Figure 1 - uploaded by Teng Fei
Content may be subject to copyright.
Source publication
Small water bodies have always been an important part of water ecology systems. In the past, due to the limitations of satellite spatial resolution and recognition method precision, there have been few satisfactory remote sensing small water bodies extraction methods. In this article, a method based on index composition and HSI (hue, saturation, an...
Contexts in source publication
Context 1
... Guangdong-Hong Kong-Macao Greater Bay Area (Greater Bay Area) is located in the south of China and is comprised of the two Special Administrative Regions of Hong Kong and Macao and nine municipalities in Guangdong Province (Figure 1). Seven cities of the Greater Bay Area are selected to compose our study area (Figure 1), including Guangzhou, Shenzhen, Hong Kong, Macao, Zhongshan, Zhuhai, and Dongguan, which have always been known as the most economically developed and densely populated regions in the Greater Bay Area. ...
Context 2
... Guangdong-Hong Kong-Macao Greater Bay Area (Greater Bay Area) is located in the south of China and is comprised of the two Special Administrative Regions of Hong Kong and Macao and nine municipalities in Guangdong Province (Figure 1). Seven cities of the Greater Bay Area are selected to compose our study area (Figure 1), including Guangzhou, Shenzhen, Hong Kong, Macao, Zhongshan, Zhuhai, and Dongguan, which have always been known as the most economically developed and densely populated regions in the Greater Bay Area. The total area is 16,500 km 2 and the total population had reached 47 million at the end of 2018. ...
Similar publications
Fine classification of urban nighttime lighting is a key prerequisite step for small-scale nighttime urban research. In order to fill the gap of high-resolution urban nighttime light image classification and recognition research, this paper is based on a small rotary-wing UAV platform, taking the nighttime static monocular tilted light images of co...
This study aimed to investigate deep convolutional neural network- (DCNN-) based artificial intelligence (AI) model using cephalometric images for the classification of sagittal skeletal relationships and compare the performance of the newly developed DCNN-based AI model with that of the automated-tracing AI software. A total of 1574 cephalometric...
This paper proposes a method for extracting crop planting structures based on indexes, image fusions and an improved U-Net deep semantic segmentation network; this method can automatically and accurately extract multiple types of information regarding crop planting structures. Taking the Landsat 8 commercial multispectral satellite dataset as an ex...
The application of land cover classification is very extensive, it can be used in land resources management, urban planning, agricultural and other fields. The multi-scale variation of targets in high-resolution remote sensing images leads to low accuracy in land cover classification tasks. In response to this problem, an improved semantic segmenta...
Crop identification is key to global food security. Due to the large scale of crop estimation, the science of remote sensing was able to do well in this field. The purpose of this study is to study the shortcomings and strengths of combined radar data and optical images to identify the type of crops in Tarom region (Iran). For this purpose, Sentine...
Citations
... Despite the variety of spectral indices aimed at enhancing water bodies, there is still no consensus on the best index developed to date for mapping WSs. Some studies have proposed adopting strategies that combine different spectral indexes to improve the potential for water information extraction and reduce classification errors [32], [33], [39], [40]. Jiang et al. [39], for example, used a combination of information extracted from vegetation indices such as NDVI [41], built-up area index NDBI [42], and MNDWI to delineate water surfaces through a transformation of the RGB-HSI color space. ...
This paper proposes a new spectral index called waterLog, aiming to enhance the delineation and performance of water body mapping in urban areas using satellite imagery. To evaluate the effectiveness of the proposed index, we compare its performance in water surfaces (WSs) in different cities in South America with the results obtained by other well-known water indices in the literature (namely, NDWI, MNDWI, AWEIsh, and AWEInsh). We utilized composite images from the Sentinel satellite (2A and 2B), all acquired in June 2021, and in cities located south of the Tropic of Capricorn to obtain images with the highest incidence of shading. This strategy enhances confusion involving mapping water classes and shadows associated with urban infrastructures, thereby allowing for a better assessment of index effectiveness. In this scenario, the present study revealed that selecting the best single index for mapping all WSs is impossible, as their performances varied across the analyzed locations. Overall, the performance of the indexes - evaluated by partial ROC curve analysis and non-water misclassification points restriction - revealed quite similar results, especially considering waterLog, NDWI, and MNDWI. Despite the similarity, in the six areas analyzed, Waterlog outperformed in three. Additionally, when considering a single threshold for all the cities, waterLog showed the best result in mapping, reducing confusion involving water and shading. Such results, therefore, are interpreted as an essential contribution to water body mapping, considering its practical applications in environmental monitoring and water resource management in urbanized areas.
