Sentinel-1 Synthetic Aperture Radar Imagery Research Articles

Integrating Sentinel-1 SAR and Sentinel-2 optical imagery with a crop structure dynamics model to track crop condition

ABSTRACT Sentinel-1 and Sentinel-2 satellites are delivering data at the spatial resolutions and geographies needed for operational crop monitoring. Of particular interest, Sentinel-1 Synthetic Aperture Radar (SAR) data in Single Look Complex (SLC) format can be processed to provide polarimetric parameters sensitive to crop development. This study created a Sentinel-1 based SAR vegetation index for canola, calibrated to Normalized Difference Vegetation Index (NDVI) (SARcal-NDVI) values calculated from Sentinel-2. A Random Forest Regressor (RFR) modelled the SARcal-NDVI, from four selected polarimetric features (degree of linear polarization (DoLP), normalized Shannon entropy (SE), the second eigenvalue of the coherency matrix (l2) and the ellipticity angle (. The coefficient of determination (R2) between the Sentinel-2 NDVI and the SARcal-NDVI was 0.89. RFR-generated SARcal-NDVI estimates, based on the four SLC generated polarimetric parameters, were then used with a Canopy Structure Dynamics Model (CSDM) and with Growing Degree Days (GDD) to estimate the condition of canola at a daily time step. The SARcal--NDVI time series estimated from the CSDM model was correlated to the ground measured biomass. During the rapid accumulation of biomass from early to mid-season, correlations of the SARcal-NDVI to wet biomass were strong (R2 of 0.88). Correlations were still significant albeit weaker during pod development and throughout the period of canola senescence (R2 of 0.42). As climate variability drives uncertainty in the agricultural sector, sensors like the Sentinels can be leveraged to track changes in crop acreages and crop productivity. The next step in this research is to extend to other economically important crops such as corn, soybeans and wheat and test the ability of a Sentinel-1-based vegetation index to inform crop yield estimates.

Integrating an attention-based deep learning framework and the SAFY-V model for winter wheat yield estimation using time series SAR and optical data

Information on the spatial distribution of yields can be obtained over a large area by using remote sensing (RS) data. Combining Synthetic Aperture Radar (SAR), being sensitive to above ground biomass and soil moisture in all weather conditions, and optical data can improve the usability of RS data and provide a basis for pixel-based crop yield estimation (YE). In this study, an Upscaled Convolutional Gated Recurrent Unit model incorporated an attention mechanism (UpSc-AConvGRU model) was proposed to improve the estimation accuracy of the winter wheat growth parameter, Leaf Area Index (LAI). Gap filling the time series of optical data was done with backscatter coefficients, local incidence angles and polarimetric decomposition information from Sentinel-1 SAR imagery. The time series LAI estimated by the UpSc-AConvGRU model and Vegetation Temperature Condition Index (VTCI) retrieved from Sentinel-3 optical imagery were then used as state variables of the SAFY-V model to estimate winter wheat yield. The results showed that the proposed UpSc-AConvGRU model incorporated the Convolutional Block Attention Module (CBAM) can effectively improve the accuracy of LAI estimation, with RMSEs ranging from 0.413 to 0.699 m2 m2 for LAI estimated within main growth stages (MGSs) of winter wheat. The correlation between estimated LAI and Sentinel-3 retrieved LAI was generally higher at irrigated farmland compared to rain-fed farmland. The estimated LAI was closest to Sentinel-3 retrieved LAI at the green-up and late heading-filling stage of winter wheat, followed by the jointing and early heading-filling stage, and finally the milk maturity stage. There was good agreement between the SAFY-V model estimated and field measured winter wheat yields (R2 = 0.546, RMSE = 0.757 t ha−1), and the estimated yields at the pixel scale in the Guanzhong Plain, PR China were satisfactory. This study combined deep learning and crop growth modeling, proposed a new pixel scale winter wheat YE method.

