A novel classification method based on texture analysis using high-resolution SAR and optical data

Normalized Difference Vegetation Index (NDVI) values extracted from remotely sensed optical imagery are used ubiquitously to monitor crop condition. However, challenges in the operational use of optical imagery are well documented making it difficult to capture measures of crop condition during critical phenology stages when clouds obscure. This study investigates the integration of Synthetic Aperture Radar (SAR) and optical imagery to characterize the condition of crop canopies in order to deliver daily measures of NDVI during the entire growing season. Multitemporal C-band polarimetric RADARSAT-2 SAR data and RapidEye images were acquired in 2012 for a study site in western Canada. SAR polarimetric parameters and NDVI were extracted. The temporal variations in SAR polarimetric parameters and NDVI were interpreted with respect to the development of the canola canopy. Optical NDVI was statistically related with SAR polarimetric parameters over test canola fields. Significant correlations were documented between a number of SAR polarimetric parameters and optical NDVI, in particular with respect to HV backscatter, span, volume scattering of the Freeman Durden decomposition and the radar vegetation index, with R-values of 0.83, 0.72, 0.81 and 0.71 respectively. Based on the statistical analysis, SAR polarimetric parameters were calibrated to optical NDVI, creating a SAR-calibrated NDVI (SARc-NDVI)). A canopy structure dynamics model (CSDM) was fitted to the SARc-NDVI, providing a seasonal temporal vegetation index curve. The coupling of NDVI from optical and SAR imagery with a CSDM demonstrates the potential to derive daily measures of crop condition over the entire growing season.

Synthetic Aperture Radar (SAR) imagery have been one of the important tools to support earth observations and topographic measurements. It means SAR imagery are essentially rich in structures and some important target categories are difficult to recognize. Optical imagery contains rich and clear spectral information which has a good influence on semantic image segmentation. The success of deep neural networks for semantic segmentation heavily depends on large-scale and well-labeled data sets, which are hard to collect in practice. In this paper, we consider deep transfer learning for semantic segmentation, we propose a deep novel transfer learning method, which transfers a semantically segment model from SAR imagery to SAR and optical fusion imagery. The experimental results show that the method proposed achieves higher mean Intersection over Union (mIoU) with less training time compared with other methods.

Ship detection in high-resolution synthetic aperture radar (SAR) imagery is a fundamental and challenging problem due to the complex environments. In this paper, a RetinaNet-Plus method is presented for ship detection in high-resolution SAR imagery based on RetinaNet network modified. In this approach, instead of setting the score for neighboring region proposals to zero as in Non-Maximum Suppression (NMS), Soft-NMS decreases the detection scores as an increasing function of overlap to avoid loss of precision. In addition, focal loss is used to address the class imbalance and to increase the importance of the hard examples during training. The experiments on SAR ship SSDD dataset and TerraSAR-X image from Barcelona port, show that our method is more accurate than the existing algorithms and is effective for ship detection of high-resolution SAR imagery.

For the spatiotemporal analysis of water resources and disasters, water body detection using satellite imagery is crucial. Recently, AI-based methods have been widely employed in water body detection using satellite imagery. To use these AI techniques, a substantial amount of training data is required. When creating training data for water body detection, optical imagery and synthetic aperture radar (SAR) imagery have their respective strengths and weaknesses. To use the advantages of both, this study proposes a water body detection method through the fusion of optical and SAR imagery. The results of the proposed model show an Intersection over Union of 0.612 and an F1 score of 0.759, which is better compared to using either optical or SAR imagery alone. This research presents a method that can easily generate a large amount of water body data, making it promising for use as AI training data for water body detection.

ABSTRACTGlaciers and ice sheets are sensitive indicators of climate change. The changes of outlines and texture features on the glacier surface are useful indicators of glacier change monitoring. The sensitivity of synthetic aperture radar (SAR), which is independent of weather and solar illumination, provides an efficient approach for glacier monitoring and the development of high-resolution SAR makes it possible to study glaciers in more detail. In this article, the decision-tree classification method, the Canny operator, and the phase congruency method are applied and compared to extract glacier outlines and water-eroded stripes using X-band high-resolution SAR imagery of the Dongkemadi glacier area in the Qinghai–Tibet Plateau, collected by the TerraSAR satellites. The experimental results are presented to illustrate the accuracy and efficiency of the phase congruency method as compared to other methods used for the extraction of linear features (outline and stripes) on glaciers. The phase congruency method, which is independent of image illumination and magnification, is used for the first time in glacier outline and stripe extraction. It is shown that, when combined with high-resolution SAR imagery, this method has the potential to provide valuable support for glacier mapping and change monitoring in the future.

