Water Surface Extraction Research Articles

Terrain Shadow Interference Reduction for Water Surface Extraction in the Hindu Kush Himalaya Using a Transformer-Based Network

Water is the basis for human survival and growth, and it holds great importance for ecological and environmental protection. The Hindu Kush Himalaya (HKH) is known as the “Water Tower of Asia”, where water influences changes in the global water cycle and ecosystem. It is thus very important to efficiently measure the status of water in this region and to monitor its changes; with the development of satellite-borne sensors, water surface extraction based on remote sensing images has become an important method through which to do so, and one of the most advanced and accurate methods for water surface extraction involves the use of deep learning networks. We designed a network based on the state-of-the-art Vision Transformer to automatically extract the water surface in the HKH region; however, in this region, terrain shadows are often misclassified as water surfaces during extraction due to their spectral similarity. Therefore, we adjusted the training dataset in different ways to improve the accuracy of water surface extraction and explored whether these methods help to reduce the interference of terrain shadows. Our experimental results show that, based on the designed network, adding terrain shadow samples can significantly enhance the accuracy of water surface extraction in high mountainous areas, such as the HKH region, while adding terrain data does not reduce the interference from terrain shadows. We obtained the water surface extraction results in the HKH region in 2021, with the network and training datasets containing both water surface and terrain shadows. By comparing these results with the data products of Global Surface Water, it was shown that our water surface extraction results are highly accurate and the extracted water surface boundaries are finer, which strongly confirmed the applicability and advantages of the proposed water surface extraction approach in a wide range of complex surface environments.

Mapping the water body area by using Sentinel 1 – SAR in dry season of 2023: A case study in Tri An reservoir

Monitoring water surface areas plays an extremely important role, especially for river and reservoir, lake systems that are significant for irrigation, hydropower and ecosystems etc. In the Tri An reservoir area, the main water source for Dong Nai province, and also where many people live in 4 districts of VinhCuu, DinhQuan, Thong Nhat and TrangBom. However, in the dry season of 2023, the weather became hot and dry with little rain due to the influence of the El Nino phenomenon. The water level of Tri An Lake has dropped to a record low in the past 12 years. Based on Sentinel 1 images and threshold method, this study conducted water surface extraction from January May 2023 of Tri An lake. The results showed that, from January to May 2023, the water surface area decreased from 26,270.97 hectares to 10,059.87 hectares. The most obvious decrease in water surface area was in Phu Ly and Ma Da communes (VinhCuu district) and the La Nga bridge section. This study has been a demonstration of the impact of global climate change on water resources, providing a basis for environmental resource management.

Use of Geostatistical Methods Involving Standard Deviation and Semivariogram to Assess the Accuracy of Water Surface Extraction by Supervised Classification

Use of Geostatistical Methods Involving Standard Deviation and Semivariogram to Assess the Accuracy of Water Surface Extraction by Supervised Classification

Spatio-temporal analysis of surface water extraction methods reliability using COPERNICUS satellite data

The aim of this research is the comparison and subsequent evaluation of the suitability of using SAR (Synthetic Aperture Radar) and multispectral (MSI) satellite data of the Copernicus program for mapping and accurate identification of surface water bodies. The paper considers sudden changes caused by significant climatological-meteorological influences in the country. The surface guidance extraction methodology includes the standard preprocessing of SAR images and concluding the determination of threshold values in binary mask generation. For MSI images, water masks are generated through automatic algorithmic processing on the Google Earth Engine cloud platform. During SAR image processing, it has been found that the VV polarization configuration type (vertical-vertical) is the most suitable. The Lee and Lee Sigma filters are recommended for eliminating radar noise. The chosen window size for filtering depends on the specific object and its spatial extent. The extraction of water surfaces from the MSI image is conducted using the Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI), a pair of Automated Water Extraction Index (AWEI) indices, and Water Ratio Index (WRI). Results are evaluated both graphically and numerically, using quantitative accuracy indicators to refine them. Automatic extraction of water surfaces from MSI images in the GEE platform environment is a fast, efficient, and relatively accurate tool for determining the true extent of groundwater. In conclusion, this research can provide more reliable estimates of hydrological changes and interannual variations in water bodies in the country. When combined with multitemporal monitoring, these results can be an effective tool for permanent monitoring of floods and droughts.The aim of this research is the comparison and subsequent evaluation of the suitability of using SAR (Synthetic Aperture Radar) and multispectral (MSI) satellite data of the Copernicus program for mapping and accurate identification of surface water bodies. The paper considers sudden changes caused by significant climatological-meteorological influences in the country. The surface guidance extraction methodology includes the standard preprocessing of SAR images and concluding the determination of threshold values in binary mask generation. For MSI images, water masks are generated through automatic algorithmic processing on the Google Earth Engine cloud platform. During SAR image processing, it has been found that the VV polarization configuration type (vertical-vertical) is the most suitable. The Lee and Lee Sigma filters are recommended for eliminating radar noise. The chosen window size for filtering depends on the specific object and its spatial extent. The extraction of water surfaces from the MSI image is conducted using the Normalized Difference Water Index (NDWI), Modified Normalized Difference Water Index (MNDWI), a pair of Automated Water Extraction Index (AWEI) indices, and Water Ratio Index (WRI). Results are evaluated both graphically and numerically, using quantitative accuracy indicators to refine them. Automatic extraction of water surfaces from MSI images in the GEE platform environment is a fast, efficient, and relatively accurate tool for determining the true extent of groundwater. In conclusion, this research can provide more reliable estimates of hydrological changes and interannual variations in water bodies in the country. When combined with multitemporal monitoring, these results can be an effective tool for permanent monitoring of floods and droughts.