Improvement of the feature tracking and patter matching algorithm for sea ice motion retrieval from SAR and optical imagery

• Q-ORB-MCC algorithm can extract sea ice motion vectors from multiple data sources. • Q-ORB-MCC outperforms ORB-MCC in terms of the extraction accuracy. • Q-ORB-MCC can extract more sea ice motion vectors in low sea ice concentration areas. • Q-ORB-MCC can extract higher accuracy sea ice motion vectors from multi-source image. • A geographic grid-based matching method for feature point matching is proposed. • Locally consistent filtering can filter erroneous vectors more effectively. This study presents an improved, versatile, and efficient algorithm based on the Oriented FAST and Rotated BRIEF (ORB) combined with the maximum cross-correlation (MCC) (ORB-MCC) for extracting sea ice motion (SIM) vectors. Quadtree ORB (Q-ORB) extracts more uniform feature points than ORB (uniformity is 3 times higher) and eliminates the concentration of ORB-extracted feature points on ice ridges, leads and coastlines, thereby providing excellent initial conditions for MCC calculations. In addition, a geographic grid-based matching (GGM) algorithm is developed to replace the brute-force matching algorithm (BFM). GGM is 8–10 times more efficient for matching feature points than BFM, thereby increasing the computational efficiency of extracting SIM vectors. Moreover, a locally consistent (LC) flow field filtering process is incorporated to facilitate the filtering of the SIM field. Combining cross-correlation-coefficient-threshold (CCCT)-based and LC filtering processes eliminates erroneous vectors more efficiently than using a CCCT-based filtering process alone. The improved algorithm, named Q-ORB-MCC, is used to extract SIM vectors from imagery acquired by the Sentinel-1 Synthetic-Aperture Radar (SAR), Envisat Advanced SAR (ASAR), Phased Array type L-band SAR-2 (PALSAR-2) onboard the Advanced Land Observing Satellite-2 (ALOS-2), and Moderate Resolution Imaging Spectroradiometer (MODIS). An analysis of the accuracy and effectiveness of the extracted SIM vectors shows that Q-ORB-MCC extracted SIM vectors from Sentinel-1, ASAR, and MODIS images with 4%, 253%, and 62% higher accuracy than ORB-MCC, respectively. Meanwhile Q-ORB-MCC could obtain more SIM vectors from Sentinel-1 and ASAR images.

A deep learning based oil spill detector using Sentinel-1 SAR imagery

ABSTRACT The Eastern Mediterranean Sea has been known as an oil pollution hotspot due to its heavy marine traffic and an increasing number of oil and gas exploration activities. To provide automatic detection of oil pollution from not only maritime accidents but also deliberate discharges in this region, a deep learning-based object detector was developed utilizing freely available Sentinel-1 Synthetic Aperture Radar (SAR) imagery. A total of 9768 oil objects were collected from 5930 Sentinel-1 scenes from 2015 to 2018 and used for training and validating the object detector and evaluating its performance. The trained object detector has an average precision (AP) of 69.10% and 68.69% on the validation and test sets, respectively, and it could be applied for building an early-stage oil contamination surveillance system.

INTEGRATING INSAR COHERENCE AND BACKSCATTERING FOR IDENTIFICATION OF TEMPORARY SURFACE WATER, CASE STUDY: SOUTH KALIMANTAN FLOODING, INDONESIA

Abstract. Accurate and reliable information about the spatiotemporal level of surface water can be provided by Temporary Surface Water (TSW) monitoring. TSW is defined as a waterbody experiencing frequent drying phases which also correspond to surfaces frequently affected by flooding. In Indonesia, flooding is a frequent disaster, which is about 30% of the total number of disasters that occurred. In mid-January 2021, South Kalimantan Province, Indonesia was hit by a flood. The loss impact of this disaster is estimated at Rp. 1.349 trillion. Synthetic Aperture Radar (SAR), one type of remote sensing, can be used to map the spatial distribution of flood inundation. SAR has the advantage of not being constrained by day or night, weather conditions, and cloud cover or fog. Nowadays, the availability of Sentinel-1 SAR images can increase the use of SAR imagery for flood mapping. Specular reflections that occur on the smooth water surface produce a darker color in the SAR backscattering data, which makes floodwater distinguishable on dry land surfaces. However, inundation between buildings can cause changes in the backscattering value. Several studies have shown that the Interferometric SAR coherence method is a good method for mapping floods in urban areas. The main goal of this study is thus to map Temporary Surface Water (flood) of the South Kalimantan flood event in Indonesia using Sentinel-1 SAR imagery. With backscattering data, flood in a non-urban area can be mapped, but it is difficult to map flood in an urban area. Therefore, we will try to integrate InSAR coherence and SAR backscattering data in order to map flood in the whole study area. The result shows that using backscattering data, bare soil or non-urban flood inundation in the whole study area can be mapped with an overall accuracy of about 76.4%. Yet, flood in an urban area cannot be mapped only with backscattering data. The result from coherence imagery can map flood inundation in an urban area. Thus, integration from both of them can map flood inundation in the whole study area, either urban or non-urban.

