Study on Urban Heat Island Intensity Level Identification Based on an Improved Restricted Boltzmann Machine

Site Selection of Urban Parks Based on Fuzzy-Analytic Hierarchy Process (F-AHP): A Case Study of Nanjing, China

The scientific siting of urban parks is critical for sustainable urban environment development, and this study aimed to identify suitable areas for future urban parks in Nanjing, China. This study has integrated geographic information systems (GIS) and fuzzy hierarchical analysis (F-AHP) in order to evaluate the suitability of the site selection of urban parks in Nanjing, China. Different physical, natural, environmental, accessibility, and human activity factors were evaluated in order to assess the suitability of a park site. The results revealed that 5% were highly suitable for urban park site selection, 36% were more suitable, 32% were moderately suitable, 19% were less suitable, and 8% were unsuitable for urban park site selection. The findings suggest that the areas that are highly suitable for urban park placement are located in the western and eastern parts of Nanjing. Carbon storage was the most important factor in the suitability of urban park site selection, followed by the normalized difference vegetation index (NDVI) and the heat-island effect. The methodology that has been adopted in this study helps to improve the methodological framework of combining F-AHP and GIS; in addition, generating urban park site selection maps assists planners and decision-makers in making scientific site selection decisions.

Urban Heat Island and Its Regional Impacts Using Remotely Sensed Thermal Data—A Review of Recent Developments and Methodology

Many novel research algorithms have been developed to analyze urban heat island (UHI) and UHI regional impacts (UHIRIP) with remotely sensed thermal data tables. We present a comprehensive review of some important aspects of UHI and UHIRIP studies that use remotely sensed thermal data, including concepts, datasets, methodologies, and applications. We focus on reviewing progress on multi-sensor image selection, preprocessing, computing, gap filling, image fusion, deep learning, and developing new metrics. This literature review shows that new satellite sensors and valuable methods have been developed for calculating land surface temperature (LST) and UHI intensity, and for assessing UHIRIP. Additionally, some of the limitations of using remotely sensed data to analyze the LST, UHI, and UHI intensity are discussed. Finally, we review a variety of applications in UHI and UHIRIP analyses. The assimilation of time-series remotely sensed data with the application of data fusion, gap filling models, and deep learning using the Google Cloud platform and Google Earth Engine platform also has the potential to improve the estimation accuracy of change patterns of UHI and UHIRIP over long time periods.

Multimodal and Multi-Model Deep Fusion for Fine Classification of Regional Complex Landscape Areas Using ZiYuan-3 Imagery

Land cover classification (LCC) of complex landscapes is attractive to the remote sensing community but poses great challenges. In complex open pit mining and agricultural development landscapes (CMALs), the landscape-specific characteristics limit the accuracy of LCC. The combination of traditional feature engineering and machine learning algorithms (MLAs) is not sufficient for LCC in CMALs. Deep belief network (DBN) methods achieved success in some remote sensing applications because of their excellent unsupervised learning ability in feature extraction. The usability of DBN has not been investigated in terms of LCC of complex landscapes and integrating multimodal inputs. A novel multimodal and multi-model deep fusion strategy based on DBN was developed and tested for fine LCC (FLCC) of CMALs in a 109.4 km 2 area of Wuhan City, China. First, low-level and multimodal spectral–spatial and topographic features derived from ZiYuan-3 imagery were extracted and fused. The features were then input into a DBN for deep feature learning. The developed features were fed to random forest and support vector machine (SVM) algorithms for classification. Experiments were conducted that compared the deep features with the softmax function and low-level features with MLAs. Five groups of training, validation, and test sets were performed with some spatial auto-correlations. A spatially independent test set and generalized McNemar tests were also employed to assess the accuracy. The fused model of DBN-SVM achieved overall accuracies (OAs) of 94.74%± 0.35% and 81.14% in FLCC and LCC, respectively, which significantly outperformed almost all other models. From this model, only three of the twenty land covers achieved OAs below 90%. In general, the developed model can contribute to FLCC and LCC in CMALs, and more deep learning algorithm-based models should be investigated in future for the application of FLCC and LCC in complex landscapes.