A Transformer-based method to reduce cloud shadow interference in automatic lake water surface extraction from Sentinel-2 imagery

Lake extraction from remote sensing images is an important approach to monitoring water resources. It provides guidance for aiding in maintaining natural ecological balance through the artificial adjustment of lake water resources. Cloud shadows are common interference factors in lake extraction from optical images. In this paper, we proposed a deep learning network based on a novel Transformer architecture to extract lakes from Sentinel-2 imagery. To determine how training datasets affect misclassifications of cloud shadows, we produced five training datasets that contained different proportions of cloud shadows to train the network; the highest proportion of cloud shadows among them was 4%. We found that, when the training dataset contained 4% cloud shadows, the obtained model could effectively reduce the misclassification of cloud shadows and improve the accuracy of lake extraction, and with this model, the evaluation results over the validation dataset achieved an overall accuracy (OA) of 0.9954 and a Kappa of 0.9568. In addition, the Transformer-based network was applied in the endorheic basin of Tibetan Plateau to further evaluate the generalization ability of the network over a large area. The Global Surface Water (GSW) dataset from the European Commission Joint Research Centre was used as a reference to validate our results in this area. Our experiment and results demonstrated the underlying potential of the Transformer-based network for improving image classification of optical imagery by reducing cloud shadow inferences.

Remote Sensing Big Data Analysis of the Lower Yellow River Ecological Environment Based on Internet of Things

This paper collects data on the ecological environment of the lower Yellow River through an IoT approach and provides an in‐depth analysis of the ecological remote sensing big data. An impervious fusion of multisource remote sensing data cooperation and multimachine learning algorithm cooperation is proposed. The water surface extraction method has improved the extraction accuracy of the construction land and rural settlements in the Yellow River Delta. The data system, big data management platform, and application scenarios of the environmental data resource center are designed specifically, respectively. Based on the spherical mesh information structure to sort out environmental data, an environmental data system containing data characteristics such as information source, timeliness, and presentation is formed. According to the characteristics of various types of environmental data, the corresponding data access, storage, and analysis support system is designed to form the big data management platform. Strengthen the construction of ecological interception projects for farmland receding water. Speed up the construction of sewage treatment facilities. Carry out waste and sewage pipeline network investigation, speed up the construction of urban sewage collection pipeline network, and improve the waste and sewage collection rate and treatment rate. The management platform adopts the Hadoop framework, which is conducive to the storage of massive data and the utilization of unstructured data. Combined with the relevant national policy requirements and the current environmental protection work status, the application scenarios of environmental big data in environmental decision‐making, supervision, and public services are sorted out to form a complete data resource center framework. Gray correlation analysis is used to identify the key influencing factors of different types of cities to elaborate the contents of the construction of water ecological civilization in different types of cities and to build a framework of ideas for the construction of urban water ecological civilization to improve the health of urban water ecological civilization. To realize the sustainable development of the lower reaches of the Yellow River, blind logging and reclamation should be avoided in the process of land development, and more efforts should be made to protect tamarisk scrub and reed scrub, which are vegetation communities with positive effects on the regional ecological environment. In urban planning, the proportion of green area and water area within the city should be reasonably increased, so that the city can develop towards a livable city that is more conducive to human‐land harmony and sustainability.