Analysis of Environmental and Atmospheric Influences in the Use of SAR and Optical Imagery from Sentinel-1, Landsat-8, and Sentinel-2 in the Operational Monitoring of Reservoir Water Level

In this work, we aim to evaluate the feasibility and operational limitations of using Sentinel-1 synthetic aperture radar (SAR) data to monitor water levels in the Poço da Cruz reservoir from September 2016–September 2020, in the semi-arid region of northeast Brazil. To segment water/non-water features, SAR backscattering thresholding was carried out via the graphical interpretation of backscatter coefficient histograms. In addition, surrounding environmental effects on SAR polarization thresholds were investigated by applying wavelet analysis, and the Landsat-8 and Sentinel-2 normalized difference water index (NDWI) and modified normalized difference water index (MNDWI) were used to compare and discuss the SAR results. The assessment of the observed and estimated water levels showed that (i) SAR accuracy was equivalent to that of NDWI/Landsat-8; (ii) optical image accuracy outperformed SAR image accuracy in inlet branches, where the complexity of water features is higher; and (iii) VV polarization outperformed VH polarization. The results confirm that SAR images can be suitable for operational reservoir monitoring, offering a similar accuracy to that of multispectral indices. SAR threshold variations were strongly correlated to the normalized difference vegetation index (NDVI), the soil moisture variations in the reservoir depletion zone, and the prior precipitation quantities, which can be used as a proxy to predict cross-polarization (VH) and co-polarization (VV) thresholds. Our findings may improve the accuracy of the algorithms designed to automate the extraction of water levels using SAR data, either in isolation or combined with multispectral images.

Retrieval of Lake Ice Characteristics from SAR Imagery

Boreal lakes ecosystems can remain partially or completely covered by ice and snow during an important portion of the year. Alterations of lake and river ice properties can deteriorate the conditions of local ice roads, negatively influencing Nordic communities and economical activities. Monitoring of lake ice characteristics and dynamics is therefore crucial. In this study, Sentinel-1 Synthetic Aperture Radar (SAR) satellite imagery is exploited to evaluate changes in the ice regime over shallow and deep high-latitude lakes during the winters of 2018 and 2019. The methodology proposed, based on the combined analysis of SAR intensity and interferometric coherence maps, enables the extraction of important characteristics of ice dynamics. Overall, the lake ice thickness change derived from Differential Interferometric SAR (D-InSAR) increases with the lake depth. The D-InSAR-derived mean rate of growth, in general, agrees with the one estimated from records of in-situ ice thickness measurements. The methodology presented herein could be temporally extended to support the understanding of historical and current climate conditions. This could be done by using archived and newly available imagery to improve lake ice models.

Monitoring Irrigation Events and Crop Dynamics Using Sentinel-1 and Sentinel-2 Time Series

Capturing and identifying field-based agricultural activities, such as the start, duration and end of irrigation, together with crop sowing/germination, growing period and time of harvest, offer informative metrics that can assist in precision agricultural activities in addition to broader water and food security monitoring efforts. While optically based band-ratios, such as the normalized difference vegetation index (NDVI) and normalized difference water index (NDWI), have been used as descriptors for monitoring crop dynamics, data are not always available due to the influence of clouds and other atmospheric effects on optical sensors. Satellite-based microwave systems, such as the synthetic aperture radar (SAR), offer an all-weather advantage in monitoring soil and crop conditions. In this paper, we leverage the relative strengths of both optical- and microwave-based approaches by combining high resolution Sentinel-1 SAR and Sentinel-2 optical imagery to monitor irrigation events and crop dynamics in a dryland agricultural landscape. A microwave backscatter model was used to analyze the responses of simulated backscatters to soil moisture, NDVI and NDWI (both are correlated with vegetation water content and can be regarded as vegetation descriptors), allowing an empirical relationship between these two platforms. A correlation analysis was also performed using Sentinel-1 SAR and Sentinel-2 optical data over crops of maize, alfalfa, carrot and Rhodes grass in Al Kharj farm of Saudi Arabia to identify an appropriate SAR-based vegetation descriptor. The results illustrate the relationship between SAR and both NDVI and NDWI and demonstrated the relationship between the cross-polarization ratio (VH/VV) and the two optical indices. We explore the capacity of this multi-platform and multi-sensor approach to inform on the spatio-temporal dynamics of a range of agricultural activities, which can be used to facilitate field-based management decisions.

