Multi-temporal SAR Data Research Articles

Threshold-based inventory for flood susceptibility assessment of the world’s largest river island using multi-temporal SAR data and ensemble machine learning algorithms

Threshold-based inventory for flood susceptibility assessment of the world’s largest river island using multi-temporal SAR data and ensemble machine learning algorithms

Detecting and Monitoring Artisanal Mining Operations in Semi-Arid Terrain Using Multitemporal SAR Data for InSAR Coherence Estimation and Unsupervised Classification

Abstract. The impact of artisanal mining in sub-Saharan Africa and other developing countries are often huge as they leave trails of environmental and socio-economic effects on the people and the environment. 123 Multi-temporal SAR data acquired between 2019 and 2023 was used. SARPROZ was used to co-register the images and other preprocessing steps like radiometric and geometric correction to transform the images from SAR coordinates to geographic coordinates after generating all the interferograms. A stack of the 122 coherence map was created. Unsupervised classification was implemented on the stack. Principal component analysis of dimensionality reductions method yielded a far better result than the other unsupervised cluster methods attempted, it showed a very high classification accuracy of the terrain. The principal component analysis worked by computing the covariance matrix of the stacked coherence map then performed eigen-decomposition on it to yield eigenvectors and eigenvalues, The eigenvectors corresponding to the largest eigenvalues represent the principal components. These principal components capture the directions of maximum variance, and the eigenvectors provides a reduced-dimensional representation of the image stack which is then used to reconstruct an approximation of the original image that captures the essential features of the original SAR data. Backscatter intensity of the SAR images processed for this study period for unsupervised change detection and land cover classification, delineated the different features and classes based on long term coherence values.

Collaborative Inversion of Soil Water Content in Alpine Meadow Area Based on Multitemporal Polarimetric SAR and Optical Remote Sensing Data

Soil water content is a critical environmental parameter in research and practice, though various technological and contextual constraints limit its estimation in arid areas with vegetation cover. This study combined the multitemporal remote sensing data of Sentinel-1 and Landsat 8 to conduct an inversion study on surface soil water content under low vegetation cover in Nagqu, central Tibetan Plateau. Four vegetation indices (NDVI, ARVI, EVI, and RVI) were extracted from optical remote sensing data. A water cloud model was used to eliminate the influence of the vegetation layer on the backscattering coefficient associated with vegetation cover, and a predictive model suitable for the Nagqu area was constructed. The water cloud model effectively incorporated a vegetation index instead of vegetation water content. We found that VV polarization was more suitable for soil water content inversion than VH polarization. Among the four vegetation indices, the soil water content inversion model constructed with RVI under VV polarization had the best fit (R2 = 0.8212; RMSE = 6.30). The second-best fit was observed for vegetation water content-NDVI (R2 = 0.8201). The soil water content inversion models all had an R2 > 0.6, regardless of the vegetation index used, though the RVI had the best fitting effect, indicating that this vegetation index is highly applicable in the water cloud model, as a substitute for vegetation water content, and is expected to perform well in similar study sites.

Kharif rice growth and area monitoring in Gosaba CD block of Indian Sundarbans region using multi-temporal dual-pol SAR data

Kharif rice growth and area monitoring in Gosaba CD block of Indian Sundarbans region using multi-temporal dual-pol SAR data

Glacier facies characterisation in transboundary West Sikkim Himalaya from TerraSAR-X; GLCM based classification approach

ABSTRACT The proposed facies classification approach uses three features of the GLCM with multitemporal X-band SAR data of TerraSAR-X combined with k-means clustering. This approach was tested on 15 transboundary Himalayan glaciers. They were classified into six facies namely debris, dry snow, wet snow, bare ice, percolation zone 1 and percolation zone 2 and the covered areas for these classes are 20.56%, 12.50%, 20.26%, 13.16%, 25.49% and 8.03% of total area respectively. After classification, the signature for classes are validated using the benchmark outline of East Rathong glacier, India. The accuracy achieved is 89.56% with negligible variance and kappa of 0.87.