Application of Satellite Imagery and Water Indices to the Hydrography of the Cetina RiverBasin (Middle Adriatic)

The paper gives a brief description of the remote sensing method used for the identification and extraction of water surfaces. Landsat 8 and Sentinel 2 satellite imagery was used to separate land from bodies of water in the complex karst area surrounding the Croatian Cetina River, flowing into the Adriatic Sea. Water indexing methods are presented in detail. The most frequently used water indices were selected: NDWI, MNDWI, AWEI_nsh, AWEI_sh, WRI and LSWI, and their results compared. The combination of satellite imagery and calculated water indices is concluded to be very useful for the identification and mapping of the area and banks of lakes, riverine zones, river mouths and the coastline in the coastal zone. Landsat 8 satellite imagery is slightly inferior to Sentinel 2 due to lower image resolution. The best results were obtained with the NDWI water index and the worst with LSWI.

Rapid Assessment of Flood Inundation and Damaged Rice Area in Red River Delta from Sentinel 1A Imagery

The Red River Delta (RRD), including 11 provinces, is one of the four largest rice-growing areas in Vietnam. Tropical storms often occur and cause serious flooding from May to October annually in the RRD, which strongly affects the productivity of the summer–autumn rice, one of two main rice crops. Therefore, the rapid assessment of damaged rice area by flooding inundation is critical for farmers and the government. In this study, we proposed a methodology for quick estimation of rice areas damaged by flooding using Sentinel 1A (S1A) imagery. Firstly, the latest rice map was produced. Then, a Near Real-Time (NRT) flood map, which is estimated from S1A images at the closest time to a flooding event, was generated by excluding the yearly permanent map from the temporal water map. Our experiment was conducted for the assessment of damaged rice area by flooding from the tropical storm named Son-Tinh, which happened on 19–21 July 2018. A Support Vector Machine (SVM) classifier was applied on time-series of S1A VV with VH data (VVVH) to obtain a rice map for the winter-spring season of 2018 with 90.5% Overall Accuracy (OA) and 2.37% difference (12,544 ha) from the General Statistics Office (GSO) of Vietnam’s reports for the whole region. Then, the Otsu thresholding method was applied for permanent water surface extraction and NRT flood mapping. The estimated damaged area was compared to available provincial and communal statistics for validation and further analysis. Right after the Son-Tinh storm, the estimation of inundated rice was approximately 50% of the total rice area in the RRD (271,092 ha). As a result, rice damage level strongly corresponds to the inundation period. In addition, the rice-flooding frequency map over the RRD was estimated to show rice fields suffering a high risk of flooding during the rainy season in the RRD. Our experiment’s results highlight the potential of using Synthetic-Aperture Radar (SAR) imagery for fast monitoring and assessment of paddy rice areas affected by flooding at a large scale in the RRD region.

Analysis of the Dynamic Changes of the Baiyangdian Lake Surface Based on a Complex Water Extraction Method

Lakes have an important role in human life and the ecological environment, but they are easily affected by human activity and climate change, especially around urban areas. Hence, it is critical to extract water with a high precision method and monitor long-term sequence dynamic changes in lakes. As the greatest natural lake of the Beijing-Tianjin-Hebei region, Baiyangdian Lake has a significant function in human life, socio-economic development, and regional ecological balance. This lake area has shown large changes due to human activity and climate change. The change monitoring process of the water surface is of great significance in providing support for the management and protection of the lake. The Spectrum Matching based on Discrete Particle Swarm Optimization (SMDPSO) method is a new, robust, and low-cost method for water extraction, that has obvious advantages in extracting complex water surfaces. In this paper, the SMDPSO method was used to extract the water surface of Baiyangdian Lake by Landsat images from 1984 to 2018. This method has a good effect on complex water surface extraction with vegetation, shadows, and so forth, and the Landsat images have higher resolution and longer time series. The main contents and results of this paper are as follows: (1) We verified the applicability of the SMDPSO method in the Baiyangdian Lake using visual interpretation and correlation analysis. The relative errors between observed and extracted results were all less than 5% in spring, summer, and fall, and the correlation coefficient between the water area and water level was 0.96. (2) According to seasonal verification and comparison of the extraction results, the SMDPSO method was used to extract the water surface area of Baiyangdian Lake during spring of the years 1984–2018. Water area changes of Baiyangdian Lake can be divided into four periods: Dry period (1984–1988), degraded period (1989–2000), stable period (2000–2008), and recovery period (2008–2018). The water area reached a maximum of 280 km2 in 1989 and a minimum of 44 km2 in 2002. (3) The possible causes of the changes in the water area of Baiyangdian Lake were also analyzed. The changes were caused by climate and human activities during the first and second periods, but mainly human activities during the third and fourth periods. In fact, effective policies combined with water conservancy projects were directly conducive to improving or even recovering the water and ecological environment of Baiyangdian Lake. Considering its importance for the benign development of the Beijing-Tianjin-Hebei Region and the construction of the Xiong’an New Area, a policy is necessary to ensure that the lake’s ecological environment will not be destroyed under the premise of economic development.