Combining Sentinel-1 and -3 Imagery for Retrievals of Regional Multitemporal Biophysical Parameters Under a Deep Learning Framework

Regions with excessive cloud cover lead to limited feasibility of applying optical images to monitor crop growth. In this study, we built an upsampling moving window network for regional crop growth monitoring (UMRCGM) model to estimate the two key biophysical parameters (BPs), leaf area index (LAI) and canopy chlorophyll content (CCC) during the main growth period of winter wheat by using Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-3 optical images. Sentinel-1 imagery is unaffected by cloudy weather and Sentinel-3 imagery has a wide width and short revisit period, the organic combination of the two will greatly improve the ability to monitor crop growth at a regional scale. The impact of two different types of SAR information (intensity and polarization) on the estimation of the two BPs was further analyzed. The UMRCGM model optimized the correspondence between inputs and outputs, it had more accurate LAI and CCC estimates compared with the three classical machine learning models, and had the highest accuracy at the green-up stage of winter wheat, followed by the jointing stage and the heading-filling stage, and the lowest accuracy was found at the milk maturity stage. The estimation accuracies of CCC were slightly higher than that of LAI for the first three growth stages of winter wheat, while lower than that of LAI for the milk maturity stage. This study proposes a new method for regional BPs (especially for CCC) estimation by combining SAR and optical imagery with large differences in spatial resolution under a deep learning framework.

Removing Cloud Cover Interference from Sentinel-2 imagery in Google Earth Engine by fusing Sentinel-1 SAR data with a CNNmodel

ABSTRACT Google Earth Engine (GEE) provides a convenient platform that enables the use of a diverse array of applications based on optical satellite images covering long time periods and large areas. However, cloud contamination often causes optical satellite images to lose land surface information, which can greatly affect their spatial and temporal availability in areas with frequent cloud cover. Reconstructing the missing values is very important when researchers attempt to improve the potential for using optical satellite images. Recently, convolutional neural network (CNN)-based methods have shown great potential in cloud removal. Unfortunately, current CNN-based cloud removal methods can only be applied locally, which would result in inefficient data downloading and storage problems. To address these problems, this paper proposes a method that integrates GEE data and a multi-level feature connected CNN (DeepGEE-S2CR) to remove clouds in Sentinel-2 imagery using Sentinel-1 Synthetic Aperture Radar imagery as auxiliary data. Specifically, the training process of the multi-level feature connected CNN was conducted locally, so that cloud removal could then be performed on the client of GEE using online data with the trained CNN model. An experiment using a set of globally distributed Sentinel-2 images was conducted to validate the proposed method; the results showed the process could generate results comparable to a classic deep Sentinel-2 cloud removal method (DSen2-CR) that should be run locally (the average root mean square errors of DeepGEE-S2CR and DSen2-CR were 0.045 and 0.042, respectively). The proposed method is especially convenient for removing clouds in Sentinel-2 imagery covering a large area.

Monthly mapping of forest harvesting using dense time series Sentinel-1 SAR imagery and deep learning