... and then processed using Dark Spectrum Fitting (DSF) algorithm embedded in ACOLITE to derive the atmospherically corrected angular dependent remote sensing reflectance (R rs ) (Vanhellemont, 2019;Vanhellemont and Ruddick, 2018). The atmospheric correction algorithm has been widely used to perform atmospheric corrections on a variety of inland lakes and reservoirs, producing reliable results (Bie et al., 2020;Rodríguez-Benito et al., 2020). ...
Column-integrated algal biomass (CAB), represented by integrated Chlorophyll-a concentrations (Chla) throughout the water column, is indicative of overall algal biomass for the entire lake. The performance of biomass retrieval algorithms is limited since previous research on CAB underestimate the impact of subsurface information. To enhance the CAB estimation in shallow lakes, an upper-to-lower method and a bivariate model were combined and a novel algorithm was applied to Lake Chaohu. Maximum Chlorophyll Index (MCI) algorithm outperformed the other three surface Chla retrieval algorithms for surface Chla inversion (R 2 = 0.73, RMSE = 10.06 μg/L, MAPE = 35.22 %). The upper-to-lower method was used for subsurface Chla retrieval, depending on the empirical regression between two adjacent layers. The performance of different surface-subsurface combinations was validated to determine the optimal one for algorithm development. The algorithm was tested in two scenarios (no-bloom scenario and no-bloom + bloom scenario), displaying superior performance compared to conventional ones (R 2 = 0.83, RMSE = 16.77 μg/L, MAPE = 25.68 %, N = 36, in no-bloom scenario; R 2 = 0.88, RMSE = 32.34 μg/L, MAPE = 38.15 %, N = 50, in no-bloom + bloom scenario). Furthermore, the application of the algorithm was further extended to OLCI imageries, exhibiting a spatial consistency with RGB composites. The enhanced stability and reliability of total biomass estimations can provide a more comprehensive understanding of aquatic ecosystem.
... Remote sensing technologies will provide highly efficient means of observing the distribution, quality, and seasonal dynamics of earth surface water bodies. Water bodies can be distinguished from other terrestrial objects by optical remote sensing due to their unique properties, which may result in a reduced water reflectivity (Bie et al., 2020;Huang et al., 2018) [6,13] . Three different techniques for extracting water bodies from optical remote sensing pictures have been devised, taking into account the properties of water bodies. ...
... Remote sensing technologies will provide highly efficient means of observing the distribution, quality, and seasonal dynamics of earth surface water bodies. Water bodies can be distinguished from other terrestrial objects by optical remote sensing due to their unique properties, which may result in a reduced water reflectivity (Bie et al., 2020;Huang et al., 2018) [6,13] . Three different techniques for extracting water bodies from optical remote sensing pictures have been devised, taking into account the properties of water bodies. ...
... Three different techniques for extracting water bodies from optical remote sensing pictures have been devised, taking into account the properties of water bodies. These consist of the following three methods: first, extracting water bodies using indices; second, extracting water bodies without using indices; and third, utilising a different combination of indices to delineate water (Bie et al., 2020) [6] . By identifying dangerous materials or blooms (pollutants) and the effects of changing land use and cover due to illicit mining, the optical remote sensor in the basin will employ satellites to gather data on the water quality. ...
To live a sustainable existence, one must abide by environmental management regulations, which place a premium on pollution prevention and cutting-edge treatment methods. Water basins afflicted by malmsey, the implementation of control measures and cutting-edge technologies will contribute to the real-time regeneration of the supply of high-quality water. Utility firms would benefit greatly from the control tactics and cutting-edge technologies for managing water pollution, as they would help guarantee that all Countries have access to sustainable, dependable, and drinkable water supplies for both the present and future generations. Artificial intelligence (AI)-driven decision-making tools facilitate the most efficient application of diverse treatment technologies, including chemical precipitation, membrane technology, adsorption, ion exchanges, electrokinetic processes, and Phyto- remediation, in the removal of pollutants from impacted water bodies. The people have benefited from the industrial sector's recent rapid development, but it also produces large amounts of wastewater that are harmful to humans and the environment since they contain heavy metals, hydrocarbons, nitrogen, and phosphorus. As industrial effluent treatment technology advances, new approaches focusing on hybrid systems that are efficient in recovering resources from effluent in a cost-effective, time-efficient, and feasible way are emerging.
