Search

Timely and accurate survey of construction and demolition waste (C&DW) distribution is of significance for managing C&DW and enhancing the quality of the urban environment, especially in rapidly urbanizing country of China. Automatic C&DW recognition using high-resolution remote sensing images is an extremely important surveying method. Existing C&DW recognition methods can only obtain a rough spatial distribution of C&DW. Mapping precise C&DW distribution on large-scale remote sensing images is still challenging. In this paper, to solve the problem of precise C&DW recognition, a novel deep learning algorithm based on high-resolution remote sensing images is proposed, which we refer to as the cross-channel multi-scale gated fusion network (CCMGNet). CCMGNet extracts depth features of C&DW from RGB and NIR bands by using two independent encoding streams. A gated fusion layer and a multi-scale attention module are designed to effectively fuse the features from two encoding streams. We manually labelled the sample set used for training and testing on 26 remote sensing images captured by the Gaofen-2 (GF-2) satellite. These images were taken in nine typical cities in China over the time period from 2019 to 2021. The results showed that the proposed method is effective in recognizing C&DW, realizing 89.42% and 84.52% in precision and IoU, and is superior to other state-of-the-art deep learning algorithms and existing C&DW recognition methods. The effectiveness of all significant components in CCMGNet was confirmed by ablation experiments. The proposed method was applied to extract C&DW regions in large-scale remote sensing images, with an example of a GF-2 image of Beijing. The high extraction efficiency and satisfactory visual effect demonstrate the potential of the proposed method for surveying the spatial distribution of C&DW. The novel method will play a crucial role in automatically surveying the spatial distribution and size of C&DW across the country. [ABSTRACT FROM AUTHOR]

The reflectance anisotropy of land surface serves as an important bridge between surface biophysical parameters and remote sensing observations. It can characterize by the linear kernel-driven bidirectional reflectance distribution function (BRDF), which is the combination of several kernel functions and kernel weights. These kernel weights can be estimated by remote sensing; however, the stability of current kernel weights products is still challenging, especially in urban areas with complex aerosol properties and heterogeneous surfaces. In this paper, we propose a method for robust estimation of kernel weights from the Moderate Resolution Imaging Spectroradiometer (MODIS) surface spectral reflectance products (MxD09GA) data based on the constrained least-squares method (CLSM) and a priori knowledge. The kernel weights data were obtained by the CLSM from 2014 to 2017 in Beijing region of China. Validations were carried out using the MxD09GA and BRDF/Albedo products (MCD43A1). The results show that the time series of kernel weights by the CLSM show small variability over different land cover types. The kernel weights estimated by the CLSM can clearly show the phenological signal and fitting ability of surface spectral reflectance is better than that of the MCD43A1 products in Beijing urban area. Experimental results demonstrate that the CLSM has the potential for the robust estimation of kernel weights in urban areas. [ABSTRACT FROM AUTHOR]

• The community livability evaluation is quantitative, practical and fine-grained. • The evaluation criteria span dimensions of environment, traffic and population. • Remote sensing, surface observation and geospatial big data are used. • Most communities are distributed within the central and marginal urban areas. • Communities in urban area tend to have robustly high livability. Effective evaluation of community livability is in urgent need to avoid increased livability at the expense of sustainability. However, studies concerning community livability evaluation were still conceptual, qualitative or conducted at city or regional scales. The availability of abundant, fine-grained, and multi-source data in the big data era laid the foundation for comprehensive livability evaluation at much finer scales. This paper proposed a quantitative and practical method for up-to-date livability evaluation at individual community scale in China. Nine evaluation criteria were identified spanning dimensions of environment, traffic, convenience, and population. These criteria were calculated respectively from remote sensing, surface observation and geospatial big data. The Technique for Order Preference by Similarity to an Ideal Solution (TOPSIS) was applied for community livability evaluation, and the uncertainty and sensitivity of evaluation results were assessed. The livability evaluation in the case study area of Haidian District, Beijing, China demonstrated the practicality and effectiveness of the framework. A total number of 1242 communities in Haidian District were evaluated. Communities in urban area were generally associated with higher evaluation scores and lower uncertainties than those in rural area. The careful selection of criteria weights with high sensitivity, i.e., green space coverage within community and driving time to schools, can potentially significantly reduce the uncertainty of the livability evaluation. The community scale livability evaluation is expected to bridge the gap between theoretical concepts and practical implementations of livability evaluation, and enables the development of more effective and locally specific regulations and policies to improve community livability. [ABSTRACT FROM AUTHOR]