Multi-temporal AWiFS and SAR data for cropping system analysis in Indian Punjab

Multi-temporal AWiFS and SAR data for cropping system analysis in Indian Punjab

Despeckling Multitemporal Polarimetric SAR Data Based on Tensor Decomposition

Despeckling is an essential task in polarimetric synthetic aperture radar (PolSAR) image processing. Most existing filters developed for multi-temporal SAR images make use of either real or complex information. Real information refers to amplitude or intensity values, whereas complex information refers to complex covariance matrix (CCM) derived from either interferometric SAR (InSAR) or PolSAR data. The InSAR CCM is formed using images of the same polarimetric channel but acquired at different dates, and the PolSAR CCM contains information acquired simultaneously in different polarimetric channels. Therefore, these despeckling methods may present a good performance in some applications and scenes but fail in other cases, due to differences in input sources. In order to achieve a more robust result in all cases, we develop a method for multi-temporal polarimetric SAR data filtering based on tensor decomposition (TD-MPF), which aims at improving the identification of homogeneous pixels for spatially adaptive filtering. The key element of this approach consists of exploiting tensor theory to construct a new CCM that contains both polarimetric and interferometric information, as well as multi-temporal information for each pixel. The effectiveness of the proposed method and its performance are evaluated with simulated and real SAR data in comparison with several established methods.

Crop Classification of Multitemporal PolSAR Based on 3-D Attention Module With ViT

Multi-temporal polarimertic SAR is considered to be very effective in crop classification and cultivated land detection, which has received much attention from researchers. Currently, for most multi-temporal polarimetric SAR data classification methods, the simultaneous temporal-polarimetric-spatial feature extraction capability has not been exploited sufficiently. Also, the diversity of different time and different polarimetric features has not been taken into account sufficiently. In this paper, we propose a classification model that combines a dual-stream network as a temporal-polarimetric-spatial feature extraction module with Vision Transformer(ViT) called Temporal-Polarimetric-Spatial Transformer(TSPT) to address the above problems. Secondly, a 3 dimension(3D) convolutional attention module that enables the network to weight the temporal dimension, polarimetric feature dimension and spatial dimension is developed, according to their importance. Experimental results on both UAVSAR and RADARSAT-2 datasets show that the proposed method outperforms ResNet.

Monitoring of Flood Dynamics Using Multi Temporal Satellite Data: A Case Study of Kerala Floods 2018

India is one of the worst flood affected country in South East Asia and accounts for one fifth of global death count due to floods. It causes heavy losses to property, infrastructure, agriculture, land and overburdens the country's budget and resources. Around 40 million hectares of land in the country are subjected to floods according to National Flood Commission, and an average of 18.6 million hectares of land is affected annually. During 2018, Kerala was hit by two flood events in July and August. In August, 2018, Kerala experienced the worst ever floods in its history since 1924. The torrential rains triggered several landslides and forced the release of excess water from 37 dams across the state, aggravating the flood impact. The devastating floods and landslides caused extensive damage to houses, roads, railways, bridges, power supplies, communications networks, and other infrastructure. Satellite Remote Sensing has made substantial contribution in flood monitoring and damage assessment. The unique capabilities of satellites to provide comprehensive, synoptic and multi-temporal coverage of very large areas at regular interval and with quick turnaround time have been very valuable in monitoring and managing flood dynamics. The microwave region of the EM spectrum has a greater potential in identification of flooded areas because of almost all weather capability. In this study, multi-temporal microwave SAR data from RADARSAT and SENTINEL-1 satellites was used to map the flood affected areas in Kerala and to capture the dynamics of the spatial flood extent. The analysis showed maximum flood inundation in the second flood event in August. A steady recession of flood was observed in the July flood event. The peak flooding was observed on 18th August 2018. There is a rapid progression of flood from August 11th  to August 18th 2018 after which, a slight recession was observed from August 18th  to 21st ,2018. The flood could be seen slightly progressing in the next interval of August 21st  to 24th ,2018 after which, again  an overall recession in the spatial flood could be observed by 27th  August 2018. Kottayam, Pathanamthitta and Alappuzha were some of the worst flood affected districts. The maximum flood affected district is observed to be Alappuzha with a maximum flood inundated area of 27691hectares on 18 August 2018. In the district of Alappuzha a steady progression in the flood is observed after 21 August. Whereas in the other two districts namely Kottayam, Pathanamthitta the flood is found to be receeding after August 24, 2018. This study demonstrated the potential of multi-temporal satellite imageries for capturing the flood dynamics in a spatial domain. The progression and recession maps can be used for relief management by the disaster managers on the ground.

Machine learning-based meta-classifier for Kharif Bajra (pearl millet) discrimination in the mixed cropping environment using multi-temporal SAR data

Study on pearl millet discrimination in mixed cropping environment was carried out as it forms the major coarse cereal crop in India. The study aims at determining the capabilities of Sentinel-1A SAR data and Machine Learning (ML) algorithms for pearl millet discrimination. Six ML algorithms, that is, k-nearest neighbour (k-NN), Decision Tree (DT), support vector machine (SVM), random forest (RF), multi-layer perceptron (MLP) and Naïve Bayes (NB) were evaluated and compared. Meta-classifier using majority voting technique was proposed by ensembling classifiers (RF, SVM and NB) which were diverse and have comparable accuracies. The diversity assessment was conducted using Cochran Q statistics for ensembling purpose. RF classifier (83.76%) using VH polarization produced better result indicating importance of cross-polarization in crop classification. Further, meta-classifier proposed in the study improved the accuracy to 88.15% (approximately by 5%) and class accuracies of pearl millet resulting in improved discrimination of pearl millet in mixed cropping environment.

