Automated Extraction of Consistent Time-Variable Water Surfaces of Lakes and Reservoirs Based on Landsat and Sentinel-2

Schwatke, C; Scherer, Daniel; Dettmering, D

doi:10.3390/rs11091010

Cited by 79 publications

(67 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In this study, we calculated 12 different indices for each granule out of which 11 were collocated from external reference studies and one was formulated as part of this study. First, the NDWI indices (NDWI 1 , NDWI 2 ) [30,54,55], the New Water Index (NWI) [56], the Tasseled Cap for wetness (TC wet ) [57,58] and the Automated Water Extraction Index with the option of shadow (AWEI sh ) or dark area removal (AWEI nsh ) [59] (Figure 4i-n) were derived to support the classification of open surface water. Second, the modified Soil-Adjusted Vegetation Index (SAVI mod ) [60], the Soil/Water Index (SWI), the Modified NDWI (MNDWI) (or Normalized Difference Snow Index (NDSI)) [61,62], as included in the European Space Agency's (ESA) Cloud/Snow Detection Algorithm [63] and the Normalized Difference Glacier Index (NDGI) [64] were included as training variables in order to support the identification of mainly rock and ice (Figure 4o-r).…”

Section: Sentinel-2mentioning

confidence: 99%

Automated Mapping of Antarctic Supraglacial Lakes Using a Machine Learning Approach

et al. 2020

View full text Add to dashboard Cite

Supraglacial lakes can have considerable impact on ice sheet mass balance and global sea-level-rise through ice shelf fracturing and subsequent glacier speedup. In Antarctica, the distribution and temporal development of supraglacial lakes as well as their potential contribution to increased ice mass loss remains largely unknown, requiring a detailed mapping of the Antarctic surface hydrological network. In this study, we employ a Machine Learning algorithm trained on Sentinel-2 and auxiliary TanDEM-X topographic data for automated mapping of Antarctic supraglacial lakes. To ensure the spatio-temporal transferability of our method, a Random Forest was trained on 14 training regions and applied over eight spatially independent test regions distributed across the whole Antarctic continent. In addition, we employed our workflow for large-scale application over Amery Ice Shelf where we calculated interannual supraglacial lake dynamics between 2017 and 2020 at full ice shelf coverage. To validate our supraglacial lake detection algorithm, we randomly created point samples over our classification results and compared them to Sentinel-2 imagery. The point comparisons were evaluated using a confusion matrix for calculation of selected accuracy metrics. Our analysis revealed wide-spread supraglacial lake occurrence in all three Antarctic regions. For the first time, we identified supraglacial meltwater features on Abbott, Hull and Cosgrove Ice Shelves in West Antarctica as well as for the entire Amery Ice Shelf for years 2017–2020. Over Amery Ice Shelf, maximum lake extent varied strongly between the years with the 2019 melt season characterized by the largest areal coverage of supraglacial lakes (~763 km2). The accuracy assessment over the test regions revealed an average Kappa coefficient of 0.86 where the largest value of Kappa reached 0.98 over George VI Ice Shelf. Future developments will involve the generation of circum-Antarctic supraglacial lake mapping products as well as their use for further methodological developments using Sentinel-1 SAR data in order to characterize intraannual supraglacial meltwater dynamics also during polar night and independent of meteorological conditions. In summary, the implementation of the Random Forest classifier enabled the development of the first automated mapping method applied to Sentinel-2 data distributed across all three Antarctic regions.

show abstract

Section: Sentinel-2mentioning

confidence: 99%

Automated Mapping of Antarctic Supraglacial Lakes Using a Machine Learning Approach

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Williamson et al [29,30] designed two algorithms named "FAST" and "FASTER" to extract the area and volume of SGLs based on thresholds of the ratio between red and blue and NDWI, respectively. Schwatke et al [31] used five water indexes MNDWI (Modified Normalized Difference Water Index), NWI (New Water Index), AWEI nsh (Automated Water Extraction Index for Non-Shadow Areas), AWEI sh (Automated Water Extraction Index for Shadow Areas) and TC wet (Tasseled Cap for Wetness) to combine their individual strengths for the water identification in the summer of 2018.…”

Section: Introductionmentioning

confidence: 99%

Automatic Extraction of Supraglacial Lakes in Southwest Greenland during the 2014–2018 Melt Seasons Based on Convolutional Neural Network

