Search

Land-use and land-cover (LULC) is an important component for sustainable natural resource management, and there are considerable impacts of the rapid anthropogenic LULC changes on environment, ecosystem services, and land surface processes. One of the significant adverse implications of the rapidly changing urban LULC is the increase in the Land Surface Temperature (LST) resulting in the urban heat island effect. In this study, we used a time series of Landsat satellite images from 1992 to 2020 in the Srinagar city of the Kashmir valley, North-western Himalaya, India to understand the linkages between LULC dynamics and LST, derived from the archived images using the Google Earth Engine (GEE). Furthermore, the relationship between LST, urban heat island (UHI), and biophysical indices, i.e., Normalized Difference Vegetation Index (NDVI) and Normalized Difference Water Index (NDWI), was also analysed. LULC change detection analysis from 1992 to 2020 revealed that the built-up area has increased significantly from 12% in 1992 to 40% in 2020, while the extent of water bodies has decreased from 6% in 1992 to 4% in 2020. The area under plantations has decreased from 26% in 1992 to 17% in 2020, and forests have decreased from 4 to 2% during the same period. Urban sprawl of Srinagar city has resulted in the depletion of natural land covers, modification of natural drainage, and loss of green and blue spaces over the past four decades. The study revealed that the maximum LST in the city has increased by 11°C between 1992 and 2020. During the same period of time, the minimum LST in the city has increased by 5°C, indicating the impact of urbanization on the city environment, which is reflected by the observed changes in various environmental indices. UHI impact in the city is quite evident with the maximum LST at the city centre having increased from 13.03°C in 1992 to 22.01°C in 2020. The findings shall serve as a vital source of knowledge for urban planners and decision-makers in developing sustainable urban environmental management strategies for Srinagar city. [ABSTRACT FROM AUTHOR]

Considering the high-level details in an ultrahigh-spatial-resolution (UHSR) unmanned aerial vehicle (UAV) dataset, detailed mapping of heterogeneous urban landscapes is extremely challenging because of the spectral similarity between classes. In this study, adaptive hierarchical image segmentation optimization, multilevel feature selection, and multiscale (MS) supervised machine learning (ML) models were integrated to accurately generate detailed maps for heterogeneous urban areas from the fusion of the UHSR orthomosaic and digital surface model (DSM). The integrated approach commenced through a preliminary MS image segmentation parameter selection, followed by the application of three supervised ML models, namely, random forest (RF), support vector machine (SVM), and decision tree (DT). These models were implemented at the optimal MS levels to identify preliminary information, such as the optimal segmentation level(s) and relevant features, for extracting 12 land use/land cover (LULC) urban classes from the fused datasets. Using the information obtained from the first phase of the analysis, detailed MS classification was iteratively conducted to improve the classification accuracy and derive the final urban LULC maps. Two UAV-based datasets were used to develop and assess the effectiveness of the proposed framework. The hierarchical classification of the pilot study area showed that the RF was superior with an overall accuracy (OA) of 94.40% and a kappa coefficient (K) of 0.938, followed by SVM (OA = 92.50% and K = 0.917) and DT (OA = 91.60% and K = 0.908). The classification results of the second dataset revealed that SVM was superior with an OA of 94.45% and K of 0.938, followed by RF (OA = 92.46% and K = 0.916) and DT (OA = 90.46% and K = 0.893). The proposed framework exhibited an excellent potential for the detailed mapping of heterogeneous urban landscapes from the fusion of UHSR orthophoto and DSM images using various ML models.

To estimate the impact of light-colored surfaces (roofs and pavements) and urban vegetation (trees, grass, shrubs) on meteorology and air quality of a city, it is essential to accurately characterize various urban surfaces. Of particular importance is the characterization of the area fraction of various surface-types as well as the vegetative fraction. In this paper, a method is discussed for developing data on surface-type distribution and city-fabric (land cover) makeup (percentage of various surface-types) using high-resolution orthophtos. We devised a semi-automatic Monte Carlo method to sample the data and visually identify the surface-type for each pixel. The color aerial photographs for Sacramento covered a total of about 65 km2, at 0.3-m resolution.Five major land-use types were examined: (1) downtown and city center, (2) industrial, (3) offices, (4) commercial, and (5) residential. In downtown Sacramento, the top view (above-the-canopy) shows that vegetation covers 30% of the area, whereas roofs cover 23% and paved surfaces (roads, parking areas, and sidewalks) 41%. In the industrial areas, vegetation covers 8–14% of the area, whereas roofs cover 19–23%, and paved surfaces 29–44%. The surface-type percentages in the office area were 21% trees, 16% roofs, and 49% paved areas. In commercial areas, vegetation covers 5–20%, roofs 19–20%, paved surfaces 44–68%. Residential areas exhibit a wide range of percentages among their various surface-types. On average, vegetation covers about 36% of the area, roofs about 20%, and paved surfaces about 28%. Trees mostly shade streets, parking lots, grass, and sidewalks. In most non-residential areas, paved surfaces cover 50–70% of the under-the-canopy area. In residential areas, on average, paved surfaces cover about 35% of the area.Land-use/land cover (LULC) data from the United States Geological Survey (USGS) was used to extrapolate these results from neighborhood scales to metropolitan Sacramento. Of an area of roughly 800 km2, defining most urban areas of the metropolitan Sacramento, about half is residential. The total roof area comprises about 150 km2 and the total paved surfaces (roads, parking areas, sidewalks) are about 310 km2. The total vegetated area covers about 230 km2. The remaining 110 km2 consist of barren land and miscellaneous surfaces. [Copyright &y& Elsevier]

Considering the high-level details in an ultrahigh-spatial-resolution (UHSR) unmanned aerial vehicle (UAV) dataset, detailed mapping of heterogeneous urban landscapes is extremely challenging because of the spectral similarity between classes. In this study, adaptive hierarchical image segmentation optimization, multilevel feature selection, and multiscale (MS) supervised machine learning (ML) models were integrated to accurately generate detailed maps for heterogeneous urban areas from the fusion of the UHSR orthomosaic and digital surface model (DSM). The integrated approach commenced through a preliminary MS image segmentation parameter selection, followed by the application of three supervised ML models, namely, random forest (RF), support vector machine (SVM), and decision tree (DT). These models were implemented at the optimal MS levels to identify preliminary information, such as the optimal segmentation level(s) and relevant features, for extracting 12 land use/land cover (LULC) urban classes from the fused datasets. Using the information obtained from the first phase of the analysis, detailed MS classification was iteratively conducted to improve the classification accuracy and derive the final urban LULC maps. Two UAV-based datasets were used to develop and assess the effectiveness of the proposed framework. The hierarchical classification of the pilot study area showed that the RF was superior with an overall accuracy (OA) of 94.40% and a kappa coefficient (K) of 0.938, followed by SVM (OA = 92.50% and K = 0.917) and DT (OA = 91.60% and K = 0.908). The classification results of the second dataset revealed that SVM was superior with an OA of 94.45% and K of 0.938, followed by RF (OA = 92.46% and K = 0.916) and DT (OA = 90.46% and K = 0.893). The proposed framework exhibited an excellent potential for the detailed mapping of heterogeneous urban landscapes from the fusion of UHSR orthophoto and DSM images using various ML models. [ABSTRACT FROM AUTHOR]