Extraction of High-Precision Urban Impervious Surfaces from Sentinel-2 Multispectral Imagery via Modified Linear Spectral Mixture Analysis

Xu, Rudong; Liu, Jin; Xu, Jianhui

doi:10.3390/s18092873

Cited by 61 publications

(30 citation statements)

References 61 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…where ρ Green , ρ R , ρ NIR , and ρ SWIR1 are the Sentinel-2A reflectance of bands 3, 4, 8b, and 11, respectively. The 10 m urban impervious surface and vegetation fractions were extracted using the modified linear spectral mixture analysis (MLSMA) method with the Sentinel-2A imagery [41]. In MLSMA, the high-precision impervious surface and vegetation fractions were extracted by integrating the conventional LSMA and Otsu's approaches with NDBI and NDVI.…”

Section: Datamentioning

confidence: 99%

“…In MLSMA, the high-precision impervious surface and vegetation fractions were extracted by integrating the conventional LSMA and Otsu's approaches with NDBI and NDVI. The process of extraction was described in detail in the research by Xu, Liu and Xu [41].…”

Section: Datamentioning

confidence: 99%

“…The Sentinel-2 was successfully used for monitoring vegetation, mapping water bodies and cropland, and monitoring urban areas [38][39][40]. In addition, this data has been used to extract 10 m urban impervious surface fraction [41]. However, this data has not been used to retrieve urban LST.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Downscaling Aster Land Surface Temperature over Urban Areas with Machine Learning-Based Area-To-Point Regression Kriging

Zhang

Jiang

et al. 2020

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Land surface temperature (LST) is a vital physical parameter of earth surface system. Estimating high-resolution LST precisely is essential to understand heat change processes in urban environments. Existing LST products with coarse spatial resolution retrieved from satellite-based thermal infrared imagery have limited use in the detailed study of surface energy balance, evapotranspiration, and climatic change at the urban spatial scale. Downscaling LST is a practicable approach to obtain high accuracy and high-resolution LST. In this study, a machine learning-based geostatistical downscaling method (RFATPK) is proposed for downscaling LST which integrates the advantages of random forests and area-to-point Kriging methods. The RFATPK was performed to downscale the 90 m Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) LST 10 m over two representative areas in Guangzhou, China. The 10 m multi-type independent variables derived from the Sentinel-2A imagery on 1 November 2017, were incorporated into the RFATPK, which considered the nonlinear relationship between LST and independent variables and the scale effect of the regression residual LST. The downscaled results were further compared with the results obtained from the normalized difference vegetation index (NDVI) based thermal sharpening method (TsHARP). The experimental results showed that the RFATPK produced 10 m LST with higher accuracy than the TsHARP; the TsHARP showed poor performance when downscaling LST in the built-up and water regions because NDVI is a poor indicator for impervious surfaces and water bodies; the RFATPK captured LST difference over different land coverage patterns and produced the spatial details of downscaled LST on heterogeneous regions. More accurate LST data has wide applications in meteorological, hydrological, and ecological research and urban heat island monitoring.

show abstract

Section: Datamentioning

confidence: 99%

Section: Datamentioning

confidence: 99%

See 1 more Smart Citation

Downscaling Aster Land Surface Temperature over Urban Areas with Machine Learning-Based Area-To-Point Regression Kriging

Zhang

Jiang

et al. 2020

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…Some studies have used Sentinel-2 imagery to evaluate impervious surfaces (Y. H. Chen et al, 2018;Priem et al, 2019;Tzelidi et al, 2019). Xu et al (2018) used a Modified Linear Spectral Mixture Analysis (MLSMA) technique to extract impervious surfaces in Guangzhou City. The results showed that the impervious surfaces extracted from Sentinel-2 imagery had better details and could clearly identify the boundaries of continuous roads and buildings in the urban environment.…”