Entropy-Based Fusion of Water Indices and DSM Derivatives for Automatic Water Surfaces Extraction and Flood Monitoring

Reliable water surface extraction is essential for river delineation and flood monitoring. Obtaining such information from fine resolution satellite imagery has attracted much interest for geographic and remote sensing applications. However, those images are often expensive and difficult to acquire. This study proposes a more cost-effective technique, employing freely available Landsat images. Despite its extensive spectrum and robust discrimination capability, Landsat data are normally of medium spatial resolution and, as such, fail to delineate smaller hydrological features. Based on Multivariate Mutual Information (MMI), the Landsat images were fused with Digital Surface Model (DSM) on the spatial domain. Each coinciding pixel would then contain not only rich indices but also intricate topographic attributes, derived from its respective sources. The proposed data fusion ensures robust, precise, and observer-invariable extraction of water surfaces and their branching, while eliminating spurious details. Its merit was demonstrated by effective discrimination of flooded regions from natural rivers for flood monitoring. The assessments we completed suggest improved extraction compared to traditional methods. Compared with manual digitizing, this method also exhibited promising consistency. Extraction using Dempster–Shafer fusion provided a 91.81% F-measure, 93.09% precision, 90.74% recall, and 98.25% accuracy, while using Majority Voting fusion resulted in an 84.91% F-measure, 75.44% precision, 97.37% recall, and 97.21% accuracy.

Improved water extraction using Landsat TM/ETM+ images in Ebinur Lake, Xinjiang, China

Water is the most common and important resources on earth. In this paper, we tested and analyzed a variety of water indices for water surface extraction using Landsat TM/ETM+ images, and evaluated extraction accuracies over Ebinur Lake area in Xinjiang Uyghur Autonomous Region of China. Eleven algorithms found in literature on land surface water extraction, including normalized difference water index (NDWI), modified normalized difference water index (MNDWI), automatic water extraction index with no shadow (AWEInsh), automatic water extraction with shadow (AWEIsh), vegetation index 1 (VI-1), vegetation index 2 (VI-2), vegetation index 3 (VI-3), water index (LBV_B), national wetland inventory (NWI), enhanced water index (EWI), and revised normalized different water index (RNDWI) were used. The results were validated by a maximum likelihood classification method, edge extraction accuracy assessment and extracted the area of Ebinur Lake from higher-resolution Landsat ETM+ panchromatic band. The results showed that these algorithms have different accuracies in extracting water information. We proposed VI-2 for KT3+ TM4>TM2+ TM7 and VI-3 for KT3+ TM2>TM4+ TM3 as an optimized and comprehensive method for land surface water extraction from Landsat TM/ETM+ Images (KT3, i.e. Wetness index from the Kauth-Thomas Transformation). The proposed VI-2 and VI-3 models demonstrated its potential in water body extraction with 92.95% and 85.04% accuracies, outperforming other algorithms. Using the optimal mask water model, the two models achieved up to 93.80% accuracy while minimizing the disturbance from vegetation and non-exploited land. Through comparison with other commonly used methods, it shows that the performance of the proposed method is superior to the others. Therefore VI-2 and VI-3 are the best indicators for water mapping using Landsat TM/ETM+ images. This study provided its great potential for quantitative evaluating of temporal changes of Ebinur Lake in Xinjiang Uyghur Autonomous Region of China.

