Considerable progress was recently made in the determination of urban morphologies or structural types from different Earth observation (EO) datasets. A relevant field of application for such methods is urban climatology, since specific urban morphologies produce distinct microclimates. However, application and comparability are so far limited by the variety of typologies used for the description of urban surfaces in EO. In this study Local Climate Zones (LCZ), a system of thermally homogenous urban structures introduced by Stewart and Oke, was used in a pixel-based classification approach. Further, different EO datasets (including satellite multitemporal thermal and multispectral data as well as a normalized digital surface model (NDSM) from airborne Interferometric Synthetic Aperture Radar) and different classifiers (including Support Vector Machines, Neural Networks and Random Forest) were evaluated for their performance in a common framework. Especially the multitemporal thermal and spectral features yielded high potential for the discrimination of LCZ, but morphological profiles from the NDSM also performed well. Further, sets of 10-100 features were selected with the Minimum Redundancy Maximal Relevance approach from multiple EO data. Overall classification accuracies of up to 97.4% and 95.3% were obtained with a Neural Network and a Random Forest classifier respectively. This provides some evidence that LCZ can be derived from multiple EO data. Hence, we propose the typology and the method for the application of automated extraction of urban structures in urban climatology. Further the chosen multiple EO data and classifiers seemed to yield considerable potential for an automated classification of LCZ.
ABSTRACT:Remote sensing has widely been used in urban climatology since it has the advantage of a simultaneous synoptic view of the full urban surface. Methods include the analysis of surface temperature patterns, spatial (biophysical) indicators for urban heat island modelling, and flux measurements. Another approach is the automated classification of urban morphologies or structural types.In this study it was tested, whether Local Climate Zones (a new typology of thermally 'rather' homogenous urban morphologies) can be automatically classified from multisensor and multitemporal earth observation data. Therefore, a large number of parameters were derived from different datasets, including multitemporal Landsat data and morphological profiles as well as windowed multiband signatures from an airborne IFSAR-DHM. The results for Hamburg, Germany, show that different datasets have high potential for the differentiation of urban morphologies. Multitemporal thermal data performed very well with up to 96.3 % overall classification accuracy with a neuronal network classifier. The multispectral data reached 95.1 % and the morphological profiles 83.2 %.The multisensor feature sets reached up to 97.4 % with 100 selected features, but also small multisensoral feature sets reached good results. This shows that microclimatic meaningful urban structures can be classified from different remote sensing datasets. Further, the potential of the parameters for spatiotemporal modelling of the mean urban heat island was tested. Therefore, a comprehensive mobile measurement campaign with GPS loggers and temperature sensors on public buses was conducted in order to gain in situ data in high spatial and temporal resolution.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.