Compared with disturbance maps produced at annual or multi-year time steps, monthly mapping of forest harvesting can provide more temporal details needed for studying the socio-economic drivers (e.g., differentiating salvage logging and slash-and-burn from other timber harvesting) of harvesting and characterizing the associated intra-annual carbon and hydrological dynamics. Frequent cloud cover limits the application of optical remote sensing in timely mapping of forest changes. The freely available Sentinel-1 synthetic aperture radar (SAR) sensor provides an unprecedented opportunity to achieve more frequent mapping of forest harvesting than ever before (i.e., at monthly interval). The unique landscape pattern of forest harvesting from Sentienl-1 data (i.e., how a harvested patch contrasts to surrounding intact forests) holds critical information for harvesting mapping but have not been fully explored. In this study, we propose a deep learning-based (i.e., U-Net) approach using the landscape pattern from Sentinel-1 data to produce monthly maps of forest harvesting in two deforestation hotspots - California, USA and Rondônia, Brazil – for as long as three years. Our results show that (1) our proposed approach is reliable (mean F1 scores (the geometric mean of user's and producer's accuracies) 0.74–0.78; mean IoU (the area of intersection over union between the prediction part and target part) 0.59–0.65) for monthly forest harvesting mapping with Sentinel-1 data, outperforming the traditional object-based approach (0.38–0.43 in IoU). The varying harvesting pattern from Sentinel-1 data can be recognized by the U-Net bottleneck block as whole entities, which is the key advantage of our proposed approach; (2) multi-temporal SAR filtering is helpful for improving the accuracies of our proposed approach (increased F1 and IoU for 0.04 and 0.06, respectively); (3) our proposed model can be trained using samples collected during a particular time period over one location and be fine-tuned using sparse local samples from a new area to achieve optimal performance, and hence can greatly reduce training data collection effort when applied to new study sites; (4) forest harvesting maps produced using our approach revealed substantial variations in monthly harvesting activities: in Rondônia, most of the forest harvest occurred in July/August (the dry season) and about 14% of the dry season harvesting were followed by fires (i.e., slash-and-burn); in California, the rates of forest harvesting were relatively stable, but abnormally high values could occur due to salvage logging after big fires. Our novel approach for mapping forest harvesting at monthly interval represents an important step towards timely monitoring of forest harvesting and assisting stakeholders in developing sustainable strategy of forest management, especially for regions with frequent cloud cover.

An Adaptive Thresholding Approach toward Rapid Flood Coverage Extraction from Sentinel-1 SAR Imagery

Flood disasters have a huge effect on human life, the economy, and the ecosystem. Quickly extracting the spatial extent of flooding is necessary for disaster analysis and rescue planning. Thus, extensive studies have utilized optical or radar data for the extraction of water distribution and monitoring of flood events. As the quality of detected flood inundation coverage by optical images is degraded by cloud cover, the current data products derived from optical sensors cannot meet the needs of rapid flood-range monitoring. The presented study proposes an adaptive thresholding method for extracting water coverage (AT-EWC) regarding rapid flooding from Sentinel-1 synthetic aperture radar (SAR) data with the assistance of prior information from Landsat data. Our method follows three major steps. First, applying the dynamic surface water extent (DSWE) algorithm to Landsat data acquired from the year 2000 to 2016, the distribution probability of water and non-water is calculated through the Google Earth Engine platform. Then, current water coverage is extracted from Sentinel-1 data. Specifically, the persistent water and non-water datasets are used to automatically determine the type of image histogram. Finally, the inundated areas are calculated by combining the persistent water and non-water datasets and the current water coverage as derived from the above two steps. This approach is fast and fully automated for flood detection. In the classification results from the WeiFang and Ji’An sites, the overall classification accuracy of water and land detection reached 95–97%. Our approach is fully automatic. In particular, the proposed algorithm outperforms the traditional method over small water bodies (inland watersheds with few lakes) and makes up for the low temporal resolution of existing water products.

Deep convolutional neural network with random field model for lake ice mapping from Sentinel-1 imagery

