The urban morphology on our planet – Global perspectives from space

Local Climate Zones (LCZ) offer a climate-aware and standardized classification scheme composed of 17 urban and natural landscape classes. Recent deep learning-based LCZ classification studies have adopted a scene classification approach with computer vision-inspired models. In light of these advancements, this study introduces a multi-scale, multi-level attention network (MSMLA-Net) for deep learning-based LCZ classification. MSMLA-Net integrates a multi-scale (MS) module to generate multi-scale features from the input data and a novel multi-level attention (MLA) module as a branch unit from the model’s main ResNet backbone. MLA uses the convolutional block attention module (CBAM) at multiple stages to generate multi-level spatially and spectrally enhanced features for context aggregation. This study presents comprehensive model-based experiments on model depth, the individual and combined influence of MS and MLA modules, and the addition of attention mechanisms. Furthermore, data-based experiments are conducted to determine optimal Sentinel-2 spectral bands, while OpenStreetMap (OSM) building data, ALOS World 3D DSM height information, and a national land cover map are included as ancillary bands. LCZ classification tests are conducted on six major cities in South Korea. With regards to model-based performance, MSMLA-Net was built using a modified SE-ResNet50 backbone (MSMLA-50) and obtained the best classification results using 48 by 48-pixel input patches with a combination of all Sentinel-2 and ancillary bands, outperforming three state-of-the-art LCZ classification models. In particular, only MSMLA-50 reached over 70% built-up overall accuracy and maintained high accuracy even when tested on completely unseen areas in a “citywise” leave-one-out sampling strategy. For data-based results, the combination of Sentinel-2 Red Edge bands were helpful, mainly due to the greater number of available bands. Training only ancillary data generated up to 75.0% for built-up overall accuracy, albeit at the cost of low natural overall accuracy. Using all available bands and ancillary data produced the best results, but a combination of only OSM and Sentinel-2 bands also generated comparable accuracy. Ultimately, the proposed MSMLA-Net bridges advanced computer vision techniques such as attention mechanisms and multi-level context aggregation to improve LCZ classification. The MS and MLA modules can be applied on different backbones, sophisticated sampling schemes, and data inputs to flexibly achieve improved classification results.

Local climate zone classification using a multi-scale, multi-level attention network

The urban morphology has impacts on the urban thermal environment, which has drawn extensive attention, especially in metropolitan regions with intensive populations and high building densities. This study explored the relationship between the urban morphology and spatial variation of land surface temperature (LST) in Wuhan by using the local climate zone (LCZ) and seven natural and social factors. A deep learning model (light LCZ model) was used to generate LCZ map in Wuhan, and a geographic detector model was utilized to explore the driving mechanism of LST spatial differentiation. The results show that the LST difference between LCZ classes in summer is greater than that in winter, and the LST of the built-up classes (LCZ 1–10) are significantly higher than that of the vegetation classes in summer. Among the six residential building classes (i.e., LCZ 1–6), LCZ 1 is characterized by compact and high buildings and has the largest average LST. Building density and height have a warming effect, and the building density has a stronger effect than the height. Compared with other natural and social factors, LCZ has the largest explanatory power for LST spatial differentiation in the main urban area and surrounding areas of Wuhan, with explanatory power (q) values reaching 0.660 (summer) and 0.316 (winter). The types of interaction for all pairwise cases are mutual and nonlinear. The strongest interaction is MNDWI-NDBI combination (0.780) in summer and LCZ-NDBI combination (0.460) in winter.

https://www.mdpi.com/2072-4292/14/5/1067/pdf?version=1645613560

Geographical Detection of Urban Thermal Environment Based on the Local Climate Zones: A Case Study in Wuhan, China

Local climate zones (LCZ) describe urban surface structures, supporting studies of urban heat islands, sustainable urbanization, and energy balance. The existing studies mapped LCZs from satellite images using scene-based classification, which trained deep-learning classifiers by labeled image patches, segmented satellite images into patches by sliding windows to match the size of training data, and finally classified the segmented patches to obtain LCZ maps. However, sliding windows are different from the real footprints of LCZs, which leads to large errors in classification. To address this problem, this article proposes a parcel-based method for LCZ classification using Sentinel-2 images, road networks, and elevation data. First, the Sentinel-2 images are segmented by the road network to obtain the land parcels as classification units. Second, each image parcel is standardized to match the training dataset, So2Sat LCZ42. Third, the trained convolutional neural network (CNN) is used to classify the standardized parcels into LCZs. Finally, the building height information derived from elevation data is used to refine the LCZs by a rule-based classifier. The results of the four test sites show that the overall accuracy of our method is 0.75, higher than the sliding-window-based method's accuracy of 0.47. Additional simulation experiments demonstrated that parcels derived from road networks can reduce the mixture effect in image patches, and parcel standardization can ensure the transferability of the CNN model trained by regular image patches. Considering that the road network and elevation data are widely available, the proposed method has the potential of mapping LCZs in large areas.

