Multi-temporal Synthetic Aperture Radar Research Articles

Landslide Mapping in Calitri (Southern Italy) Using New Multi-Temporal InSAR Algorithms Based on Permanent and Distributed Scatterers

Landslides play a significant role in the morpho-evolutional processes of slopes, affecting them globally under various geological conditions. Often unnoticed due to low velocities, they cause diffuse damage and loss of economic resources to the infrastructure or villages built on them. Recognizing and mapping mass movements is crucial for mitigating economic and social impacts. Conventional monitoring techniques prove challenging for large areas, necessitating resource-intensive ground-based networks. Leveraging abundant synthetic aperture radar (SAR) sensors, satellite techniques offer cost-effective solutions. Among the various methods based on SAR products for detecting landslides, multi-temporal differential interferometry SAR techniques (MTInSAR) stand out for their precise measurement capabilities and spatiotemporal evolution analysis. They have been widely used in several works in the last decades. Using information from the official Italian landslide database (IFFI), this study employs Sentinel-1 imagery and two new processing chains, E-PS and E-SBAS algorithms, to detect deformation areas on the slopes of Calitri, a small town in Southern Italy; these algorithms assess the cumulated displacements and their state of activity. Taking into account the non-linear trends of the scatterers, these innovative algorithms have helped to identify a dozen clusters of points that correspond well with IFFI polygons.

InSAR supported by geophysical and geotechnical information constrains two-dimensional motion of a railway embankment constructed on peat

Rail and road embankments constructed on peatlands are subjected to significant challenges due to the high compressibility of peat. They are, therefore, susceptible to considerable settlement following construction. Accurate and timely monitoring of such embankments is important in order to enable proactive intervention strategies and to avoid failures. Multi-temporal Synthetic Aperture RADAR Interferometry (MT-InSAR) techniques applied to satellite-derived SAR data have been shown to be effective for remotely measuring and monitoring the deformation of civil engineering infrastructure. This paper presents a comprehensive approach, involving MT-InSAR supported by local geophysical and geotechnical information, for the detection and investigation of the movement of a railway embankment constructed on peatland. The Small Baselines approach, implemented in StaMPS (referred to as StaMPS-SB), was performed to measure long-term deformation of the embankment in vertical, horizontal east-west and satellite line-of-sight (LOS) directions. In this regard, a Sentinel-1 A/1B dataset composed of 362 descending images, acquired from 2015 to 2022, was analysed to measure LOS displacement. Also, 282 Sentinel-1 A/1B images of both ascending and descending tracks, collected from 2017 to 2022, were analysed to obtain vertical, horizontal and LOS displacements. According to the results, the maximum ground motion rate along the LOS direction was −29 mm/year for the period from 2015 to 2022. However, from 2017 to 2022, this value was about −25 mm/year and − 22 mm/year for descending and ascending tracks, respectively. During this period, the maximum motion rate obtained was −23.1 mm/year in the vertical direction. Moreover, horizontal movement up to −10 mm/year was observed in the westward direction and + 7 mm/year in the eastern direction. We used in-situ data to support corroborate and improve our interpretation of the InSAR results. In this context, peat thickness profiles, records of tamping activities and interpretations of the railway ballast base from ground penetrating radar data, were employed. The in-situ data revealed that the embankment section exhibiting the greatest vertical motion detected by InSAR corresponds closely to the thickest section of railway ballast, the zone of greatest number of tamping activities and the deepest section of peat. As such, this case study highlights how remote detection of embankment motion, coupled with targeted in-situ investigation, can underpin proactive intervention to improve safety.

Measuring Dam Deformation of Long-Distance Water Transfer Using Multi-Temporal Synthetic Aperture Radar Interferometry: A Case Study in South-to-North Water Diversion Project, China