Comparing four operational SAR-based water and flood detection approaches

In recent years, the German Remote Sensing Data Center (DFD) of the German Aerospace Center (DLR) has gained a lot of experience in water surface extraction from synthetic aperture radar (SAR) data for various application domains. In this context, four approaches have been developed, which jointly form the so-called DFD Water Suite: The Water Mask Processor (WaMaPro) is based on a simple and high-performance algorithm that processes multi-sensor SAR data in order to provide decision-makers with information about the location of water surfaces. The Rapid Mapping of Flooding tool (RaMaFlood) has been developed for flood extent mapping using an interactive object-based classification algorithm. The TerraSAR-X Flood Service (TFS) is used for rapid mapping activities and provides satellite-derived information about the extent of floods in order to support emergency management authorities and decision-makers. It is based on a fully automated processing chain. The last approach is the TanDEM-X Water Indication Mask processor (TDX WAM). It is part of the processing chain for the generation of the seamless, accurate, and high-resolution global digital elevation model (DEM) produced based on data of the TanDEM-X mission. Its purpose is to support the subsequent DEM editing process by the generation of a global reference water mask. In this study, the design of the four approaches and their methodological backgrounds are explained in detail, while simultaneously elaborating on the preferred application domains for the different algorithms. The advantages and disadvantages of the four approaches are identified by qualitatively as well as quantitatively evaluating the water masks derived from data of the TanDEM-X mission for five test sites located in Vietnam, China, Germany, Mali, and the Netherlands.

Comparing four operational SAR-based water and flood detection approaches

In recent years, the German Remote Sensing Data Center DFD of the German Aerospace Center DLR has gained a lot of experience in water surface extraction from synthetic aperture radar SAR data for v...

Effects of spatial scale on water surface delineation with satellite images

Lake area is an important indicator for lake-related research. Accurate extraction of water surface from remote sensing images with various spatial resolutions still remains unsettled. To investigate the effects of spatial resolution on lake surface monitoring,two Landsat ETM +( Enhanced Thematic Mapper Plus) images were acquired with one at high water level and the other at low water level. These images were resampled to lower resolutions using Nearest Neighboring( NN) and Pixel Aggregation( PA) methods,and extracted for water surface area using NDWI( Normalized Difference Water Index) thresholding method. Variation trend and error distribution of water surface area with spatial resolution were thoroughly investigated. In addition,the influence of different factors on water surface extraction was discussed. The main conclusions are as follows:( 1) the accuracy decreases gradually at lower spatial resolution relative to 30 m resolution. However,the overall accuracy is higher with a minimum of 67. 64%;( 2) NN has minor impact on DN values,whereas PA reduces mean digital number values and standard values. The reduction is gradual and smoother than NN; and( 3) the threshold varies for PA and remains stable for NN. Thus,use of threshold determined on 30 m image should introduce larger errors for PA-resampled images than NN-resampled images. This study provides invaluable guidance for water surface mapping using remote sensing methods under global changes.

Accuracy comparison and analysis of methods for water area extraction of discrete lakes

Remote sensing is a widely used technology for water surface monitoring. Currently,there exists no general method for water surface extraction at a dispersed lake,which affects the accuracy of lake area monitoring. For investigation of different methods,this paper uses ALOS multi-spectral data to extract lake surface in Lake Poyang. The reference lake area is obtained by unsupervised classification( ISODATA,Iterative Self-Organizing Data Analysis Technique Algorithm) based on fused 2. 5 m ALOS multi-spectral data. Subsequently,three methods are investigated based on 10 m ALOS data,including Normalized Difference Water Index( NDWI) thresholding,NDWI-based ISODATA method and Near Infrared( NIR)-based ISODATA method. Differences between these extractions are analyzed for intrinsic reasons. The main findings are:( 1) all three methods can be used for water surface identification,ISODATA method provides more detailed information and larger water surface area;( 2) NDWI-based method performs better than NIR-based method and the extraction accuracy increases;( 3) NDWI-based ISODATA gets the most reliable result with R2= 0. 993 and RMSE = 0. 115 km2,followed by NIR-based ISODATA with R2= 0. 992 and RMSE = 0. 144 km2,and NDWI thresholding with R2= 0. 938 and RMSE = 0. 443 km2. The results provide important references for selection of method and data source for water extraction of lake in dry season.

Index of extraction of water surfaces from Landsat 7 ETM+ images

The aim of this study was to develop an index of water surfaces (IWS) for separating the water surfaces from other types of land use, by using the images of Landsat 7 ETM+. The index was applied on four areas characterized by different types of land use from different regions in Algeria. The first is from the center of Algeria (Landsat ETM+ scene: 195−36 acquired March 24, 2001); the second is from the east of Algeria (Landsat ETM+ scene: 193−35 acquired March 24, 2000); the third is from the west of Algeria (Landsat ETM+ scene: 197−36 acquired February 16, 2000); and the fourth is from the south of Algeria (Landsat ETM + scene: 197−43 acquired February 16, 2000). The results showed that the application of the IWS on the different tested areas can distinguish clearly the surface water from the other land use (basin dams, wadis, Sebkha, and Chott). These findings indicated that this index can be used in the mapping of the water surfaces.