Improving Urban Impervious Surfaces Mapping through Integrating Statistical Methods and Spectral Mixture Analysis

As an important indicator of anthropogenic impacts on the Earth’s surface, it is of great necessity to accurately map large-scale urbanized areas for various science and policy applications. Although spectral mixture analysis (SMA) can provide spatial distribution and quantitative fractions for better representations of urban areas, this technique is rarely explored with 1-km resolution imagery. This is due mainly to the absence of image endmembers associated with the mixed pixel problem. Consequently, as the most profound source of error in SMA, endmember variability has rarely been considered with coarse resolution imagery. These issues can be acute for fractional land cover mapping due to the significant spectral variations of numerous land covers across a large study area. To solve these two problems, a hierarchically object-based SMA (HOBSMA) was developed (1) to extrapolate local endmembers for regional spectral library construction; and (2) to incorporate endmember variability into linear spectral unmixing of MODIS 1-km imagery for large-scale impervious surface abundance mapping. Results show that by integrating spatial constraints from object-based image segments and endmember extrapolation techniques into multiple endmember SMA (MESMA) of coarse resolution imagery, HOBSMA improves the discriminations between urban impervious surfaces and other land covers with well-known spectral confusions (e.g., bare soil and water), and particularly provides satisfactory representations of urban fringe areas and small settlements. HOBSMA yields promising abundance results at the km-level scale with relatively high precision and small bias, which considerably outperforms the traditional simple mixing model and the aggregated MODIS land cover classification product.

Endmember selection is the key to success in pixel unmixing which plays an important role in urban impervious surface abundance extraction. During the extraction, however, there has been a problem for the discrimination of impervious surfaces and soils because of their similarity in spectral. This increase the difficulty in distinguishes impervious surface and soil in endmember selection. To address this issue, in the current study, the biophysical composition index (BCI) and soil adjusted vegetation index (SAVI) were introduced to enhance the information of impervious surface and bare soil in the study area. Then, by selecting high albedo, low albedo, soil and vegetation endmembers with the utilization of the histogram of the indices and minimum noise fraction (MNF) scatter plot, we applied spectral mixture analysis (SMA) to extract impervious surface abundance. The scene of multispectral Landsat TM image was acquired allowing for the interpretation and analysis of impervious surfaces distribution. Experiments and comparisons indicate that this method performs well in estimating subpixel impervious surface distribution with relatively high precision and small bias.

The increase of urban impervious surface has significant influence on the urban ecological environment, also contributes to urban waterlogging and urban heat island (UHI). Therefore, the remote sensing extraction of urban impervious surface becomes a hotspot. The widely used sub-pixel approach - Linear Spectral Mixture Analysis (LSMA) estimates the impervious surface by adding the high albedo (the bright impervious surface) and the low albedo (the dark impervious surface) from the solving percentage of different objects from mixed pixels. However for the approach, the selection of end members is difficult and some misclassifications will occur, which causes a large area error, and low accuracy of the impervious surface area. For these issue, in this study, a modified LSMA is explored combining with high-resolution image (Google earth image, 2 meters), the Principal Component Analysis (PCA) and the Normalized Difference Building Index (NDBI) to extract the impervious surface of Guangzhou city with Landsat 8 OLI, October 2015. Based on the PCA, and high resolution image are employed to accurate the selection of end members. The LSMA based on the PCA, the modified LSMA based on the PCA and NDBI are taken to extract the impervious surface of the research area. And the Google earth image is for screening the end members and testing the accuracy estimation by sample area. The result shows that after the accurate topographic correction, the modified LSMA based on the PCA and NDBI is better than the conventional LSMA based on the PCA. The area precision of impervious surface in research area by the modified LSMA is improved with the correlation coefficient is 0.947. The study indicates that taking the high resolution images, the PCA and NDBI to improve the LSMA can raise the un-mix accuracy to a certain degree.

This paper explores the potential to improve the impervious surface estimation accuracy using a multi-stage approach on the basis of vegetation-impervious surface-soil (V-I-S) model. In the first stage of Spectral Mixture Analysis (SMA) process, pixel purity index, a quantitative index for defining endmember quality, and a 3-dimensional endmember selection method were applied to refining endmembers. In the second stage, instead of obtaining impervious surface fraction by adding high and low albedo fractions directly, a linear regression model was built between impervious surface and high/low albedo using a random sampling method. The urban impervious surface distribution in the urban central area of Shanghai was predicted by the linear regression model. Estimation accuracy of spectral mixture analysis and impervious surface fraction were assessed using root mean square (RMS) and color aerial photography respectively. In comparison with three different research methods, this improved estimation method has a higher overall accuracy than traditional Linear Spectral Mixture Analysis (LSMA) method and the normalized SMA model both in root mean square error (RMSE) and standard error (SE). However, the model has a tendency to overestimate the impervious surface distribution.

