scholarly journals Automatic Impervious Surface Area Detection Using Image Texture Analysis and Neural Computing Models with Advanced Optimizers

2021 ◽  
Vol 2021 ◽  
pp. 1-17
Author(s):  
Nhat-Duc Hoang
Keyword(s):  
Surface Area ◽  
Impervious Surface ◽  
Urban Land Use ◽  
Experimental Result ◽  
Neural Computing ◽  
Impervious Surface Area ◽  
Computing Model ◽  
Moment Estimation ◽  
Planning And Management ◽  
Computing Models

Up-to-date information regarding impervious surface is valuable for urban planning and management. The objective of this study is to develop neural computing models used for automatic impervious surface area detection at a regional scale. To achieve this task, advanced optimizers of adaptive moment estimation (Adam), a variation of Adam called Adamax, Nesterov-accelerated adaptive moment estimation (Nadam), Adam with decoupled weight decay (AdamW), and a new exponential moving average variant (AMSGrad) are used to train the artificial neural network models employed for impervious surface detection. These advanced optimizers are benchmarked with the conventional gradient descent with momentum (GDM). Remotely sensed images collected from Sentinel-2 satellite for the study area of Da Nang city (Vietnam) are used to construct and verify the proposed approach. Moreover, texture descriptors including statistical measurements of color channels and binary gradient contour are employed to extract useful features for the neural computing model-based pattern recognition. Experimental result supported by statistical test points out that the Nadam optimizer-based neural computing model has achieved the most desired predictive accuracy for the data collected in the studied region with classification accuracy rate of 97.331%, precision = 0.961, recall = 0.984, negative predictive value = 0.985, and F1 score = 0.972. Therefore, the model developed in this study can be a helpful tool for decision-makers in the task of urban land-use planning and management.

scholarly journals A 30-meter resolution dataset of China's urban impervious surface area and green space fractions, 2000–2018

2020 ◽  
Author(s):  
Wenhui Kuang ◽  
Shu Zhang ◽  
Xiaoyong Li ◽  
Dengsheng Lu
Keyword(s):  
Land Use ◽  
Surface Area ◽  
Urban Areas ◽  
Green Space ◽  
Impervious Surface ◽  
Urban Land ◽  
Google Earth ◽  
Urban Land Use ◽  
Impervious Surface Area ◽  
Urban Impervious Surface

Abstract. Urban impervious surface area (UISA) and urban green space (UGS) are two core components of cities for characterizing urban environments. Although several global or national urban land use/cover products such as Globeland30 and FROM-GLC are available, they cannot effectively delineate the complex intra-urban land cover components. Here we proposed a new approach to map fractional UISA and UGS in China using Google Earth Engine (GEE) based on multiple data sources. The first step is to extract the vector boundaries of urban areas from China's Land Use/cover Dataset (CLUD). The UISA was retrieved using the logistic regression from the Landsat-derived annual maximum Normalized Difference Vegetation Index (NDVI). The UGS was developed through linear calibration between reference UGS from high spatial resolution image and the normalized NDVI. Thus, the China's UISA and UGS fraction datasets (CLUD-Urban) at 30-meter resolution are generated from 2000 to 2018. The overall accuracy of national urban areas is over 92 %. The root mean square errors of UISA and UGS fractions are 0.10 and 0.14, respectively. The datasets indicate that total urban area of China was 7.10 ×104 km2 in 2018, with average fractions of 70.70 % for UISA and 26.54 % for UGS. The UISA and UGS increased with unprecedented annual rates of 1,492.63 km2/yr and 400.43 km2/yr during 2000–2018. CLUD-Urban can enhance our understanding of urbanization impacts on ecological and urban dwellers’ environments, and can be used in such applications as urban planning, urban environmental studies and practices. The datasets can be downloaded from https://doi.org/10.5281/zenodo.3778424 (Kuang et al., 2020).

Impervious Surface Area: Effects

2020 ◽  
pp. 93-99
Author(s):  
Carl L. Zimmerman ◽  
Daniel L. Civco
Keyword(s):  
Surface Area ◽  
Impervious Surface ◽  
Impervious Surface Area ◽  
Area Effects

scholarly journals Study on Urban Expansion Using the Spatial and Temporal Dynamic Changes in the Impervious Surface in Nanjing

2019 ◽  
Vol 11 (3) ◽  
pp. 933 ◽  
Author(s):  
Yanping Qian ◽  
Zhen Wu
Keyword(s):  
Surface Area ◽  
Time Series Data ◽  
Urban Expansion ◽  
Impervious Surface ◽  
Development Planning ◽  
Series Data ◽  
Dynamic Changes ◽  
Impervious Surface Area ◽  
Key Factor ◽  
Comprehensive Classification

Impervious surface area is a key factor affecting urbanization and urban environmental quality. It is of great significance to analysis timely and accurately the dynamic changes of impervious surface for urban development planning. In this study, we use a comprehensive method to extract the time series data on the impervious surface area (ISA) from the multi-temporal Landsat remote sensing images with a high overall accuracy of 90%. The processes and mechanisms of urban expansion at different political administration and direction level in the Nanjing metropolitan area are investigated by using the comprehensive classification method consisting of minimum noise fraction, linear spectral mixture analysis, spectral index, and decision tree classifiers. The expansion of Nanjing is examined by using various ISA indexes and concentric regression analyses. Results indicate that the overall classification accuracy of ISA is higher than 90%. The ISA in Nanjing has dramatically increased in the past three decades from 427.36 km2 to 1780.21 km2 and with a high expansion rate of 0.48 from 2000 to 2005. The city sprawls from monocentric to urban core with multiple subcenters in a concentric structure, and the geometric gravity center of construction land moves southward annually. The stages of urbanization in different district levels and the dynamic changes in different direction levels are influenced by the topographic and economic factors.

Sign in / Sign up

Export Citation Format

Share Document