Long-distance water transfer is a critical engineering measure to rectify disparities in water resource distribution across regions. The effective operation and safety of such projects are paramount to their success, as localized issues can have cascading consequences, potentially disrupting the entire network. Conventional ground-based monitoring methods have limitations in measuring the deformation of large-scale structures. In this paper, InSAR is employed to monitor the deformation of the Shuangwangcheng (SWC) Reservoir, which features a long embankment dam as part of the South-to-North Water Diversion Project in China. We utilize data from both Sentinel-1 and TerraSAR-X satellites to derive 7-year deformation. Results reveal that the entire dam experiences continuous subsidence, with the maximum deformation in the line-of-sight direction measuring ~160 mm. While minor differential settlements are noted in different sections of the dam, the gradient is not significant due to the dam’s substantial length. The InSAR deformation results from multiple geometries demonstrate good consistency, with the highest correlation observed between the Sentinel-1 ascending and descending datasets, exceeding 0.9. Validation against the GNSS observations of the three sites on the SWC Dam shows the accuracy of InSAR displacements is ~8 mm. Water level changes do impact deformation, but consolidation settlement appears to be the primary controlling factor during the monitoring period. This study underscores the potential of InSAR in long-distance water transfer projects and highlights that spatially continuous deformation is the most significant advantage.

Ground displacement analysis in the Sarulla geothermal field using Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) method

The Sarulla geothermal field is aggressively developed in Indonesia, reaching 330 MW in two consecutive years. Furthermore, the field is situated along the active Great Sumatra Fault. This condition has the potential to induce surface deformation phenomena attributed to exploitation activities, tectonic activities, or a combination of both. The Persistent Scatterer-Interferometric Synthetic Aperture Radar (PS-InSAR) method is a multi-temporal Synthetic Aperture Radar (SAR) image processing technique employed to detect surface deformations with millimeter-level accuracy. PS-InSAR has been applied in this paper over the Sarulla geothermal field, which comprises two exploited prospects (Silangkitang and Namora-I-Langit) and two unexploited prospects (Donotasik and Sibualbuali). The objective of this paper is to analyze the characteristics of ground displacement over the exploited and unexploited geothermal areas. Multi-temporal images of SENTINEL-1A with ascending and descending orbital modes from 2017 to 2021 were processed using PS-InSAR method. A series of interferograms from the selected primary image were paired with secondary images using SNAP program and Python-based program snap2stamps. The generated interferograms were used as input for the StaMPS program to obtain the persistent scatterers as the best coherent points. Ground displacement towards the satellite line of sight was observed within those two exploited geothermal areas adjacent to the production and injection zones. The descending images resulted in more significant PS points than ascending images. The exploited geothermal area shows a clustered pattern of PS points with a significant rate of ground displacement, whereas the unexploited area suggests a wide dispersion of PS points with a slight amount of displacement rate. Additionally, the detected ground displacement that occurred adjacent to the Great Sumatran Fault may indicate the active movement of the fault.

Deep Learning for Integrated Speckle Reduction and Super-Resolution in Multi-Temporal SAR

In the domain of synthetic aperture radar (SAR) image processing, a prevalent issue persists wherein research predominantly focuses on single-task learning, often neglecting the concurrent impact of speckle noise and low resolution on SAR images. Currently, there are two main processing strategies. The first strategy involves conducting speckle reduction and super-resolution processing step by step. The second strategy involves performing speckle reduction as an auxiliary step, with a focus on enhancing the primary task of super-resolution processing. However, both of these strategies exhibit clear deficiencies. Nevertheless, both tasks jointly focus on two key aspects, enhancing SAR quality and restoring details. The fusion of these tasks can effectively leverage their task correlation, leading to a significant improvement in processing effectiveness. Additionally, multi-temporal SAR images covering imaging information from different time periods exhibit high correlation, providing deep learning models with a more diverse feature expression space, greatly enhancing the model’s ability to address complex issues. Therefore, this study proposes a deep learning network for integrated speckle reduction and super-resolution in multi-temporal SAR (ISSMSAR). The network aims to reduce speckle in multi-temporal SAR while significantly improving the image resolution. Specifically, it consists of two subnetworks, each taking the SAR image at time 1 and the SAR image at time 2 as inputs. Each subnetwork includes a primary feature extraction block (PFE), a high-level feature extraction block (HFE), a multi-temporal feature fusion block (FFB), and an image reconstruction block (REC). Following experiments on diverse data sources, the results demonstrate that ISSMSAR surpasses speckle reduction and super-resolution methods based on a single task in terms of both subjective perception and objective evaluation metrics regarding the quality of image restoration.

A Statistical Approach for the Integration of Multi-Temporal InSAR and GNSS-PPP Ground Deformation Measurements.

