Two-Step Urban Water Index (TSUWI): A New Technique for High-Resolution Mapping of Urban Surface Water

Wu, Wei; Li, Qiangzi; Zhang, Yuan; Du, Xin; Wang, Hongyan

doi:10.3390/rs10111704

Cited by 42 publications

(24 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This is largely due to the capability of the FCN model to exploit the spatial context in VHR images well. This capability also makes the FCN-based method withstand radiometric changes, which is a quite challenging task for typical feature extraction methods [13][14][15]. It should be noted that the high accuracy of the FCN-based method in our experiments is at the expense of efficiency compared with the NDWI based method.…”

Section: Discussionmentioning

confidence: 90%

“…Over the past decades, various water body mapping methods have been developed for remote sensing data [3][4][5][6][7][8][9][10][11][12][13][14][15]. A commonly used approach is based on water spectral indices such as the Normalized Difference Water Index (NDWI) [3,4].…”

Section: Introductionmentioning

confidence: 99%

“…However, the shadow removal method has a strong assumption of a rigid geometric relationship between a tall building and its shadow in the VHR image, which does not always hold true due to the existence of artificial targets with irregular shapes in urban areas. Recently Wu et al [15] proposed a Two-Step Urban Water Index to extract water bodies from high spatial resolution images in a robust way. The method follows a strategy similar to [14] but it models the spectral features of water and shadows differently by combining an Urban Water Index (UWI) and an Urban Shadow Index (USI) both of which are established on the basis of spectral analysis and linear SVM.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Water Body Extraction from Very High Spatial Resolution Remote Sensing Data Based on Fully Convolutional Networks

Yan

Shen

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

This paper studies the use of the Fully Convolutional Networks (FCN) model in the extraction of water bodies from Very High spatial Resolution (VHR) optical images in the case of limited training samples. Two different seasonal GaoFen-2 images with a spatial resolution of 0.8 m in the south of the Beijing metropolitan area were used to extensively validate the FCN model. Four key factors including input features, training data, transfer learning, and data augmentation related to the performance of the FCN model were empirically analyzed by using 36 combinations of various parameter settings. Our findings indicate that the FCN-based method can work as a robust and cost-effective tool in the extraction of water bodies from VHR images. The FCN-based method trained on a small amount of labeled L1A data can also significantly outperform the Normalized Difference Water Index (NDWI) based method, the Support Vector Machine (SVM) based method, and the Sparsity Model (SM) based method, even when radiometric normalization and spatial contexts are introduced to preprocess the input data for the latter three methods. The advantages of the FCN-based method are mainly due to its capability to exploit spatial contexts in the image, especially in urban areas with mixed water and shadows. Though the settings of four key factors significantly affect the performance of the FCN based method, choosing a qualified setting for the FCN model is not difficult. Our lessons learned from the successful use of the FCN model for the extraction of water from VHR images can be extended to extract other land covers.

show abstract

Section: Discussionmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Water Body Extraction from Very High Spatial Resolution Remote Sensing Data Based on Fully Convolutional Networks

Yan

Shen

et al. 2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, the commonly used high-resolution remote sensing data lack mid-infrared bands, which has limited the number of applicable water body indices, leading to commission problems because of insufficient spectral information. Although many studies have made use of the rich spatial features in high-resolution remote sensing images, such as geometry, morphology, texture, contextual features, to compensate for the lack of high-resolution remote sensing spectral features and to improve the overall accuracy [32,33]. However, due to the complexity and diversity of urban scenes, as well as the differences between cities, it is difficult to fully solve the commission problem caused by insufficient spectral information by relying only on the spatial information provided by high-resolution remote sensing.…”

Section: Introductionmentioning

confidence: 99%

“…On the basis of summarizing and analyzing the existing IUSW literatures [10,32,33,41,42], this paper suggests that there are still three issues that need to be further addressed, and the comprehensive solution through the three issues is reflected in the contribution of this paper:…”

Section: Introductionmentioning

confidence: 99%

Fusion of High- and Medium-Resolution Optical Remote Sensing Imagery and GlobeLand30 Products for the Automated Detection of Intra-Urban Surface Water