Rapid urbanization has resulted in great changes in rural landscapes globally. Using remote sensing data to quantify the distribution of rural settlements and their changes has received increasing attention in the past three decades, but remains a challenge. Previous studies mostly focused on the residential changes within a grid or administrative boundary, but not at the individual village level. This paper presents a new change detection approach for rural residential settlements, which can identify different types of rural settlement changes at the individual village level by integrating remote sensing and Geographic Information System (GIS) analyses. Using multi-temporal Landsat TM image data, this approach classifies villages into five types: “no change”, “totally lost”, “shrinking”, “expanding”, and “merged”, in contrast to the commonly used “increase” and “decrease”. This approach was tested in the Beijing metropolitan area from 1984 to 2010. Additionally, the drivers of such changes were investigated using multinomial logistic regression models. The results revealed that: (1) 36% of the villages were lost, but the total area of developed lands in existing villages increased by 34%; (2) Changes were dominated by the type of ‘expansion’ in 1984–1990 (accounted for 43.42%) and 1990–2000 (56.21%). However, from 2000 to 2010, 49.73% of the villages remained unchanged; (3) Both topographical factors and distance factors had significant effects on whether the villages changed or not, but their impacts changed through time. The topographical driving factors showed decreasing effects on the loss of rural settlements, while distance factors had increasing impacts on settlement expansion and merging. This approach provides a useful tool for better understanding the changes in rural residential settlements and their associations with urbanization. [ABSTRACT FROM AUTHOR]

Spatial sampling design is important for accurately assessing land use and land cover (LULC) classification results from remote sensing data. Spatial stratification can dramatically improve spatial sampling efficiency by dividing the study area into several strata when classification correctness is spatially stratified heterogeneous. By integrating the LULC classification results from different sources and spatial resolutions, a spatial stratification method for spatial sampling of accuracy assessment is presented in this paper. Its efficiency is demonstrated in the case study using LULC data of Beijing, China, in the following steps. First, we standardized and reclassified multiresolution remote sensing data, including China's land use/cover datasets (CLUDs) from 2017 (resolution: 30 m), 500 m MCD12Q1, and 10 m FROM-GLC10 data, into six classes. Second, we customized stratification rules, formulated a technical specification to realize 11 strata using CLUDs and MCD12Q1, and employed FROM-GLC10 as the reference data for accuracy assessment. Furthermore, six sample sets with sizes of 16,417; 1821; 652; 337; 198; and 142 were drawn using different methods, and their overall accuracy (OA), deviation accuracy (DA), root-mean-square error (RMSE), and standard deviation (STDEV) values were also evaluated to demonstrate the efficiency brought by spatial stratification. Compared with the spatial even sampling method, the OAs of the stratified even sampling method adopting the proposed stratification method was much closer to the true OA, and the corresponding RMSE and STDEV results decreased from 2.097% and 2.127% to 0.914% and 0.713%, respectively, due to the contribution of spatial stratification in the sampling scheme. The method can be used to distinguish the differences and improve the representativeness of samples, and it can be employed to select validation samples for LULC classification. [ABSTRACT FROM AUTHOR]

In the acceleration of industrialization and urbanization, brownfield is an important resource for land regeneration and restoration targeting to recover its ecosystem function. Landfills, as a type of brownfield distributed in the highly populated areas, occupy massive land resources. The ecological restoration of landfills becomes an engineering approach to achieve multiple effects of society, environment, and economy. This paper aims to monitor and assess the restoration microclimatic effects of landfills restoration in China with remote sensing data and techniques. We selected representative landfill restoration projects, including Nanhaizi Park in Beijing, Nanhu Park in Tangshan, and Tianziling Park in Hangzhou, as the study cases. Using the Landsat imagery, the scenes of the pre-restoration, mid-restoration, and post-restoration were retrieved, and the surface energy balance equation was applied to calculate normalized difference vegetation index (NDVI), land surface temperature (T s), and evapotranspiration (ET), representing vegetation conditions and hydro-heat microclimate conditions. The study areas are divided into four subzones and extracted the calculated values for statistics and comparison. We defined an indicator of restoration intensity (RI) using the different subzones to the outer contour distance radius and restoration phases to evaluate the spatial-temporal restoration degrees. The spatial pattern dynamics was displayed in the urbanization context in the cases of Beijing and Tangshan. We examined and quantified the relations between RI and the key indicators, NDVI, T s , and ET. The overall results revealed that with higher restoration intensity, NDVI and ET became higher, and T s became lower. It suggested that the ecological restoration on the landfills brought better vegetation, cooling, and humidification effects for the microclimatic environment. Our research has the implications for monitoring and assessing the climatic effects of ecological restoration in the brownfield regeneration in a macroscopic and ecosystem perspective. Unlabelled Image • With satellite dataset, we developed a way to monitor vegetation and microclimatic changes in the restored landfills. • The indicator to quantify the ecological restoration intensity was invented with spatial distance and restoration phase. • Overall, with higher restoration intensity, vegetation and evapotranspiration improved, and surface temperature declined. [ABSTRACT FROM AUTHOR]