Determining and monitoring ground deformations is critical for hazard management studies, especially in megacities, and these studies might help prevent future disaster conditions and save many lives. In recent years, the Golden Horn, located in the southeast of the European part of Istanbul within a UNESCO-protected region, has experienced significant changes and regional deformations linked to rapid population growth, infrastructure work, and tramway construction. In this study, we used Interferometric Synthetic Aperture Radar (InSAR) and Global Navigation Satellite System (GNSS) techniques to investigate the ground deformations along the Golden Horn coastlines. The investigated periods are between 2015 and 2020 and 2017 and 2020 for InSAR and GNSS, respectively. For the InSAR analyses, we used sequences of multi-temporal synthetic aperture radar (SAR) images collected by the Sentinel-1 and ALOS-2 satellites. The ground displacement products (i.e., time series and velocity maps) were then cross-compared with those achievable using the Precise Point Positioning (PPP) technique for the GNSS solutions, which can provide precise positions with a single receiver. In the proposed analysis, we compared the ground displacement velocities obtained by both methods by computing the standard deviations of the difference between the relevant observations considering a weighted least square estimation procedure. Additionally, we identified five circle buffers with different radii ranging between 50 m and 250 m for selecting the most appropriate coherent points to conduct the cross-comparison analysis. Moreover, a vertical displacement rate map was produced. The comparison of the vertical ground velocities derived from PPP and InSAR demonstrates that the PPP technique is valuable. For the coherent stations, the vertical displacement rates vary between -4.86 mm/yr and -23.58 mm/yr and -9.50 and -27.77 mm/yr for InSAR and GNSS, respectively.

SURFACE DEFORMATION MONITORING IN SHIYAN BASED ON MULTI-TEMPORAL INSAR TECHNOLOGY

Abstract. In recent years, InSAR technology has continuously developed and become a mainstream technology for monitoring wide-area surface deformation. In this study, Shiyan was selected as the work area, and Multi-temporal Synthetic Aperture Radar Interferometry (MT-InSAR) technology was used to monitor surface deformation over a long time series. The temporal and spatial distribution characteristics of the InSAR monitoring results were analyzed. The surveillance results showed that from January 2021 to March 2023, Shiyan experienced noticeable uneven settlement, with a deformation rate range of [−111.8mm/a, 20.9mm/a]. The maximum cumulative deformation variable reached −212.9mm, and more than 70 deformation zones were identified during the study period. The main causes of deformation were also analyzed. This study provides a reference for large-scale surface deformation monitoring and disaster management in Shiyan.

Ionospheric compensation in L-band InSAR time-series: Performance evaluation for slow deformation contexts in equatorial regions

Multi-temporal Synthetic Aperture Radar Interferometry (MT-InSAR) is the only geodetic technique allowing to measure ground deformation down to mm/yr over continuous areas. Vegetation cover in equatorial regions favors the use of L-band SAR data to improve interferometric coherence. However, the electron content of ionosphere, affecting the propagation of the SAR signal, shows particularly strong spatio-temporal variations near the equator, while the dispersive nature of the ionosphere makes its effect stronger on low-frequencies, such as L-band signals. To tackle this problem, range split-spectrum method can be implemented to compensate the ionospheric phase contribution. Here, we apply this technique for time-series of ALOS-PALSAR data, and propose optimizations for low-coherence areas. To evaluate the efficiency of this method to retrieve subtle deformation rates in equatorial regions, we compute time-series using four ALOS-PALSAR datasets in contexts of low to medium coherence, showing slow deformation rates (mm/yr to cm/yr). The processed tracks are located in Ecuador, Trinidad and Sumatra, and feature 15 to 19 acquisitions including very high, dominating ionospheric noise, corresponding to equivalent displacements of up to 2 m. The correction method performs well and allows to reduce drastically the noise level due to ionosphere, with significant improvement compared with a simple plane fitting method. This is due to frequent highly non-linear patterns of perturbation, characterizing equatorial TEC distribution. We use semivariograms to quantify the uncertainty of the corrected time-series, highlighting its dependence on spatial distance. Thus, using ALOS-PALSAR-like archive, one can expect a detection threshold on the Line-of-Sight velocity ranging between 3 and 6 mm/yr, depending on the spatial wavelength of the signal to be observed. These values are consistent with the accuracy derived from the comparison of velocities between two tracks in their overlapping area. In the case studies that we processed, the time-series corrected from ionosphere allows to retrieve accurately fault creep and volcanic signal but it is still too noisy for retrieving tiny long-wavelength signals such as slow (mm/yr) interseismic strain accumulation.