Section: Introductionmentioning

confidence: 99%

A comparative study of impervious surface extraction using Sentinel-2 imagery

Chen

Yang

et al. 2020

European Journal of Remote Sensing

View full text Add to dashboard Cite

The accuracy and efficiency of impervious surface extraction using different algorithms vary greatly, and algorithm applicability depends on the study area. Therefore, it is necessary to carry out a comparative study of different algorithms across different study areas. This study compared six impervious surface extraction indices (i.e., normalized difference built-up index (NDBI), index-based built-up index (IBI), biophysical composition index (BCI), combinational build-up index (CBI), combinational biophysical composition index (CBCI), and enhanced normalized difference impervious surfaces index (ENDISI)) using Sentinel-2 imagery in Fuxian Lake Basin, Shenzhen City, and Nanjing City. Three study areas with different geographical locations, climatic conditions and altitudes can test spatial heterogeneity of different indices. The results show that: (1) All indices could be used to extract impervious surface, but BCI and CBI were greatly disturbed by water bodies; (2) CBCI, IBI, and NDBI were influenced by study area, while ENDISI could be used across all three study areas; (3) ENDISI algorithm was the best among the six algorithms with a much higher separability degree and an overall accuracy of more than 91.00%. ENDISI can extract impervious surface quickly and accurately from Sentinel-2 imagery across different study areas, and can be well applied in the field of impervious surface change monitoring.

show abstract

“…Sentinel-2 imagery was already deployed to estimate the degree of imperviousness (Lefebvre et al, 2016;Xu et al, 2018). However, a joint derivation of built-up density and height was just recently proposed by Geiß et al (2017Geiß et al ( , 2019 based on an integrative analysis of TDM and Sentinel-2 data.…”

Section: Introductionmentioning

confidence: 99%

Multistrategy ensemble regression for mapping of built-up density and height with Sentinel-2 data

Geiß

Schrade

Pelizari

et al. 2020

ISPRS Journal of Photogrammetry and Remote Sensing

View full text Add to dashboard Cite

In this paper, we establish a workflow for estimation of built-up density and height based on multispectral Sentinel-2 data. To do so, we render the estimation of built-up density and height as a supervised learning problem. Given the rational level of measurement of those two target variables, the regression estimation problem is regarded as finding the mapping between an incoming vector, i.e., ubiquitously available features computed from Sentinel-2 data, and an observable output (i.e., training set), which is derived over spatially limited areas in an automated manner. As such, training sets are automatically generated from a joint exploitation of TanDEM-X mission elevation data and Sentinel-2 imagery, and, as an alternative, from cadastral sources. The training sets are used to regress the target variables for spatial processing units which correspond to urban neighborhood scales. From a methodological point of view, we introduce a novel ensemble regression approach, i.e., multistrategy ensemble regression (MSER), based on advanced machine learning-based regression algorithms including Random Forest Regression, Support Vector Regression, Gaussian Process Regression, and Neural Network Regression. To establish a robust ensemble, those algorithms are learned with a modified version of the AdaBoost.RT algorithm. However, to reliably ensure diversity between single boosted regressors, we include a random feature subspace method in the procedure. In contrast to existing approaches, we selectively prune non-favorable regressors trained during the boosting procedure and calculate the final prediction by a weighted mean function on the residual models to ensure enhanced accuracy properties of predictions. Finally, outputs are concatenated into a single prediction with a decision fusion strategy. Experimental results are obtained from four test areas which cover the settlement areas of the four largest German cites, i.e., Berlin, Hamburg, Munich, and Cologne. The results unambiguously underline the beneficial properties of the MSER approach, since all best predictions were obtained with a boosted regressor in conjunction with a decision fusion strategy in a comparative setup. The mean absolute errors of corresponding models vary between 3-16% and 1-5.4m with respect to builtup density and height, respectively, depending on the validation strategy, size of the spatial processing units, and test area. Also in a domain adaptation setup (i.e., when learning a model over a source domain and applying it over a geographically different target domain) numerous predictions show comparable accuracy levels as predictions obtained within a source domain. This further underlines the viability to transfer a model and, thus, enable a substitution of the training data in the target domains.

show abstract

Extraction of High-Precision Urban Impervious Surfaces from Sentinel-2 Multispectral Imagery via Modified Linear Spectral Mixture Analysis

Cited by 61 publications

References 61 publications

Downscaling Aster Land Surface Temperature over Urban Areas with Machine Learning-Based Area-To-Point Regression Kriging

Downscaling Aster Land Surface Temperature over Urban Areas with Machine Learning-Based Area-To-Point Regression Kriging

A comparative study of impervious surface extraction using Sentinel-2 imagery

Multistrategy ensemble regression for mapping of built-up density and height with Sentinel-2 data

Contact Info

Product

Resources

About