Synthetic Aperture Radar (SAR) satellite systems may give important contribution in terms of Digital Surface Models (DSMs) generation considering their complete independence from logistic constraints on the ground and weather conditions. In recent years, the new availability of very high resolution SAR data (up to 20 cm Ground Sample Distance) gave a new impulse to radargrammetry and allowed new applications and developments. Besides, to date, among the software aimed to radargrammetric applications only few show as free and open source. It is in this context that it has been decided to widen DATE (Digital Automatic Terrain Extractor) plug-in capabilities and additionally include the possibility to use SAR imagery for DSM stereo reconstruction (i.e. radargrammetry), besides to the optical workflow already developed. <br><br> DATE is a Free and Open Source Software (FOSS) developed at the Geodesy and Geomatics Division, University of Rome “La Sapienza”, and conceived as an OSSIM (Open Source Software Image Map) plug-in. It has been developed starting from May 2014 in the framework of 2014 Google Summer of Code, having as early purpose a fully automatic DSMs generation from high resolution optical satellite imagery acquired by the most common sensors. <br><br> Here, the results achieved through this new capability applied to two stacks (one ascending and one descending) of three TerraSAR-X images each, acquired over Trento (Northern Italy) testfield, are presented. Global accuracies achieved are around 6 metres. These first results are promising and further analysis are expected for a more complete assessment of DATE application to SAR imagery.

Active remote sensing technologies, including airborne laser scanning (LIDAR), interferometric radar (InSAR) have the capability to provide accurate information relating to three-dimensional forest canopy structure over extensive areas of the landscape. Detailed mapping of forests height and terrain features is now possible through 3D remote sensing. Consequently, forest inventory parameters are evaluated through point cloud and normalized surface models. Practically, forest resource mapping is carried out through Airborne Laser Scanner (ALS). In the modern age, ALS achieve considerable popularity in alternative 3-D techniques along with the apace-borne and air-borne sensors. Point clouds are generated through radargrammetry, photogrammetry and interferometry. Photogrammetric point clouds are derived through airborne stereo imagery while radargrammetry and interferometry utilize very-high-resolution Synthetic Aperture Radar (SAR) data. Similarly, high resolution optical data is also used for forest inventory. ALS has the ability of mapping tree heights and terrain in even mixed forest scenarios, which is advantageous over SAR data or aerial imagery. To put it simply, in the forest scenarios, height of the canopy, single tree heights and canopy density can be mapped. Forest zoning, crown density, crown height and forest area has been mapped out using these different datasets in comparison. In this paper, first we review experiences of the use of ALS data in estimation of forest inventory parameters in Lubrecht forest in California, and we compare techniques to SAR and optical imagery. In addition, on the basis of our experiences, we aim to present new implications.

Oil spills on the ocean from ships have a strong impact on the environment as well as on human societies. The MV X-Press Pearl container ship incident in 2021 became the worst marine environmental disaster in Sri Lanka due to its powerful impact. Oil leakage from the ship to the ocean continued for months. Synthetic Aperture Radar (SAR) imagery has the advantage of penetrating cloud cover, as well as day and night operating capabilities. Therefore, SAR imagery can be used to detect as well as observe the temporal changes of oil spills. The study in this article aimed to detect the oil spill caused by the MV X-Press Pearl container ship on Sri Lanka’s west coast from May to August 2021 using Sentinel-1 SAR data and measure the temporal changes of the oil slick. Three SAR imageries with Vertical-Vertical (VV) and Vertical-Horizontal (VH) polarization from June, July, and August of 2021 have been processed by applying the orbit file, running the multi-looking algorithm, and making the ellipsoid correction. The possible oil spills have been identified from each set of imagery as dark linear shapes with lengths of 3.1 ±0.012 km with an average reflectance of 15.6 decibels for June and 3.6 ±0.012 km with an average reflectance of 16.5 decibels for the other two months, and the shapes correspond with the oil slick classifications from other literature. The results indicate that the VV polarization is the most suitable to detect oil spills, and that the oil spill from the X-Press Pearl continued from June to the end of August 2021.