Spatio-temporal multi-level attention crop mapping method using time-series SAR imagery

Accurate crop mapping is of great significance for crop yield forecasting, agricultural productivity development and agricultural management. Thanks to its all-time and all-weather capability, integrating multi-temporal synthetic aperture radar (SAR) for crop mapping has become essential and challenging task in remote sensing. In recent years, deep learning (DL) has demonstrated excellent crop mapping accuracy to interpret crop dynamics. However, existing DL-based methods tend to be incapable of capturing spatial and temporal features at different scales simultaneously, and this often leads to severe mis-classification due to the complex and heterogeneous distribution of crops and diverse phenological patterns. In this paper, we propose a novel spatio-temporal multi-level attention method, named as STMA, for crop mapping using time-series SAR imagery in an end-to-end fashion to increase the capability of crop phenology retrieval. Specifically, the multi-level attention mechanism is designed to aggregate multi-scale spatio-temporal representations on crops via cascaded spatio-temporal self-attention (STSA) and multi-scale cross-attention (MCA) modalities. To ensure a fine extraction of multi-granularity features, a learnable spatial attention position encoding is proposed to adaptively generate the position priors to facilitate multi-level attention learning. Experimental results on Brandenburg Sentinel-1 dataset, public PASTIS-R dataset and South Africa dataset demonstrated that STMA can achieve state-of-the-art performance in crop mapping tasks, with the accuracy of 96.54% in the Brandenburg Sentinel-1 dataset, 86.77% in the PASTIS-R dataset and 83.37% in the South Africa dataset, validating its effectiveness and superiority. Further comparison of spatio-temporal generalization capability reflected its excellent performance in spatio-temporal modeling on different crops and scenarios. This research provides a viable and intelligent spatio-temporal framework for large-area crop mapping using time-series SAR imagery in complex agricultural systems. The Brandenburg Sentinel-1 dataset and the STMA code will be publicly available at https://github.com/hanzhu97702/ISPRS_STMA.

Alarming a tailings dam failure with a joint analysis of InSAR-derived surface deformation and SAR-derived moisture content

A tailings dam failure can be catastrophic. One constantly dumps or removes ore-related materials behind or within a dam before its closure, creating substantial surface change or deformation. The deformation can be assessed with multiple temporal synthetic aperture radar (SAR) observations and interferometric SAR (InSAR) techniques. The surface deformation is one prerequisite causing the failure. The water content increase is another primary factor that can reduce the surface friction among piled materials and induce further surface deformation. Intuitively, large deformation and high water content behind the tailings dam are concerns of a possible dam failure. Thus, we propose a new joint analysis of the InSAR-derived surface deformation and SAR-derived moisture content to achieve the objectives, delineating the stable/unstable status of a tailings dam and capturing a possible pre-failure signal of the dam. We study three types of tailing dams to verify the proposed analysis. The first is the Majiatian tailings dam in China, closed safely at the end of 2020. Our analysis determines that the dam status is stable. The second is the collapsed Córrego de Feijão Tailings Dam I in Brazil. The analysis identified a turning point from stable to unstable near December 2018, and the dam failure occurred in January 2019. In case three, an unstable status first at the Maanshan tailings dam was delineated. The findings were conveyed to parties interested in dam safety, and they carried out mitigation activities afterward. The analysis continued until February 2023, indicating a stable status of the tailings dam. The analysis is also robust to slight variations of moving window size around the proposed value. Thus, a valid joint analysis has been studied and is transferable to locations since the analysis and multitemporal SAR observations are available.

Mapping and Pre- and Post-Failure Analyses of the April 2019 Kantutani Landslide in La Paz, Bolivia, Using Synthetic Aperture Radar Data

Urban landslides have brought challenges to developing countries undergoing urbanization. Rapid approaches to assess ground deformation are required when facing the challenge of insufficient geological survey methods. Additionally, it is indeed a challenge to map landslide-affected areas, especially precipitation-induced landslides, through optical remote sensing methods. This study applied SAR change detection methods to map the slope failure event of the San Jorge Kantutani landfill site in La Paz, Bolivia, which occurred in April 2019, and Multi-Temporal Synthetic Aperture Radar Interferometry (MTInSAR) methods to assess pre- and post-failure ground stability related to this event. We found that the amplitude information of high-resolution COSMO-SkyMed SAR imagery and its texture information can be very useful in landslide mapping, especially in situations in which optical images are not available because of complex meteorological conditions and the similar spectral characteristics between the original land cover and landslide deposits. The MTInSAR analyses found that there was already significant deformation of more than 50 mm/year along the slope direction over this site before the landslide, and such deformation could be clearly discriminated from the surrounding environment. After the landslide event and the remobilization of the landslide deposit, the slope still shows a deformation velocity of more than 30 mm/year. The SAR amplitude change detection and MTInSAR fully exploited the SAR data in landslide studies and were useful in back analyzing the occurred landslides; this could be a good method for monitoring the ground stability of La Paz or even on a national scale over the long term for reducing the catastrophic effects of geological hazards in this landslide-prone city.