Cover classifications in wetlands using Sentinel-1 data (Band C): a case study in the Parana river delta, Argentina

With the launch of the Sentinel-1 mission, for the first time, multitemporal and dual-polarization C-band SAR data with a short revisit time is freely available. How can we use this data to generate accurate vegetation cover maps on a local scale? Our main objective was to assess the use of multitemporal C-Band Sentinel-1 data to generate wetland vegetation maps. We considered a portion of the Lower Delta of the Paraná River wetland (Argentina). Seventy-four images were acquired and 90 datasets were created with them, each one addressing a combination of seasons (spring, autumn, winter, summer, complete set), polarization (VV, HV, both), and texture measures (included or not). For each dataset, a Random Forest classifier was trained. Then, the kappa index values (κ) obtained by the 90 classifications made were compared. Considering the datasets formed by the intensity values, for the winter dates the achieved kappa index values (κ) were higher than 0.8, while all summer datasets achieved κ up to 0.76. Including feature textures based on the GLCM showed improvements in the classifications: for the summer datasets, the κ improvements were between 9% and 22% and for winter datasets improvements were up to 15%. Our results suggest that for the analyzed context, winter is the most informative season. Moreover, for dates associated with high biomass, the textures provide complementary information.

Crop Classification Based on the Physically Constrained General Model-Based Decomposition Using Multi-Temporal RADARSAT-2 Data

Crop identification and classification are of great significance to agricultural land use management. The physically constrained general model-based decomposition (PCGMD) has proven to be a promising method in comparison with the typical four-component decomposition methods in scattering mechanism interpretation and identifying vegetation types. However, the robustness of PCGMD requires further investigation from the perspective of final applications. This paper aims to validate the efficiency of the PCGMD method on crop classification for the first time. Seven C-band time-series RADARSAT-2 images were exploited, covering the entire growing season over an agricultural region near London, Ontario, Canada. Firstly, the response and temporal evolution of the four scattering components obtained by PCGMD were analyzed. Then, a forward selection approach was applied to achieve the highest classification accuracy by searching an optimum combination of multi-temporal SAR data with the random forest (RF) algorithm. For comparison, the general model-based decomposition method (GMD), the original and its three improved Yamaguchi four-component decomposition approaches (Y4O, Y4R, S4R, G4U), were used in all tests. The results reveal that the PCGMD method is highly sensitive to seasonal crop changes and matches well with the real physical characteristics of the crops. Among all test methods used, the PCGMD method using six images obtained the optimum classification performance, reaching an overall accuracy of 91.83%.

Mapping paddy rice using an adaptive stacking algorithm and Sentinel-1/2 images based on Google Earth Engine

ABSTRACT Rice is the most important food crop in China, which is of great significance to the country’s food security and regional stability. Therefore, it is very important to accurately monitor the paddy rice planting area and its changes. In this study, an adaptive-stacking method based on Google Earth Engine (GEE) was proposed to identify paddy rice using multi-temporal Sentinel-1 and Sentinel-2 remote sensing data. The classification accuracy and Kappa coefficient are 88.53% and 0.85, respectively. Moreover, the user accuracy and producer accuracy of paddy rice reached 86.58% and 86.92%, respectively. The results demonstrate that the superiority of the strategy that integrates multi-temporal optical and SAR data, and the potential of using adaptive-Stacking algorithm based on the GEE for paddy classification.

Geospatial investigation on transitional (quiescence to surge initiation) phase dynamics of Monacobreen tidewater glacier, Svalbard