/pdf/a-parcel-based-deep-learning-classification-to-map-local-3n6rph76uj.pdf

A Parcel-Based Deep-Learning Classification to Map Local Climate Zones From Sentinel-2 Images

As a unique classification scheme for urban forms and functions, the local climate zone (LCZ) system provides essential general information for any studies related to urban environments, especially on a large scale. Remote sensing data-based classification approaches are the key to large-scale mapping and monitoring of LCZs. The potential of deep learning-based approaches is not yet fully explored, even though advanced convolutional neural networks (CNNs) continue to push the frontiers for various computer vision tasks. One reason is that published studies are based on different datasets, usually at a regional scale, which makes it impossible to fairly and consistently compare the potential of different CNNs for real-world scenarios. This article is based on the big So2Sat LCZ42 benchmark dataset dedicated to LCZ classification. Using this dataset, we studied a range of CNNs of varying sizes. In addition, we proposed a CNN to classify LCZs from Sentinel-2 images, Sen2LCZ-Net. Using this base network, we propose fusing multilevel features using the extended Sen2LCZ-Net-MF. With this proposed simple network architecture, and the highly competitive benchmark dataset, we obtain results that are better than those obtained by the state-of-the-art CNNs, while requiring less computation with fewer layers and parameters. Large-scale LCZ classification examples of completely unseen areas are presented, demonstrating the potential of our proposed Sen2LCZ-Net-MF as well as the So2Sat LCZ42 dataset. We also intensively investigated the influence of network depth and width, and the effectiveness of the design choices made for Sen2LCZ-Net-MF. This article will provide important baselines for future CNN-based algorithm developments for both LCZ classification and other urban land cover land use classification. Code and pretrained models are available at https://github.com/ChunpingQiu/benchmark-on-So2SatLCZ42-dataset-a-simple-tour .

/pdf/multilevel-feature-fusion-based-cnn-for-local-climate-zone-a5q43zum2c.pdf

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

As a unique classification scheme for urban forms and functions, the local climate zone (LCZ) system provides essential general information for any studies related to urban environments, especially on a large scale. Remote sensing data-based classification approaches are the key to large-scale mapping and monitoring of LCZs. The potential of deep learning-based approaches is not yet fully explored, even though advanced convolutional neural networks (CNNs) continue to push the frontiers for various computer vision tasks. One reason is that published studies are based on different datasets, usually at a regional scale, which makes it impossible to fairly and consistently compare the potential of different CNNs for real-world scenarios. This study is based on the big So2Sat LCZ42 benchmark dataset dedicated to LCZ classification. Using this dataset, we studied a range of CNNs of varying sizes. In addition, we proposed a CNN to classify LCZs from Sentinel-2 images, Sen2LCZ-Net. Using this base network, we propose fusing multi-level features using the extended Sen2LCZ-Net-MF. With this proposed simple network architecture and the highly competitive benchmark dataset, we obtain results that are better than those obtained by the state-of-the-art CNNs, while requiring less computation with fewer layers and parameters. Large-scale LCZ classification examples of completely unseen areas are presented, demonstrating the potential of our proposed Sen2LCZ-Net-MF as well as the So2Sat LCZ42 dataset. We also intensively investigated the influence of network depth and width and the effectiveness of the design choices made for Sen2LCZ-Net-MF. Our work will provide important baselines for future CNN-based algorithm developments for both LCZ classification and other urban land cover land use classification.

Xiaochong Tong

Papers

Multilevel Feature Fusion-Based CNN for Local Climate Zone Classification From Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset

Multi-level Feature Fusion-based CNN for Local Climate Zone Classification from Sentinel-2 Images: Benchmark Results on the So2Sat LCZ42 Dataset