ABSTRACT Timely information on lake ice cover conditions is critical in support of commercial shipping, winter-road transportation, and winter leisure activities such as snowmobiling and ice fishing. Monitoring of lake ice extent and ice phenology (i.e. dates associated with freeze-up/break-up and ice duration) is also valuable for improving numerical weather prediction (NWP) and for climate monitoring. The availability of free synthetic aperture radar (SAR) data from the European Space Agency’s Sentinel-1 A/B constellation provides an unprecedented opportunity to develop operational algorithms for lake ice cover mapping at a temporal frequency not available until now from SAR missions (ca. every 1–5 days depending on latitude). For NWP, rapid and accurate mapping of ice cover and open water areas in lake-rich regions is required. However, the classification of SAR imagery using traditional machine learning (ML) approaches is challenging due to the large data volume generated by imaging systems such as Sentinel-1 SAR as well as the complexity of radar signatures as a function of sensor and target characteristics. For lakes specifically, radar backscatter can vary greatly with incidence angle, polarization and surface properties (e.g. calm and wind-roughed open water, new thin ice, surface roughness due to the presence of pressure ridges, ice type, melting of ice and on-ice snow). To address the challenge of large-scale lake ice mapping, we investigate the GPU-boosted deep neural network approach that is efficient at handling big complex data. In this paper, we design a novel maximum a posterior (MAP) approach combining a convolutional neural network (CNN) and conditional random field (CRF) for better addressing the challenges of operational lake ice mapping. The proposed approach is tested on 17 Sentinel-1 dual-polarization (VV and VH) SAR images, where eight are used for training and validation and nine used for out-of-sample testing. To identify the optimal network architecture, an independent validation set is used to evaluate the performance of a series of six CNNs with increasing model complexity. The best model overcomes the noise effect in Sentinel-1 SAR imagery and the lake ice signature ambiguity issue; it achieves average classification accuracies of 97.10% and 97.14% for open water and ice, respectively, on the validation set. Moreover, the best model outperforms the last-ranked model by about 2% in terms of mean overall accuracy (OA), demonstrating the improvement and importance of model selection. The use of CRF can consistently improve the CNN by reducing the artefacts and noise effect in ice maps, outperforming the CNN model when used alone by about 3% in terms of mean OA on the validation set. The proposed CNN-CRF approach also achieves high accuracy on the nine test scenes, achieving a mean OA of 93.10%, demonstrating strong generalization capability that is important for SAR lake ice mapping.

Statistical Time-Series Analysis of Interferometric Coherence from Sentinel-1 Sensors for Landslide Detection and Early Warning.

Landslides are one of the most destructive natural hazards worldwide, affecting greatly built-up areas and critical infrastructure, causing loss of human lives, injuries, destruction of properties, and disturbance in everyday commute. Traditionally, landslides are monitored through time consuming and costly in situ geotechnical investigations and a wide range of conventional means, such as inclinometers and boreholes. Earth Observation and the exploitation of the freely available Copernicus datasets, and especially Sentinel-1 Synthetic Aperture Radar (SAR) images, can assist in the systematic monitoring of landslides, irrespective of weather conditions and time of day, overcoming the restrictions arising from in situ measurements. In the present study, a comprehensive statistical analysis of coherence obtained through processing of a time-series of Sentinel-1 SAR imagery was carried out to investigate and detect early indications of a landslide that took place in Cyprus on 15 February 2019. The application of the proposed methodology led to the detection of a sudden coherence loss prior to the landslide occurrence that can be used as input to Early Warning Systems, giving valuable on-time information about an upcoming landslide to emergency response authorities and the public, saving numerous lives. The statistical significance of the results was tested using Analysis of Variance (ANOVA) tests and two-tailed t-tests.

A novel cotton mapping index combining Sentinel-1 SAR and Sentinel-2 multispectral imagery

Cotton is an important cash crop in the world, as the main source of natural and renewable fiber for textiles. Accurate and timely monitoring of the cotton distribution is crucial for cotton cultivation management and international trade. However, most of the previous researches on cotton identification using remotely sensed images are highly dependent on training samples, and the collection of samples is time-consuming and expensive. To overcome this limitation, a new index, termed as Cotton Mapping Index (CMI), was developed in this study for automatic cotton mapping using time series of Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 Multispectral Instrument (MSI) satellite data. Four sites in the United States (U.S.) and four sites in China were selected to develop and assess the performance of the CMI. The spectral characteristics derived from Sentinel-2 and backscattering coefficients derived from Sentinel-1 for cotton and non-cotton crops during the cotton growth period were analyzed. Considering the phenology differences of crops in different regions, the features at an adaptive window were adopted to construct the CMI. The results showed that at the peak greenness period, the multiplication of red-edge 1 and red-edge 2 band for cotton samples were much larger than those for non-cotton samples, whereas the spectral angle at the red band as well as the absolute values of backscattering coefficients in vertical transmit and vertical receive (VV) polarization for cotton samples were much smaller than those for non-cotton samples. Based on these findings, the CMI was developed to identify cotton cultivated area within the cropland area. The overall accuracy of classification results for the sites in the U.S. was higher than 81.20%, and the mean relative error for the sites in Xinjiang of China was 26.69%. The CMI, which incorporated optical and radar features, had a better performance than the indices using optical features solely. The advantage of the CMI over supervised classifiers (i.e., k-nearest neighbors, support vector machine and random forest) is that no training samples are required. Moreover, the cotton distribution map can be obtained before the harvest using the CMI. These results indicated the potential of the CMI for cotton mapping. The applicability of CMI in other regions with different cropping systems and crop types needs to be further assessed in the future study.