Synthetic Aperture Radar (SAR) imagery is available all the time and, in all weathers, due to its ability to penetrate through cloud cover, dust, haze except heavy rainfall. SAR imagery mainly characterizes structural properties of various earth objects and provides a data which is rich in spatial information. Processing of SAR data has been of great interest due to these advantages. However, due to coherent processing of SAR signal, imagery is corrupted by speckle noise which is multiplicative in nature. Reduction of speckle noise from SAR imagery is helpful for analysis and interpretation of SAR images. In this paper, performance of conventional speckle reduction filters, namely Lee, Enhanced Lee, Frost, Enhanced Frost and Gamma MAP are compared with wavelet-based filtering technique for RISAT-1 imagery. Results are compared visually and using quality metrics, Speckle Suppression Index (SSI), Equivalent Number of Looks (ENL) and Speckle Suppression and Mean Preservation Index (SMPI). From visual interpretation of de-speckled image, it is evident that wavelet-based filtering out performs the conventional filters in terms of edge and texture preservation.

Rock slope failures are the catastrophic expression of long-term geomorphological processes occurring in alpine regions. Their impact is often limited to single slopes; however, rock and debris material can occasionally travel very long distances and affect landscape, infrastructures, as well as endanger human life several kilometers away from the source area. Monitoring the evolution of surface activity is recognized as a suitable method to timely identify changes potentially leading to such failure events. Satellite based remote sensing, and in particular Synthetic Aperture Radar (SAR), has shown to be an efficient alternative to in-situ sensors to monitor displacements, especially in situations where the area of interest is large and/or barely accessible. Despite the advent of satellite missions like the ESA Copernicus Sentinel-1, operational monitoring and early warning on single slopes exhibiting surface displacement acceleration potentially leading to failure is still not viable from satellite radars. This is mainly because of the current limitations in spatial and temporal resolution, which prevent obtaining the accuracy and the timeliness often needed for such scenarios.Here we demonstrate how high spatial and temporal resolution SAR imagery can improve monitoring and characterization of the evolution of a rock slope instability prior and after catastrophic failure. We benefit from ICEYE imagery (X-Band, SPOT mode, 5x5 km scene size, ~50cm resolution) acquired over the Brienz/Brinzauls slope instability in the Swiss Alps between March and August 2023. Among 100 SAR images, we have identified a subset of 30 datasets (ascending orbit, left looking) providing an optimal viewing of the moving slope and imaging the area of interest with revisit times ranging from 3 days to a few hours. We use digital image correlation to measure surface displacements and change detection analyses to map rockfall activity and the slope failure event on June 15th, 2023. We also applied SAR interferometry on data pairs exhibiting suitable perpendicular baselines and computed topographic models at different times and determine failed volumes. The latter have been validated with local terrain models based on photogrammetric drone flights. We discuss the results obtained with ICEYE imagery versus the possibilities with Sentinel-1 data and focus on advantages and specific problems. Our results provide an important step forward towards the use of satellite SAR imagery for operational landslide monitoring scenarios and in the identification and forecasting of catastrophic slope failure events in alpine areas. 

<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">X</tex> -band synthetic aperture radar (SAR) imagery of the Goto Islands of Japan was digitally analyzed to extract air-sea interaction parameters and to assess the potential of texture measures in analysis of SAR ocean imagery. Wind direction is extracted from wind rows, wind streaks, and random turbulence patterns observed in the SAR imagery. Sea-state parameters are either extracted directly from the imagery or estimated using the extracted information in previously established empirical formulas. A convenient method of digitally presenting imagery, local power spectra, and the extracted/estimated parameters is presented. Texture analysis based on gray-level co-occurrence (GLC) matrices is applied to SAR ocean imagery. The inertia measure is shown to extract similar information to the power spectrum. The cluster-shade measure is shown to be sensitive to image phase.