... However, research on water quality monitoring in small-sized rivers using remote sensing was still limited. Current studies primarily focus on larger bodies of water, with relatively less attention given to small streams [16]. Especially small-micro bodies of water located in typical agricultural areas, these small-micro bodies have limited surface area, making them highly susceptible to external influences from agricultural activities and residential living. ...
Accurate prediction of spatial variation in water quality in small microwaters remains a challenging task due to the complexity and inherent limitations of the optical properties of small microwaters. In this paper, based on unmanned aerial vehicles (UAV) multispectral images and a small amount of measured water quality data, the performance of seven intelligent algorithm-optimized SVR models in predicting the concentration of chlorophyll (Chla), total phosphorus (TP), ammonia nitrogen (NH3-N), and turbidity (TUB) in small and micro water bodies were compared and analyzed. The results show that the Gray Wolf optimized SVR model (GWO-SVR) has the highest comprehensive performance, with R2 of 0.915, 0.827, 0.838, and 0.800, respectively. In addition, even when dealing with limited training samples and different data in different periods, the GWO-SVR model also shows remarkable stability and portability. Finally, according to the forecast results, the influencing factors of water pollution were discussed. This method has practical significance in improving the intelligence level of small and micro water body monitoring.
... In tropical wetlands, this criterion is important because in the dry season, a high fragmentation of the covers, especially of the water bodies, is present (Fang et al. 2018 ;Zhang et al. 2022 ); therefore, the ease of differentiating small areas affects mapping accuracy (Bie et al. 2020 ;Isikdogan et al. 2017 ;Lira 2006 ). Table 5 shows the score of the alternatives that constitute the DR-2. ...
A novel method for assessing spectral index efficiencies for landscape mapping in tropical wetlands was formulated: spectral indices assessment for mapping tropical wetlands (SIA_MW). SIA_MW consists of three stages: (1) identification of covers that make up the landscape, (2) feature selection consistency assessment, and (3) result validation. These stages are evaluated based on six criteria, each of which contains a decision rule (DR) with their respective rating alternatives. The DRs are integrated into two equations: efficiency of an index for landscape mapping in tropical wetlands (EIM_W) and efficiency of an index for water body mapping in tropical wetlands (EIM_Ww). SIA_MW has been proposed as a novel instrument that allows each of the stages of supervised classification to be developed and evaluated in an orderly and coherent manner. This ensures that the final decision to select an index is supported by a robust process that integrates qualitative and quantitative methods of spectral evaluation. SIA_MW is applicable to multiple remote sensing products and can be used in environments other than wetlands. This is because it is independent of factors such as landscape cover categories, the type of sensor product from which spectral indices are derived, and spectral classification algorithms. For the formulation of SIA_MW, the Bajo Sinú Wetland Complex (BSWC), located in northern Colombia, was selected as a pilot site, and 9 vegetation indices derived from a PlanteScope image were compared and evaluated. The soil-adjusted vegetation and water-adjusted vegetation indices (SAVI and WAVI, respectively) yielded the best results with values for EMI_W of 0.94 and 0.89, respectively. These results indicate SIA_MW was consistent because the covariance between the two best indices was 0.88. Additionally, the correlation between the DR scores of the evaluated indices was low, thus, indicating criteria complementarity.
... It suggests that the construction of the S1-S2 constellation has far-reaching significance for water resources management and flood/drought impact assessment. With a spatial resolution of up to 10 m, it can effectively monitor smaller lakes and capture the intricacies of the water cycle in finer detail (Bie et al. 2020;Li and Niu 2022). Previous research has demonstrated that its capability to monitor lakes and ponds larger than 350 m 2 , this is of great significance in the monitoring of thermokarst waters caused by permafrost thawing and degradation in Panarctic and Arctic regions (Freitas et al. 2019). ...