The change in the phase, from quiescence to surge, may perturb the glacier’s dynamical behavior. To understand these changes through geospatial technique, the fastest moving tidewater Monacobreen Glacier, Svalbard, was studied for the year 2016–2019. It was elucidated that the surge had initiated during 2017–2018 before it the glacier was in quiescence since 2001. Initially, the glacier radar zones, namely percolation refreeze, lower percolation, and clean ice, were identified using the multi-temporal SAR data. These zones were utilized to delineate the equilibrium line altitude, and it was found that it is continuously moving down during surging, unlike the quiescence phase. The accumulation area ratio was always more than 0.67 throughout the analysis. The seasonal change in glacier surface velocity for both the phases was estimated, adapting the most appropriate Offset Tracking approach using the SAR data. The mean velocity over the main trunk was found to vary from 0.5 to 4 m/day. Thereafter, Glen's flow law equation was used to estimate the ice-thickness and found that the glacier has an average thickness range of 216–326 m in quiescence and 136–244 m during the surging. The analysis depicted that the basal shear stresses are increasing with surging, and the viscosity is decreasing. It can be said that the transition of the glacier from quiescent to surging phase has entirely changed its dynamic behavior and characteristics. Further, in the absence of field observations, the geospatial technique may provide reasonable estimates of the glacier’s physical and dynamical parameters.

Segmentation of multi-temporal polarimetric SAR data based on mean-shift and spectral graph partitioning.

Polarimetric SAR (PolSAR) image segmentation is a key step in its interpretation. For the targets with time series changes, the single-temporal PolSAR image segmentation algorithm is difficult to provide correct segmentation results for its target recognition, time series analysis and other applications. For this, a new algorithm for multi-temporal PolSAR image segmentation is proposed in this paper. Firstly, the over-segmentation of single-temporal PolSAR images is carried out by the mean-shift algorithm, and the over-segmentation results of single-temporal PolSAR are combined to get the over-segmentation results of multi-temporal PolSAR images. Secondly, the edge detectors are constructed to extract the edge information of single-temporal PolSAR images and fuse them to get the edge fusion results of multi-temporal PolSAR images. Then, the similarity measurement matrix is constructed based on the over-segmentation results and edge fusion results of multi-temporal PolSAR images. Finally, the normalized cut criterion is used to complete the segmentation of multi-temporal PolSAR images. The performance of the proposed algorithm is verified based on three temporal PolSAR images of Radarsat-2, and compared with the segmentation algorithm of single-temporal PolSAR image. Experimental results revealed the following findings: (1) The proposed algorithm effectively realizes the segmentation of multi-temporal PolSAR images, and achieves ideal segmentation results. Moreover, the segmentation details are excellent, and the region consistency is good. The objects which can’t be distinguished by the single-temporal PolSAR image segmentation algorithm can be segmented. (2) The segmentation accuracy of the proposed multi-temporal algorithm is up to 86.5%, which is significantly higher than that of the single-temporal PolSAR image segmentation algorithm. In general, the segmentation result of proposed algorithm is closer to the optimal segmentation. The optimal segmentation of farmland parcel objects to meet the needs of agricultural production is realized. This lays a good foundation for the further interpretation of multi-temporal PolSAR image.

Multitemporal SAR and Polarimetric SAR Optimization and Classification: Reinterpreting Temporal Coherence

In multitemporal SAR and Polarimetric SAR (Pol-SAR) coherence is a capital parameter to exploit common information between temporal acquisitions. Yet, its use is limited to high coherences. This article proposes the analysis of low coherence scenarios by introducing a reinterpretation of coherence. It is demonstrated that coherence results from the product of two terms accounting for coherent and radiometric changes, respectively. For low coherences, the first term presents low values, preventing its exploitation for information retrieval. The information provided by the second term can be used in these circumstances to exploit common information. This second term is proposed, as an alternative to coherence, for information retrieval for low coherences. Besides, it is shown that polarimetry allows the temporal optimization of its values. To prove the benefits of this approach, multitemporal SAR and PolSAR data classification is considered as a tool, showing that improvements of the classification overall accuracy may range between 20% and 50%, compared to classification based on coherence.

Statistical Analysis for Tidal Flat Classification and Topography Using Multitemporal SAR Backscattering Coefficients

Coastal zones are very dynamic natural systems that experience short-term and long-term morphological changes. Their highly dynamic behavior requires frequent monitoring. Tidal flat topography for a large spatial coverage has been generated mainly by the waterline extraction method from multitemporal remote sensing observations. Despite the efficiency and robustness of the waterline extraction method, the waterline-based digital elevation model (DEM) is limited to representing small scale topographic features, such as localized tidal tributaries. Tidal flats show a rapid increase in SAR backscattering coefficients when the tide height is lower than the tidal flat topography compared to when the tidal flat is covered by water. This leads to a tidal flat with a distinct statistical behavior on the temporal variability of our multitemporal SAR backscattering coefficients. Therefore, this study aims to suggest a new method that can overcome the constraints of the waterline-based method by using a pixel-based DEM generation algorithm. Jenks Natural Break (JNB) optimization was applied to distinguish the tidal flat from land and ocean using multitemporal Senitnel-1 SAR data for the years 2014–2020. We also implemented a logistic model to characterize the temporal evolution of the SAR backscattering coefficients along with the tide heights and estimated intertidal topography. The Sentinel-1 DEM from the JNB classification and logistic function was evaluated by an airborne Lidar DEM. Our pixel-based DEM outperformed the waterline-based Landsat DEM. This study demonstrates that our statistical approach to intertidal classification and topography serves to monitor the near real-time spatiotemporal distribution changes of tidal flats through continuous and stable SAR data collection on local and regional scales.