Abstract. While many spectral transformation techniques have been applied on spectral mixture analysis (SMA), few study examined their necessity and applicability. This paper focused on exploring the difference between spectrally transformed schemes and untransformed scheme to find out which transformed scheme performed better in SMA. In particular, nine spectrally transformed schemes as well as untransformed scheme were examined in two study areas. Each transformed scheme was tested 100 times using different endmember classes’ spectra under the endmember model of vegetation- high albedo impervious surface area-low albedo impervious surface area-soil (V-ISAh-ISAl-S). Performance of each scheme was assessed based on mean absolute error (MAE). Statistical analysis technique, Paired-Samples T test, was applied to test the significance of mean MAEs’ difference between transformed and untransformed schemes. Results demonstrated that only NSMA could exceed the untransformed scheme in all study areas. Some transformed schemes showed unstable performance since they outperformed the untransformed scheme in one area but weakened the SMA result in another region.

The distribution of urban impervious surfaces is usually recognized as a significant environmental and an essential indicator of various urban problems. The typical methods of extracting impervious surfaces are Linear Spectral Mixture Analysis Method (LSMA), Exponential Method (EM), and Maximum Likelihood Classification Method (MLC). However, all of the above methods have their drawbacks. Therefore, we propose a new method for extraction of urban impervious surfaces based on Principal Component Analysis (PCA) and Random Forest (RF). The synthetic aperture radar data and hyperspectral data of Nanjing are employed to test and validate the proposed methodology. The result of this new method is compared with the results obtained by LSMA, EM, and MLC to evaluate feasibility and effectiveness of the proposed methodology to extract the urban impervious surface. Experiments show that the Kappa coefficient in the optimal random forest model can reach 0.9744 and the overall classification accuracy is 99.6402%, which has obvious advantages over other methods.

Quantifying the temporal and spatial patterns of impervious surfaces (IS) is important for assessing the environmental and ecological impacts of urbanization. In order to better extract IS, and to explore the divergence in urbanization in different regions, research on the regional differentiation features and regional change difference features of IS are required. To extract China’s 2013 urban impervious area, we used the 2013 night light (NTL) data and the Moderate Resolution Imaging Spectroradiometer Normalized Difference Vegetation Index and enhanced vegetation index (EVI) temporal series data, and used three urban impervious surface extraction indexes—Human Settlements Index, Vegetation-Adjusted NTL Urban Index, and the EVI-adjusted NTL index (EANTLI)—which are recognized as the best and most widely used indexes for extracting urban impervious areas. We used the classification results of the Landsat-8 images as the benchmark data to visually compare and verify the results of the urban impervious area extracted by the three indexes. We determined that the EANTLI index better reflects the distribution of the impervious area. Therefore, we used the EANTLI index to extract the urban impervious area from 2003 to 2013 in the study area, and researched the spatial and temporal differentiation in urban IS. The results showed that China’s urban IS area was 70,179.06 km2, accounting for 0.73% of the country’s land area in 2013, compared with 20,565.24 km2 in 2003, which accounted for 0.21% of the land area, representing an increase of 0.52%. On a spatial scale, like economic development, the distribution of urban impervious surfaces was different in different regions. The overall performance of the urban IS percentage was characterized by a decreasing trend from Northwest China, Southwest China, the Middle Reaches of the Yellow River, Northeast China, the Middle Reaches of the Yangtze River, Southern Coastal China, and Northern Coastal China to Eastern Coastal China. On the provincial scale, the urban IS expansion showed considerable differences in different regions. The overall performance of the Urban IS Expansion index showed that the eastern coastal areas had higher values than the western inland areas. The cities or provinces of Beijing, Tianjin, Jiangsu, and Shanghai had the largest growth in impervious areas. Spatially and temporally quantifying the change in urban impervious areas can help to better understand the intensity of urbanization in a region. Therefore, quantifying the change in urban impervious area has an important role in the study of regional environmental and economic development, policy formulation, and the rational use of resources in both time and space.