Observation of Surface Displacement Associated with Rapid Urbanization and Land Creation in Lanzhou, Loess Plateau of China with Sentinel-1 SAR Imagery

Lanzhou is one of the cities with the higher number of civil engineering projects for mountain excavation and city construction (MECC) on the China’s Loess Plateau. As a result, the city is suffering from severe surface displacement, which is posing an increasing threat to the safety of the buildings. However, up to date, there is no comprehensive and high-precision displacement map to characterize the spatiotemporal surface displacement patterns in the city of Lanzhou. In this study, satellite-based observations, including optical remote sensing and synthetic aperture radar (SAR) sensing, were jointly used to characterize the landscape and topography changes in Lanzhou between 1997 and 2020 and investigate the spatiotemporal patterns of the surface displacement associated with the large-scale MECC projects from 2015 December to March 2021. First, we retrieved the landscape changes in Lanzhou during the last 23 years using multi-temporal optical remote sensing images. Results illustrate that the landscape in local areas of Lanzhou has been dramatically changed as a result of the large-scale MECC projects and rapid urbanization. Then, we optimized the ordinary time series InSAR processing procedure by a “dynamic estimation of digital elevation model (DEM) errors” step added before displacement inversion to avoid the false displacement signals caused by DEM errors. The DEM errors and the high-precision surface displacement maps between December 2015 and March 2021 were calculated with 124 ascending and 122 descending Sentinel-1 SAR images. By combining estimated DEM errors and optical images, we detected and mapped historical MECC areas in the study area since 2000, retrieved the excavated and filling areas of the MECC projects, and evaluated their areas and volumes as well as the thickness of the filling loess. Results demonstrated that the area and volume of the excavated regions were basically equal to that of the filling regions, and the maximum thickness of the filling loess was greater than 90 m. Significant non-uniform surface displacements were observed in the filling regions of the MECC projects, with the maximum cumulative displacement lower than −40 cm. 2D displacement results revealed that surface displacement associated with the MECC project was dominated by settlements. From the correlation analysis between the displacement and the filling thickness, we found that the displacement magnitude was positively correlated with the thickness of the filling loess. This finding indicated that the compaction and consolidation process of the filling loess largely dominated the surface displacement. Our findings are of paramount importance for the urban planning and construction on the Loess Plateau region in which large-scale MECC projects are being developed.

Monitoring the summer flooding in the Poyang Lake area of China in 2020 based on Sentinel-1 data and multiple convolutional neural networks

Precise monitoring of floods is significant in disaster management and loss reduction; however, remote sensing data resource and methods can largely affect the monitoring accuracy of flooded areas. In this study, we use cloud-free Sentinel-1 Synthetic Aperture Radar (SAR) imagery, preferable to the optical imagery. We have used 5 convolutional neural networks (CNNs), including HRNet, DenseNet, SegNet, ResNet and DeepLab v3 + for flood monitoring in the Poyang Lake area, and compared their performances with the traditional methods — the bimodal threshold segmentation (BTS) and the OSTU method. The HRNet has superior performance in water body identification with the highest precision and efficiency, based on a parallel structure to not only extract rich semantic information but also maintain high-resolution features in the whole process. Besides, speckle noise reduction by deep convolutional neural networks in SAR imagery is better compared with the Refined Lee filter. The CNNs are then used to monitor the temporal evolution of summer flooding (May-Nov.) in 2020. Results show the smallest water coverage of Poyang Lake in late May; it gradually increases to the maximum in mid-July, and then shows a downward trend until November.

Rapid and large-scale mapping of flood inundation via integrating spaceborne synthetic aperture radar imagery with unsupervised deep learning

