over 55 percent of the world’s population resides in urban areas, as of 2018 [1]. The migration of the world’s population toward urban areas significantly increases impervious surfaces that absorb solar radiation and reduce convective cooling [2,3]. The stored heat makes the urban areas have a higher temperature than rural surroundings [4,5,6,7], a phenomenon called an urban heat island (UHI). UHI, a leading threat to urban residents, exposing them to higher heat stress and more greenhouse gas emission problems [8], has been analyzed based on various approaches using numerical models or remote sensing (RS) data combined with land cover data, which separate urban areas from their surroundings [9,10]. The different urban structures in various cities are not analyzed with the existing land cover products
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