It is well known that urban impervious surface (IS) has a warming effect on urban land surface temperature (LST). However, the influence of an IS’s structure, components, and spatial distribution on LST has rarely been quantitatively studied within strictly urban areas. Using ETM+ remote sensing images from the downtown area of Shanghai, China in 2010, this study characterized and quantified the influence of the IS spatial pattern on LST by selecting the percent cover of each IS cover feature and ten configuration metrics. The IS fraction was estimated by linear spectral mixture analysis (LSMA), and LST was retrieved using a mono-window algorithm. The results indicate that high fraction IS cover features account for the majority of the study area. The high fraction IS cover features are widely distributed and concentrated in groups, which is similar with that of high temperature zones. Both the percent composition and the configuration of IS cover features greatly affect the magnitude of LST, but the percent composition is a more important factor in determining LST than the configuration of those features. The significances and effects of the given configuration variables on LST vary greatly among IS cover features.

Prior-knowledge-based spectral mixture analysis for impervious surface mapping

Based on Landsat ETM+ data within the metropolitan area of Lanzhou, China, green vegetation(GV) and impervious surface was extracted by a constrained linear spectral mixture analysis (LSMA),together with single window algorithm to invert land surface temperature ,and the correlation analysis was then conducted to examine the relationship between urban heat island (UHI) effect and impervious surface. Four types of end members with high albedo, GV, soil and low albedo are selected to model complicated urban land cover, estimation accuracy is assessed using Root-Mean-Square (RMS)error and color aerial images, with the help of Mantel and Partial Mantel. Spatial relationship of land surface temperatures (LST), impervious surface and GV were analyzed. Results indicate that impervious surface distribution and GV can be derived from Landsat TM/ETM+ images with satisfactory precision. Impervious surface and GV were positively correlated with UHI, while LST has space dependence, it has high space dependence, and was higher correlated with impervious surface than GV.

In recent years, the urban impervious surface has been recognized as a key quantifiable indicator in assessing urbanization impacts on environmental and ecological conditions. A surge of research interests has resulted in the estimation of urban impervious surface using remote sensing studies. The objective of this paper is to examine and compare the effectiveness of two algorithms for extracting impervious surfaces from Landsat TM imagery; the multilayer perceptron neural network (MLPNN) and the support vector machine (SVM). An accuracy assessment was performed using the high-resolution WorldView images. The root mean square error (RMSE), the mean absolute error (MAE), and the coefficient of determination (R(2)) were calculated to validate the classification performance and accuracies of MLPNN and SVM. For the MLPNN model, the RMSE, MAE, and R(2) were 17.18%, 11.10%, and 0.8474, respectively. The SVM yielded a result with an RMSE of 13.75%, an MAE of 8.92%, and an R2 of 0.9032. The results indicated that SVM performance was superior to that of MLPNN in impervious surface classification. To further evaluate the performance of MLPNN and SVM in handling the mixed-pixels, an accuracy assessment was also conducted for the selected test areas, including commercial, residential, and rural areas. Our results suggested that SVM had better capability in handling the mixed-pixel problem than MLPNN. The superior performance of SVM over MLPNN is mainly attributed to the SVM's capability of deriving the global optimum and handling the over-fitting problem by suitable parameter selection. Overall, SVM provides an efficient and useful method for estimating the impervious surface. (C) 2011 Society of Photo-Optical Instrumentation Engineers (SPIE). [DOI: 10.1117/1.3539767]

The biophysical composition index (BCI)-based linear spectral mixture model (LSMM) is used in this study to extract the impervious surface (IS), vegetation, and soil coverage of the main urban region (MUR) of Hefei City over the 2001–2021 period. In addition, the Soil Conservation Service-Curve Number (SCS-CN) model is first applied to simulate the surface runoff (SR) in the MUR of Hefei City over the past 21 years, then assessed for simulation accuracy using typical waterlogging points in the study area. On this basis, the spatiotemporal evolution of IS and SR and their relationships in the MUR of Hefei City are investigated and discussed in this study. The obtained results showed that (1) the root-mean-square error (RMSE), mean absolute error (MAE), and systematic error (SE) values of the BCI index-based LSMM are smaller than those of the LSMM, demonstrating a higher extraction accuracy of urban IS extraction of the BCI index-based LSMM. (2) The IS area of the MUR of Hefei City exhibits an increasing trend from 107.555 km2 in 2001 to 387.660 km2 in 2021. In addition, the change rate and change intensity values indicate an increasing–decreasing–increasing trend. The highest change rate and change intensity values are 24.839 km2/year and 23.094%, respectively, and were observed in the 2001–2005 period. (3) The simulated SR (165–195 mm) in the MUR of Hefei City demonstrates an increasing trend in the 2001–2021 period at a rainfall intensity value of 200 mm/d. In addition, the simulated SR amount in the central area exhibits slight changes, while that in the surrounding areas shows substantial variations. (4) The distribution of IS and SR in the MUR of Hefei City reveals strong directional variations, which are all affected by geographical conditions. The IS coverage and SR show high positive correlation coefficients in different years. (5) The present study provides primary data for effective urban planning, water resources management and regulation, and disaster prevention and mitigation in Hefei City, as well as a scientific reference for future studies on urban IS, SR, and their quantitative relationships in other regions.