Synthetic aperture radar (SAR) has great potential for timely monitoring of flood information as it penetrates the clouds during flood events. Moreover, the proliferation of SAR satellites with high spatial and temporal resolution provides a tremendous opportunity to understand the flood risk and its quick response. However, traditional algorithms to extract flood inundation using SAR often require manual parameter tuning or data annotation, which presents a challenge for the rapid automated mapping of large and complex flooded scenarios. To address this issue, we proposed a segmentation algorithm for automatic flood mapping in near-real-time over vast areas and for all-weather conditions by integrating Sentinel-1 SAR imagery with an unsupervised machine learning approach named Felz-CNN. The algorithm consists of three phases: (i) super-pixel generation; (ii) convolutional neural network-based featurization; (iii) super-pixel aggregation. We evaluated the Felz-CNN algorithm by mapping flood inundation during the Yangtze River flood in 2020, covering a total study area of 1,140,300 km2. When validated on fine-resolution Planet satellite imagery, the algorithm accurately identified flood extent with producer and user accuracy of 93% and 94%, respectively. The results are indicative of the usefulness of our unsupervised approach for the application of flood mapping. Meanwhile, we overlapped the post-disaster inundation map with a 10-m resolution global land cover map (FROM-GLC10) to assess the damages to different land cover types. Of these types, cropland and residential settlements were most severely affected, with inundation areas of 9,430.36 km2 and 1,397.50 km2, respectively, results that are in agreement with statistics from relevant agencies. Compared with traditional supervised classification algorithms that require time-consuming data annotation, our unsupervised algorithm can be deployed directly to high-performance computing platforms such as Google Earth Engine and PIE-Engine to generate a large-spatial map of flood-affected areas within minutes, without time-consuming data downloading and processing. Importantly, this efficiency enables the fast and effective monitoring of flood conditions to aid in disaster governance and mitigation globally.

A Novel Method for Automated Supraglacial Lake Mapping in Antarctica Using Sentinel-1 SAR Imagery and Deep Learning

Supraglacial meltwater accumulation on ice sheets can be a main driver for accelerated ice discharge, mass loss, and global sea-level-rise. With further increasing surface air temperatures, meltwater-induced hydrofracturing, basal sliding, or surface thinning will cumulate and most likely trigger unprecedented ice mass loss on the Greenland and Antarctic ice sheets. While the Greenland surface hydrological network as well as its impacts on ice dynamics and mass balance has been studied in much detail, Antarctic supraglacial lakes remain understudied with a circum-Antarctic record of their spatio-temporal development entirely lacking. This study provides the first automated supraglacial lake extent mapping method using Sentinel-1 synthetic aperture radar (SAR) imagery over Antarctica and complements the developed optical Sentinel-2 supraglacial lake detection algorithm presented in our companion paper. In detail, we propose the use of a modified U-Net for semantic segmentation of supraglacial lakes in single-polarized Sentinel-1 imagery. The convolutional neural network (CNN) is implemented with residual connections for optimized performance as well as an Atrous Spatial Pyramid Pooling (ASPP) module for multiscale feature extraction. The algorithm is trained on 21,200 Sentinel-1 image patches and evaluated in ten spatially or temporally independent test acquisitions. In addition, George VI Ice Shelf is analyzed for intra-annual lake dynamics throughout austral summer 2019/2020 and a decision-level fused Sentinel-1 and Sentinel-2 maximum lake extent mapping product is presented for January 2020 revealing a more complete supraglacial lake coverage (~770 km2) than the individual single-sensor products. Classification results confirm the reliability of the proposed workflow with an average Kappa coefficient of 0.925 and a F1-score of 93.0% for the supraglacial water class across all test regions. Furthermore, the algorithm is applied in an additional test region covering supraglacial lakes on the Greenland ice sheet which further highlights the potential for spatio-temporal transferability. Future work involves the integration of more training data as well as intra-annual analyses of supraglacial lake occurrence across the whole continent and with focus on supraglacial lake development throughout a summer melt season and into Antarctic winter.

Comparative Study of Flooding Area Detection with SAR Images based on Thresholding and Difference Images Acquired Before and After the Flooding

Comparative study of flooding area detection with Synthetic Aperture Radar (SAR) images based on thresholding and difference images acquired before and after the flooding is conducted. Method for flooding, landslide and sediment disaster area detections with SAR is proposed. The following two different methods for flooding detection are common. It is not so easy to determine a threshold for the thresholding method while subtraction method between before and after images of a disaster occurrence has the disadvantage that false disaster areas are detected due to a variation of ground cover targets. Therefore, a comparative study between both methods is required. Its application is demonstrated for the disaster which is occurred in Saga Prefecture, Japan due to a long term of heavy rain during from the begging of August to the middle of August in 2021. Through experiments with Sentinel-1 SAR imagery data, it is found that the proposed method works well for the detection of the disaster.