Monitoring maize lodging severity based on multi-temporal Sentinel-1 images using Time-weighted Dynamic time Warping

Lodging is one of the most important stresses in maize growth, which affects the yield, quality and mechanical harvesting ability of maize. Monitoring the lodging range and severity of large-scale maize by satellite remote sensing technology can support agricultural insurance claims, planting structure adjustment and field management. The purpose of this study is to investigate the application of Synthetic Aperture Radar (SAR) remote sensing images in monitoring the severity of maize lodging at the county scale. A time series feature dataset was obtained from multi-temporal Sentinel-1 SAR images before and after lodging. The sensitive features of maize lodging severity were screened by Jeffreys-Matusita (J-M) distance. The study compared the performance of three different methods for monitoring maize lodging severity, including Time-weighted Dynamic Time Warping (TwDTW), random forest (RF) and minimum distance (MinD). The results showed that all time phases of SAR images selected in the study had an important contribution to the differentiation of maize lodging severities. Among all features, the VH (Vertical Send and Horizontal Receive) time series features composed of five time-phase had better discrimination for different maize lodging severities. The accuracy of extracting maize lodging severities based on TwDTW was 76% and the Kappa coefficient was 0.70, which was higher than RF and MinD. Thus, by utilizing the multi-time phase features of Sentinel-1, we can effectively monitor the grades of maize lodging at the county scale.

Enhancing RABASAR for Multi-Temporal SAR Image Despeckling through Directional Filtering and Wavelet Transform.

The presence of speckle noise severely hampers the interpretability of synthetic aperture radar (SAR) images. While research on despeckling single-temporal SAR images is well-established, there remains a significant gap in the study of despeckling multi-temporal SAR images. Addressing the limitations in the acquisition of the "superimage" and the generation of ratio images within the RABASAR despeckling framework, this paper proposes an enhanced framework. This enhanced framework proposes a direction-based segmentation approach for multi-temporal SAR non-local means filtering (DSMT-NLM) to obtain the "superimage". The DSMT-NLM incorporates the concept of directional segmentation and extends the application of the non-local means (NLM) algorithm to multi-temporal images. Simultaneously, the enhanced framework employs a weighted averaging method based on wavelet transform (WAMWT) to generate superimposed images, thereby enhancing the generation process of ratio images. Experimental results demonstrate that compared to RABASAR, Frost, and NLM, the proposed method exhibits outstanding performance. It not only effectively removes speckle noise from multi-temporal SAR images and reduces the generation of false details, but also successfully achieves the fusion of multi-temporal information, aligning with experimental expectations.

A cross‐cross‐correlation based method for joint coregistration of rotated multitemporal synthetic aperture radar images

AbstractCoregistration is among the most important and challenging tasks when dealing with multiple synthetic aperture radar (SAR) images, especially when they are acquired at different time instants and characterised by low signal to noise power ratio (SNR) that contributes to their coherence reduction. However, even if some technological expedients could be implemented to maintain the same trajectory and to compensate for these inaccuracies during the acquisition campaign, multitemporal SAR images always need additional registration refinements after compression. Usually, to coregister a series of multitemporal SAR images, one of them is selected as the master, and the remainders are separately registered to it. Differently, in this study, a new strategy is developed to jointly coregister a stack of multitemporal SAR images. It is based on the exploitation of the cross‐correlations in turn computed from each couple of cross‐correlations (a.k.a. cross‐cross‐correlations) of the extracted patches. By doing so, the method is capable of exploiting also the respective misregistration information between the slaves during the estimation process. In this respect, this methodology is applied to enhance the registration capabilities of the constrained Least Squares (CLS) optimisation method, which instead does not account for the reciprocal information related to the slaves. Several tests are performed on multitemporal airborne‐measured SAR data. Obtained results show the effectiveness of the proposed algorithm in terms of achieved root mean square error for images affected by respective rotations also in comparison with the CLS counterpart.