Yang

2020

Remote Sensing

View full text Add to dashboard Cite

Intra-urban surface water (IUSW) is an indispensable resource for urban living. Accurately acquiring and updating the distributions of IUSW resources is significant for human settlement environments and urban ecosystem services. High-resolution optical remote sensing data are used widely in the detailed monitoring of IUSW because of their characteristics of high resolution, large width, and high frequency. The lack of spectral information in high-resolution remote sensing data, however, has led to the IUSW misclassification problem, which is difficult to fully solve by relying only on spatial features. In addition, with an increasing abundance of water products, it is equally important to explore methods for using water products to further enhance the automatic acquisition of IUSW. In this study, we developed an automated urban surface-water area extraction method (AUSWAEM) to obtain accurate IUSW by fusing GaoFen-1 (GF-1) images, Landsat-8 Operational Land Imager (OLI) images, and GlobeLand30 products. First, we derived morphological large-area/small-area water indices to increase the salience of IUSW features. Then, we applied an adaptive segmentation model based on the GlobeLand30 product to obtain the initial results of IUSW. Finally, we constructed a decision-level fusion model based on expert knowledge to eliminate the problem of misclassification resulting from insufficient information from high-resolution remote sensing spectra and obtained the final IUSW results. We used a three-case study in China (i.e., Tianjin, Shanghai, and Guangzhou) to validate this method based on remotely sensed images, such as those from GF-1 and Landsat-8 OLI. We performed a comparative analysis of the results from the proposed method and the results from the normalized differential water index, with average kappa coefficients of 0.91 and 0.55, respectively, which indicated that the AUSWAEM improved the average kappa coefficient by 0.36 and obtained accurate spatial patterns of IUSW. Furthermore, the AUSWAEM displayed more stable and robust performance under different environmental conditions. Therefore, the AUSWAEM is a promising technique for extracting IUSW with more accurate and automated detection performance.

show abstract

Long‐term and seasonal variation of open‐surface water bodies in the Yellow River Basin during 1990–2020

Jiao

Wang

Song

et al. 2023

Hydrological Processes

View full text Add to dashboard Cite

Open-surface water bodies are essential terrestrial water sources and ecosystem service providers, and their evaluation is necessary for effective water management. In this study, 36 000 Landsat images of the Yellow River Basin (YRB) were collected, and a multiple index (Modified Normalized Difference Water Index, Normalized Difference Vegetation Index and Enhanced Vegetation Index, i.e. MNDWI, NDVI and EVI) method was used to identify open-surface water bodies in the flood and dry seasons during 1990-2020. Our results showed that during these 30 years, YRB surface waters were characterized by spatial and seasonal heterogeneities. The open-surface water coverage in the upper and middle reaches of the YRB was 8.74‰ and 4.24‰, respectively, less than the average coverage in the whole YRB of 9.45‰. Surface water area was significant larger in flood seasons than in dry seasons, while during 1990-2020, the surface water area increased by 27.5% in the flood season and by 58.9% in the dry season, reaching 7239.2 km 2 (flood season) and 6654.8 km 2 (dry season) in 2020. Meanwhile the seasonal variation has decreased. Climate factors (winter temperature and summer precipitation) positively correlated with open-surface water only in the source region of the YRB. In other regions, anthropic factors (e.g. water conservation projects) strongly affected open-surface water bodies by increasing their spatial area overall and decreasing seasonal differences in their coverage.

show abstract

Two-Step Urban Water Index (TSUWI): A New Technique for High-Resolution Mapping of Urban Surface Water

Cited by 42 publications

References 43 publications

Water Body Extraction from Very High Spatial Resolution Remote Sensing Data Based on Fully Convolutional Networks

Water Body Extraction from Very High Spatial Resolution Remote Sensing Data Based on Fully Convolutional Networks

Fusion of High- and Medium-Resolution Optical Remote Sensing Imagery and GlobeLand30 Products for the Automated Detection of Intra-Urban Surface Water

Long‐term and seasonal variation of open‐surface water bodies in the Yellow River Basin during 1990–2020

Contact Info

Product

Resources

About