In remote sensing studies of land surface temperatures (LST), thematic land-use and land-cover (LULC) data are frequently employed for simple correlation analyses between LULC types and their thermal signatures. Development of quantitative surface descriptors could improve our capabilities for modeling urban thermal landscapes and advance urban climate research. This study developed an analytical procedure based upon a spectral unmixing model for characterizing and quantifying the urban landscape in Indianapolis, Indiana. A Landsat Enhanced Thematic Mapper Plus image of the study area, acquired on 22 June 2002, was spectrally unmixed into four fraction endmembers, namely, green vegetation, soil, high and low albedo. Impervious surface was then computed from the high and low albedo images. A hybrid classification procedure was developed to classify the fraction images into seven land-use and land-cover classes. Next, pixel-based LST measurements were related to urban surface biophysical descriptors derived from spectral mixture analysis (SMA). Correlation analyses were conducted to investigate land-cover based relationships between LST and impervious surface and green vegetation fractions for an analysis of the causes of LST variations. Results indicate that fraction images derived from SMA were effective for quantifying the urban morphology and for providing reliable measurements of biophysical variables such as vegetation abundance, soil, and impervious surface. An examination of LST variations within census block groups and their relationships with the compositions of LULC types, biophysical descriptors, and other relevant spatial data shows that LST possessed a weaker relation with the LULC compositions than with other variables (including urban biophysical descriptors, remote sensing biophysical variables, GIS-based impervious surface variables, and population density). Further research should be directed to refine spectral mixture modeling. The use of multi-temporal remote sensing data for urban time-space modeling and comparison of urban morphology in different geographical settings are also feasible.

The urban impervious surface, an important part in the city system, has a great influence on theecologicalenvironment in urban areas. The coverage of it is an important indicator for the evaluation ofurbanization. TheRemotesensing data has prominent features such as information-rich and accurate and it can provide data basis for large area extraction of impervious surface. GF-1 satellite is the first satellite of high-resolution earth observation system in China. With the homemade GF-1 satellite remote sensing image date as a resolution, this research, by the combination of V-I-S model and linear spectral mixture model, has first made estimation on the impervious surface of Tianjin City and then employed the remote sensingimage date with high resolution to test the precision of the estimated results. The results not only show that this method will make high precision available, but also reveal that Tianjin City has a wide coverage of impervious surface in general level, especially a high coverage rate both in the center and the coastal areas. The average coverage of impervious surface of the Tianjin city is very high and the coverage of impervious surface in the center and the coastal areas of Tianjin city reach seventy percent.City managers can use these data to guide city management and city planning.

Mapping urban expansion and impervious surfaces (IS) has become a useful tool for supporting watershed assessments. The lack of large-area time-series maps created the need to develop an approach and products that can easily be scaled. In this research application, 81 Landsat 1, 2, and 5 scenes for the epochs of 1975, 1985, and 1996 were used to map urban land use/land cover across New England, USA. A Classification And Regression Tree (CART) using random forest classified the landscape into a scheme matching the 2011 National Land Cover Database scheme, which was then aggregated to urban versus nonurban land cover. Regression models between Tasseled Cap brightness and greenness indices and IS values were developed. The CART and IS models were applied to modern imagery and backcast to selected archived imagery to generate maps of urban and IS across New England for the past four decades. The aggregated urban versus nonurban maps had an overall accuracy of 95% and the IS model had an R2 of 0.89. Multiscale spatiotemporal analyses show the highest urban expansion in watersheds along the coasts in southeastern New England and along highway corridors. Imperviousness intensity increase of urban existing in 1975 was highest for the coastal northeast between 1975 and 2011. The products will be used to support lake risk management and help identify potential stressors to lake health in the northeast.