What Have We Learned from the Past? An Analysis of Ground Deformations in Urban Areas of Palermo (Sicily, Italy) by Means of Multi-Temporal Synthetic Aperture Radar Interferometry Techniques

This study focuses on analyzing and monitoring urban subsidence, particularly in the city of Palermo, Italy. Land subsidence, induced by natural and human factors, poses threats to infrastructure and urban safety. Remote sensing (RS), specifically synthetic-aperture radar interferometry (In-SAR), is employed due to its ability to detect ground displacements over large areas with great precision. The persistent scatterer InSAR (PS-InSAR) technique is utilized to identify stable targets and track millimeter-level surface deformations. This research spans from October 2014 to October 2021, using Sentinel-1 satellite data to capture ground deformation from various angles. The findings are integrated into an accessible web app (ArcGIS) for local authorities that could be used aiding in urban planning and enhancing safety measures. This study’s results offer updated deformation maps, serving as an operational tool to support decision-making and community resilience, emphasizing risk awareness and responsible practices. This study highlights that the exponential expansion of urban areas, which does not take into account historical information, can gravely jeopardize both the integrity of urban infrastructure and the well-being of its inhabitants. In this context, remote sensing technologies emerge as an invaluable ally, used in monitoring and safeguarding the urban landscape.

Monitoring Urban Change in Conflict from the Perspective of Optical and SAR Satellites: The Case of Mariupol, a City in the Conflict between RUS and UKR

Modern armed conflicts can cause serious humanitarian disasters, and remote sensing technology is critical in monitoring war crimes and assessing post-war damage. In this study, a constrained energy minimization algorithm incorporating the feature bands (IFB-CEM) is designed to detect urban burning areas in optical images. Due to the difficulty of obtaining the ground survey data of the battlefield, the dual-polarization normalized coherence index (DPNCI) is designed based on the multi-temporal synthetic aperture radar (SAR) image, and the quantitative inversion and evaluation of the destruction of urban architecture are combined with the public images on the Internet. The results show that the burning area is widely distributed in the armed conflict region, and the distribution is most concentrated around the Azovstal steel and iron works. The burning area reached its peak around 22 March, and its change is consistent with the conflict process in time and space. About 79.2% of the buildings in the city were severely damaged or completely destroyed, and there was a significant correlation with burning exposure. The results of this study show that publicly available medium-resolution remote sensing data and Internet information have the ability to respond quickly to the damage assessment of armed conflict and can provide preliminary reference information for dealing with humanitarian disasters.

Evaluating the Capability of Sentinel-1 Data in the Classification of Canola and Wheat at Different Growth Stages and in Different Years

Canola and wheat are the main oilseed crop and grain crop, respectively, and they often have similar phenological stages. The understanding of the interactions between microwave signals with wheat and canola in different stages is important for their monitoring using synthetic aperture radar (SAR) imagery. This paper investigates the characteristics of canola and wheat through the use of backscattering profiles from multi-year Sentinel-1 images. Large fluctuations are observed for the temporal backscattering profiles of canola and wheat in different growth statuses induced by agrometeorological conditions in different years. The capability and stability of Sentinel-1 for wheat and canola mapping is further investigated using single- and multi-temporal SAR images hosted in Google Earth Engine (GEE) using the random forest classifier. Although different agrometeorological conditions and field managements make the temporal profiles of backscattering variations, the large difference in canopy structure allows SAR images to make the separability of canola and wheat stable on Sentinel-1 images in different phenology stages. The classification accuracies and the feature importance scores from multi-temporal classification in different years show that the backscattering features obtained at flowering to maturity stages make more contributions to the good-quality mapping of canola and wheat than those at other stages. The F1 scores of canola and wheat achieve 0.95 during the canola flowering and podding period, and the minimum F1 scores of 0.85 were also obtained at other stages. These findings show that SAR images have great potential in the good-quality mapping of canola and wheat in a wide phenology window.