Clean Water and Sanitation, the sixth goal of Sustainable Development Goals (SDGs 6) is a call for action by the United Nations aiming at balancing the water cycle for sustainable life on the earth. For water security and regional sustainable development, the quantity and quality of inland waters are key variables. Over the past decades, satellite remote sensing offers global information about inland water dynamics in a real-time and low-cost way. Amongst, the Sentinel satellites designed by the European Space Agency can provide global monitoring with a spatial resolution of up to 10 m and several days of revisit time. Although Sentinel satellites have been explored in inland water monitoring for a long time period, a systematical review on the research progress and challenges of their applications has not been documented well. This review aims to present a comprehensive review of the Sentinel satellites (especially for Sentinel-1, Sentinel-2, and Sentinel-3) in monitoring inland water, both on the quantity and quality dimensions, including the water extent, level, depth, volume and water quality (e.g., chlorophyll-a, phycocyanin, suspended particulate matter, colored dissolved organic matter, and Secchi disk depth). A total of 690 publications are involved and the bibliometric quantitative approach is used to analyze the areas in which Sentinel instrument excelled and their performance with different processing methods. The implications for virtual constellation construction using Sentinel satellites from different missions and the contribution of a virtual constellation in support of the SDG 6 are also discussed. According to the initial investigation and characteristics of various satellites, we have proposed several schemes for Sentinel virtual constellation toward different missions covering water quantity measurement and water quality monitoring, which can maximize the observation capability of the satellite. The optimal Sentinel virtual constellation constructing scheme theoretically enables a coverage of 10 m spatial resolution and less than 2 days temporal resolution for all-weather inland water monitoring. These solutions will significantly enhance the observational capacity to obtain high-quality, long-term water security parameters in supporting SDG 6. Nevertheless, there remains a scarcity of freely available Sentinel-derived products, widely applicable data processing algorithms, and unified platform, capable of supporting water security monitoring on a broad scale.
... This limits their applicability in various situations [1]. For instance, in the study of inland water bodies, the actual shape and size of relatively small water bodies (with areas ranging between 1 m 2 and about 5 ha [9]) is difficult to assess. This is due to the mixed pixel phenomenon that arises when a pixel footprint over the surface covers a varying proportion of water [10]. ...
The accuracy assessment of three different Normalized Difference Water indices (NDWIs) was performed in La Salada, a typical lake in the Pampean region. Data were gathered during April 2019, a period in which floods occurred in a large area in the Southwest of the Buenos Aires Province (Argentina). The accuracy of the estimations using spaceborne medium-resolution multi-spectral imaging and the reliability of three NDWIs to highlight shallow water features in satellite images were evaluated using a high-resolution airbone imagery as ground truth. We show that these indices computed using Landsat-8 and Sentinel-2 imagery are only loosely correlated to the actual flooded area in shallow waters. Indeed, NDWI values vary significantly depending on the satellite mission used and the type of index computed.
... Furthermore, the priority of mining activities and the hot-spot nature of water pollution caused by illegal mining (galamsey) with its associated consequences must be well verified using overlay analysis in GIS in the study area [31,32], by utilizing remote sensing technologies, that will offer very effective ways to observe the distribution, quality and seasonal dynamics of earth surface water bodies. Optical remote sensing can identify water bodies based on their characteristics and as such, their potential lower reflectivity of water compared to other land objects [33,34]. Based on the characteristics of water bodies, three types of extraction methods for water bodies from optical remote sensing imagery have been developed. ...
... Based on the characteristics of water bodies, three types of extraction methods for water bodies from optical remote sensing imagery have been developed. They include first, using indices to extract water bodies, second, the extraction of water bodies without the use of indices and third, to differently use a combination of indices to delineate water [33]. Using satellites in the Pra basin, the optical remote sensor will produce data on the water quality by detecting harmful substances or blooms (pollutants) as well as the impacts of land use land cover changes on the water quality as a result of illegal mining. ...