A generalized control chart for anomaly detection in SAR imagery

Land use and land cover (LULC) classification through remote sensing imagery serves as a cornerstone for environmental monitoring, resource management, and evidence-based urban planning. While Synthetic Aperture Radar (SAR) and optical sensors individually capture distinct aspects of Earth’s surface, their complementary nature SAR excelling in structural and all-weather observation and optical sensors providing rich spectral information—offers untapped potential for improving classification robustness. However, the intrinsic differences in their imaging mechanisms (e.g., SAR’s coherent scattering versus optical’s reflectance properties) pose significant challenges in achieving effective multimodal fusion for LULC analysis. To address this gap, we propose a multimodal deep-learning framework that systematically integrates SAR and optical imagery. Our approach employs a dual-branch neural network, with two fusion paradigms being rigorously compared: the Early Fusion strategy and the Late Fusion strategy. Experiments on the SEN12MS dataset—a benchmark containing globally diverse land cover categories—demonstrate the framework’s efficacy. Our Early Fusion strategy achieved 88% accuracy (F1 score: 87%), outperforming the Late Fusion approach (84% accuracy, F1 score: 82%). The results indicate that optical data provide detailed spectral signatures useful for identifying vegetation, water bodies, and urban areas, whereas SAR data contribute valuable texture and structural details. Early Fusion’s superiority stems from synergistic low-level feature extraction, capturing cross-modal correlations lost in late-stage fusion. Compared to state-of-the-art baselines, our proposed methods show a significant improvement in classification accuracy, demonstrating that multimodal fusion mitigates single-sensor limitations (e.g., optical cloud obstruction and SAR speckle noise). This study advances remote sensing technology by providing a precise and effective method for LULC classification.

Abstract. Disaster events occur around the world and cause significant damage to human life and property. Earth observation (EO) data enables rapid and comprehensive building damage assessment, an essential capability crucial in the aftermath of a disaster to reduce human casualties and inform disaster relief efforts. Recent research focuses on developing artificial intelligence (AI) models to accurately map unseen disaster events, mostly using optical EO data. These solutions based on optical data are limited to clear skies and daylight hours, preventing a prompt response to disasters. Integrating multimodal EO data, particularly combining optical and synthetic aperture radar (SAR) imagery, makes it possible to provide all-weather, day-and-night disaster responses. Despite this potential, the lack of suitable benchmark datasets has constrained the development of robust multimodal AI models. In this paper, we present a Building damage assessment dataset using veRy-hIGH-resoluTion optical and SAR imagery (Bright) to support AI-based all-weather disaster response. To the best of our knowledge, Bright is the first open-access, globally distributed, event-diverse multimodal dataset specifically curated to support AI-based disaster response. It covers five types of natural disasters and two types of human-made disasters across 14 regions worldwide, focusing on developing countries where external assistance is most needed. The dataset's optical and SAR images with spatial resolutions between 0.3 and 1 m provide detailed representations of individual buildings, making it ideal for precise damage assessment. We train seven advanced AI models on Bright to validate transferability and robustness. Beyond that, it also serves as a challenging benchmark for a variety of tasks in real-world disaster scenarios, including unsupervised domain adaptation, semi-supervised learning, unsupervised multimodal change detection, and unsupervised multimodal image matching. The experimental results serve as baselines to inspire future research and model development. The dataset (https://doi.org/10.5281/zenodo.14619797, Chen et al., 2025a), along with the code and pretrained models, is available at https://github.com/ChenHongruixuan/BRIGHT (last access: 7 November 2025) and will be updated as and when a new disaster data is available. Bright also serves as the official dataset for the 2025 IEEE GRSS Data Fusion Contest Track II. We hope that this effort will promote the development of AI-driven methods in support of people in disaster-affected areas.

&amp;amp;lt;p&amp;amp;gt;Previous studies of synthetic aperture radar (SAR) imagery have shown qualitative relationships between radar backscatter and soil moisture. However, to be able to use these data in operational programs it will be necessary to establish quantitatively how the radar return is related to soil moisture and the effects of surface roughness, soil type, and vegetation cover and growth stage, as a function of frequency and polarization. To this end, a multi-year experiment began in 1990 as a cooperative venture amongst the Canada Centre for Remote Sensing, the Ontario Centre for Remote Sensing, the Land Resource Research Centre (Agriculture Canada), and the Universities of Guelph, Sherbrooke, Laval, and Waterloo.&amp;amp;lt;/p&amp;amp;gt;&amp;amp;lt;p&amp;amp;gt;During 1990, SAR imagery was acquired during two periods (May and July) to correspond to times of minimal and substantial vegetation cover. SAR data were acquired on three days in May and on four days in July to cover different soil moisture conditions. This unique comprehensive data set will be used to investigate the relationships between soil moisture and radar backscatter. This paper describes the experiment and data collected as well as providing a preliminary qualitative interpretation of the relationship between soil moisture and image tone.&amp;amp;lt;/p&amp;amp;gt;