Deep ResU-Net Convolutional Neural Networks Segmentation for Smallholder Paddy Rice Mapping Using Sentinel 1 SAR and Sentinel 2 Optical Imagery

Rice is a globally significant staple food crop. Therefore, it is crucial to have adequate tools for monitoring changes in the extent of rice paddy cultivation. Such a system would require a sustainable and operational workflow that employs open-source medium to high spatial and temporal resolution satellite imagery and efficient classification techniques. This study used similar phenological data from Sentinel-2 (S2) optical and Sentinel-1 (S1) Synthetic Aperture Radar (SAR) satellite imagery to identify paddy rice distribution with deep learning (DL) techniques. Using Google Earth Engine (GEE) and U-Net Convolutional Neural Networks (CNN) segmentation, a workflow that accurately delineates smallholder paddy rice fields using multi-temporal S1 SAR and S2 optical imagery was investigated. The study′s accuracy assessment results showed that the optimal dataset for paddy rice mapping was a fusion of S2 multispectral bands (visible and near infra-red (VNIR), red edge (RE) and short-wave infrared (SWIR)), and S1-SAR dual polarization bands (VH and VV) captured within the crop growing season (i.e., vegetative, reproductive, and ripening). Compared to the random forest (RF) classification, the DL model (i.e., ResU-Net) had an overall accuracy of 94% (three percent higher than the RF prediction). The ResU-Net paddy rice prediction had an F1-Score of 0.92 compared to 0.84 for the RF classification generated using 500 trees in the model. Using the optimal U-Net classified paddy rice maps for the dates analyzed (i.e., 2016–2020), a change detection analysis over two epochs (2016 to 2018 and 2018 to 2020) provided a better understanding of the spatial–temporal dynamics of paddy rice agriculture in the study area. The results indicated that 377,895 and 8551 hectares of paddy rice fields were converted to other land-use over the first (2016–2018) and second (2018–2020) epochs. These statistics provided valuable insight into the paddy rice field distribution changes across the selected districts analyzed. The proposed DL framework has the potential to be upscaled and transferred to other regions. The results indicated that the approach could accurately identify paddy rice fields locally, improve decision making, and support food security in the region.

Enhancing flood susceptibility modeling using multi-temporal SAR images, CHIRPS data, and hybrid machine learning algorithms

Flood susceptibility maps are useful tool for planners and emergency management professionals in the early warning and mitigation stages of floods. In this study, Sentinel-1 dB radar images, which provide Synthetic-Aperture Radar (SAR) data were used to delineate flooded and non-flooded locations. 12 input parameters, including elevation, lithology, drainage density, rainfall, Normalized Difference Vegetation Index (NDVI), curvature, ground slope, Stream Power Index (SPI), Topographic Wetness Index (TWI), soil, Land Use Land Cover (LULC), and distance from the river, were selected for model development. The importance of each input parameter on flood occurrences was assessed via the Mutual Information (MI) technique. Several machine learning models, including Radial Basis Function (RBF), and three hybrid models of Bagging (BA-RBF), Random Committee (RC-RBF), and Random Subspace (RSS-RBF), were developed to delineate flood susceptibility areas at Goorganrood watershed, Iran. The performance of each model was evaluated using several error indicators, including correlation coefficient (r), Nash Sutcliffe Efficiency (NSE), Mean Absolute Error (MSE), Root Mean Square Error (RMSE), and the Area Under the Receiver Operating Characteristic (ROC) Curve (AUC). The results showed that the hybrid techniques enhanced the modeling performance of the standalone model, and generally, all hybrid models are more accurate than the standalone model. Although all developed models have performed well, RC-RBF outperforms all of them (AUC = 0.997), followed by BA-RBF (AUC = 0.996), RSS-RBF (AUC = 0.992), and RBF (AUC = 0.975). Generally, about 12 % of the study area has high and very high susceptibility to future flood occurrences.

Coherent change detection of fine traces based on multi-angle SAR observations

Coherent change detection (CCD) is an effective method to detect subtle scene changes that occur between temporal synthetic aperture radar (SAR) observations. Most coherence estimators are obtained from a Hermitian product based on local statistics. Increasing the number of samples in the local window can improve the estimation bias, but cause the loss of the estimated images spatial resolution. The limitations of these estimators lead to unclear contour of the disturbed region, and even the omission of fine change targets. In this paper, a CCD approach is proposed to detect fine scene changes from multi-temporal and multi-angle SAR image pairs. Multi-angle CCD estimator can improve the contrast between the change target and the background clutter by jointly accumulating singleangle alternative estimator results without further loss of image resolution. The sensitivity of detection performance to image quantity and angle interval is analyzed. Theoretical analysis and experimental results verify the performance of the proposed algorithm.