Change Detection of Selective Logging in the Brazilian Amazon Using X-Band SAR Data and Pre-Trained Convolutional Neural Networks

It is estimated that, in the Brazilian Amazon, forest degradation contributes three times more than deforestation for the loss of gross above-ground biomass. Degradation, in particular those caused by selective logging, result in features whose detection is a challenge to remote sensing, due to its size, space configuration, and geographical distribution. From the available remote sensing technologies, SAR data allow monitoring even during adverse atmospheric conditions. The aim of this study was to test different pre-trained models of Convolutional Neural Networks (CNNs) for change detection associated with forest degradation in bitemporal products obtained from a pair of SAR COSMO-SkyMed images acquired before and after logging in the Jamari National Forest. This area contains areas of legal and illegal logging, and to test the influence of the speckle effect on the result of this classification by applying the classification methodology on previously filtered and unfiltered images, comparing the results. A method of cluster detections was also presented, based on density-based spatial clustering of applications with noise (DBSCAN), which would make it possible, for example, to guide inspection actions and allow the calculation of the intensity of exploitation (IEX). Although the differences between the tested models were in the order of less than 5%, the tests on the RGB composition (where R = coefficient of variation; G = minimum values; and B = gradient) presented a slightly better performance compared to the others in terms of the number of correct classifications for selective logging, in particular using the model Painters (accuracy = 92%) even in the generalization tests, which presented an overall accuracy of 87%, and in the test on RGB from the unfiltered image pair (accuracy of 90%). These results indicate that multitemporal X-band SAR data have the potential for monitoring selective logging in tropical forests, especially in combination with CNN techniques.

Systematic discrimination of irrigation and upheaval associated salinity using multitemporal SAR data

The increasing salinization in the soil profile by irrigation water and groundwater upheaval is a widespread issue and considered as a major threat to agricultural production in arid and semi-arid regions. The present study aimed to propose a systematic SAR simulation involving the imaginary part of dielectric constant measurements of two consecutive seasons (dry and wet) to quantify and discriminate the irrigation-induced and upheaval-associated salinity from total salinity levels and investigate its impact on crop growth. The Sentinel-1 data of C-band frequency (5.36 GHz) acquired for both the dry and wet spells from 2015 to 2019 was instrumental in the present study. The total soil EC (Electrical Conductivity) was quantified from the imaginary part of dielectric constant (ε″) using semi-empirical microwave simulation “DSDM-SS”. Irrigation-induced salinity (εIrrigation″) and upheaval-associated salinity (εUpheaval″) were extracted from ε″ by proposing a site-, and climatic-specific novel model. The εUpheaval″ and εIrrigation″ have shown promising statistical significance with the in-situ soil EC (R2 = 0.89, p = <0.001, rMSE = 1.08, Bias = 0.584) and groundwater EC measurements (R2 = 0.85, p = <0.001, rMSE = 1.28, Bias = 1.16). The study found that the rate of salinity increase over time due to irrigation (77%) was considerably higher than the upheaval (42%) process. This demonstrated that the intensive use of groundwater for irrigation has a higher impact on vegetation vigor (θ = −0.87) than the upheaval process. The study revealed that crop failure in the dry season was provoked by osmotic stress and waterlogging conditions.

A Fast Phase Optimization Approach of Distributed Scatterer for Multitemporal SAR Data Based on Gauss–Seidel Method

Distributed scatterer (DS) interferometric synthetic aperture can retrieve maximum available information by jointly processing persistent scatterers (PSs) and DSs. Unlike PSs, DSs are vulnerable to temporal, geometrical, and volumetric decorrelation. The phase optimization of DSs is essential for reliable parameter estimation. However, the preprocessing of DSs is very computationally expensive, and this drawback limits its engineering application to some degree. To improve computational efficiency, a fast scheme for reliable phase optimization of DSs is proposed based on the coherence-weighted model in this letter. The Gauss–Seidel iteration, having the advantages of fast convergence rate and small data memory, is introduced to solve the adopted phase optimization model. Experiments both on simulated data and real data are used to verify the reliability and efficiency of the presented method in this letter.