Yuan

Chi

Cheng

et al. 2020

Water

View full text Add to dashboard Cite

The mass loss of the Greenland Ice Sheet (GrIS) has implications for global sea level rise, and surface meltwater is an important factor that affects the mass balance. Supraglacial lakes (SGLs), which are representative and identifiable hydrologic features of surface meltwater on GrIS, are a means of assessing surface ablation temporally and spatially. In this study, we have developed a robust method to automatically extract SGLs by testing the widely distributed SGLs area—in southwest Greenland (68°00′ N–70°00′ N, 48°00′ W–51°30′ W), and documented their dynamics from 2014 to 2018 using Landsat 8 OLI images. This method identifies water using Convolutional Neural Networks (CNN) and then extracts SGLs with morphological and geometrical algorithms. CNN combines spectral and spatial features and shows better water identification results than the widely used adaptive thresholding method (Otsu), and two machine learning methods (Random Forests (RF) and Support Vector Machine (SVM)). Our results show that the total SGLs area varied between 158 and 393 km2 during 2014 to 2018; the area increased from 2014 to 2015, then decreased and reached the lowest point (158.73 km2) in 2018, when the most limited surface melting was observed. SGLs were most active during the melt season in 2015 with a quantity of 700 and a total area of 393.36 km2. The largest individual lake developed in 2016, with an area of 9.30 km2. As for the elevation, SGLs were most active in the area, with the elevation ranging from 1000 to 1500 m above sea level, and SGLs in 2016 were distributed at higher elevations than in other years. Our work proposes a method to extract SGLs accurately and efficiently. More importantly, this study is expected to provide data support to other studies monitoring the surface hydrological system and mass balance of the GrIS.

show abstract

“…Most of the previously mentioned approaches aim to detect water in open-water bodies such as rivers, lakes, reservoirs, and watersheds [17,19,20,30,33,37,43], while a part of them focuses on wetland areas [13,[22][23][24].…”

Section: Introductionmentioning

confidence: 99%

Automatic Inundation Mapping Using Sentinel-2 Data Applicable to Both Camargue and Doñana Biosphere Reserves

et al. 2019

View full text Add to dashboard Cite

Flooding periodicity is crucial for biomass production and ecosystem functions in wetland areas. Local monitoring networks may be enriched by spaceborne derived products with a temporal resolution of a few days. Unsupervised computer vision techniques are preferred, since human interference and the use of training data may be kept to a minimum. Recently, a novel automatic local thresholding unsupervised methodology for separating inundated areas from non-inundated ones led to successful results for the Doñana Biosphere Reserve. This study examines the applicability of this approach to Camarque Biosphere Reserve, and proposes alternatives to the original approach to enhance accuracy and applicability for both Camargue and Doñana wetlands in a scientific quest for methods that may serve accurately biomes at both protected areas. In particular, it examines alternative inputs for automatically estimating thresholds while applying various algorithms for estimating the splitting thresholds. Reference maps for Camargue are provided by local authorities, and generated using Sentinel-2 Band 8A (NIR) and Band 12 (SWIR-2). The alternative approaches examined led to high inundation mapping accuracy. In particular, for the Camargue study area and 39 different dates, the alternative approach with the highest overall Kappa coefficient is 0.84, while, for the Doñana Biosphere Reserve and Doñana marshland (a subset of Doñana Reserve) and 7 different dates, is 0.85 and 0.94, respectively. Moreover, there are alternative approaches with high overall Kappa for all areas, i.e., at 0.79 for Camargue, over 0.91 for Doñana marshland, and over 0.82 for Doñana Reserve. Additionally, this study identifies the alternative approaches that perform better when the study area is extensively covered by temporary flooded and emergent vegetation areas (i.e., Camargue Reserve and Doñana marshland) or when it contains a large percentage of dry areas (i.e., Doñana Reserve). The development of credible automatic thresholding techniques that can be applied to different wetlands could lead to a higher degree of automation for map production, while enhancing service utilization by non-trained personnel.

show abstract

Automated Extraction of Consistent Time-Variable Water Surfaces of Lakes and Reservoirs Based on Landsat and Sentinel-2

Cited by 79 publications

References 34 publications

Automated Mapping of Antarctic Supraglacial Lakes Using a Machine Learning Approach

Automated Mapping of Antarctic Supraglacial Lakes Using a Machine Learning Approach

Automatic Extraction of Supraglacial Lakes in Southwest Greenland during the 2014–2018 Melt Seasons Based on Convolutional Neural Network

Automatic Inundation Mapping Using Sentinel-2 Data Applicable to Both Camargue and Doñana Biosphere Reserves

Contact Info

Product

Resources

About