In Ghana, illegal mining (galamsey) activities have polluted most of the river bodies. For example, water bodies in Ghana that are polluted amounts to 60% with most of them in deteriorating condition. However, to live a sustainable life, there is the need to follow rules of environmental management, where pollution control and advanced treatment technologies are imperative. The adoption of control strategies and advanced technologies in galamsey-affected-water basins in Ghana will help provide real-time revitalization for supply of quality water. The control strategies for water pollution management and advanced technologies would particularly help utility companies in ensuring that all Ghanaians continue to get potable, reliable, and sustainable water supplies for the current and future generations. The paper covers three key control strategies for water pollution management, vis-à-vis six major aspects of advanced technologies and the use of artificial intelligence (AI). AI based decision-making tools help optimize the use of various treatment technologies, such as adsorption, ion exchanges, electrokinetic processes, chemical precipitation, phytobial remediation, and membrane technology to effectively remove pollutants from affected water bodies. The paper also focuses on advantages and disadvantages of several advanced technologies, challenges on leveraging the technologies while identifying gaps, and possible technology roadmap. The review contributes to water quality issues in Ghana's Pra river basin by embracing AI and other cutting-edge technologies to address the current water pollution crisis and also ensure sustainable and secure water supply for future generations. This contribution is in line with the United Nations' Agenda 2030 Sustainable Development Goals' (SDGs) goal 6 (clean water and sanitation) and goal 3 (good health and well-being).
... Sentinel-2 satellite images were used to map water bodies in the Three Gorges Reservoir, China. The study found that Sentinel-2 imagery can provide accurate and detailed information on water body dynamics (Bie, 2020). Several methods have been suggested for recognizing water bodies by utilizing Landsat bands in various water indices (Du et al., 2012;Rokni et al., 2014). ...
The study introduces an automated approach for extracting water bodies from satellite images using the Faster R-CNN algorithm. The approach was tested on two datasets consisting of water body images collected from Sentinel-2 and Landsat-8 (OLI) satellite images, totaling over 3500 images. The results showed that the proposed approach achieved an accuracy of 98.7% and 96.1% for the two datasets, respectively. This is significantly higher than the accuracy achieved by the convolutional neural network (CNN) approach, which achieved 96% and 80% for the two datasets, respectively. These findings highlight the effectiveness of the proposed approach in accurately mapping water bodies from satellite imagery. Additionally, the Sentinel-2 dataset performed better than the Landsat dataset in both the Faster R-CNN and CNN approaches for water body extraction.
... R 2 smaller than 0.90 were found in site 8 (R 2 = 0.8722) and site 10 (R 2 = 0.8591) where the dense vegetation and phytoplankton have similar spectral features as the SWBs. Figure 11 shows MAPEs of the predicted SWB water area for SWBs of different sizes in the ten sites; a lower MAPE indicates a better match between the predicted and the reference water area for a target SWB. Different from previous studies that mapped the SWBs smaller than 5-30 ha based on the pixel-based classification (Bie et al. 2020;Perin et al. 2021), this study explored the potential of the sub-pixel method of RSWFM in mapping SWBs smaller than 1 ha. In general, the water area estimation accuracy from the proposed RSWFM increased with the increase of area ranges except for the area range of 0.5-1 ha in site 4, the area range of 0.3-0.4 ...
Small water bodies (SWBs), such as ponds and on-farm reservoirs, are a key part of the hydrological system and play important roles in diverse domains from agriculture to conservation. The monitoring of SWBs has been greatly facilitated by medium-spatial-resolution satellite images, but the monitoring accuracy is considerably affected by the mixed-pixel problem. Although various spectral unmixing methods have been applied to map sub-pixel surface water fractions for large water bodies, such as lakes and reservoirs, it is challenging to map SWBs that are small in size relative to the image pixel and have dissimilar spectral properties. In this study, a novel regression-based surface water fraction mapping method (RSWFM) using a random forest and a synthetic spectral library is proposed for mapping 10 m spatial resolution surface water fractions from Sentinel-2 imagery. The RSWFM inputs a few endmembers of water, vegetation, impervious surfaces, and soil to simulate a spectral library, and considers spectral variations in endmembers for different SWBs. Additionally, RSWFM applies noise-based data augmentation on pure endmembers to overcome the limitation often arising from the use of a small set of pure spectra in training the regression model. RSWFM was assessed in ten study sites and compared with the fully constrained least squares (FCLS) linear spectral mixture analysis, multiple endmember spectral mixture analysis (MESMA), and the nonlinear random forest (RF) regression without data-augmentation. The results showed that RSWFM decreases the water fraction mapping errors by ~ 30%, ~15%, and ~ 11% in root mean square error compared with the linear FCLS, MESMA unmixings, and the nonlinear RF regression without data-augmentation respectively. RSWFM has an accuracy of approximately 0.85 in R² in estimating the area of SWBs smaller than 1 ha.
