Permanent Scatterer SAR Interferometry (PSInSAR) aims to identify coherent radar targets exhibiting high phase stability over the entire observation time period. These targets often correspond to ...point-wise, man-made objects widely available over a city, but less present in non-urban areas. To overcome the limits of PSInSAR, analysis of interferometric data-stacks should aim at extracting geophysical parameters not only from point-wise deterministic objects (i.e., PS), but also from distributed scatterers (DS). Rather than developing hybrid processing chains where two or more algorithms are applied to the same data-stack, and results are then combined, in this paper we introduce a new approach, SqueeSAR, to jointly process PS and DS, taking into account their different statistical behavior. As it will be shown, PS and DS can be jointly processed without the need for significant changes to the traditional PSInSAR processing chain and without the need to unwrap hundreds of interferograms, provided that the coherence matrix associated with each DS is properly "squeezed" to provide a vector of optimum (wrapped) phase values. Results on real SAR data, acquired over an Alpine area, challenging for any InSAR analysis, confirm the effectiveness of this new approach.
Monitoring ground displacements identifies potential geohazard risks early before they cause critical damage. Interferometric synthetic aperture radar (InSAR) is one of the techniques that can ...monitor these displacements with sub-millimeter accuracy. However, using the InSAR technique is challenging due to the need for high expertise, large data volumes, and other complexities. Accordingly, the development of an automated system to indicate ground displacements directly from the wrapped interferograms and coherence maps could be highly advantageous. Here, we compare different machine learning algorithms to evaluate the feasibility of achieving this objective. The inputs for the implemented machine learning models were pixels selected from the filtered-wrapped interferograms of Sentinel-1, using a coherence threshold. The outputs were the same pixels labeled as fast positive, positive, fast negative, negative, and undefined movements. These labels were assigned based on the velocity values of the measurement points located within the pixels. We used the Parallel Small Baseline Subset service of the European Space Agency's GeoHazards Exploitation Platform to create the necessary interferograms, coherence, and deformation velocity maps. Subsequently, we applied a high-pass filter to the wrapped interferograms to separate the displacement signal from the atmospheric errors. We successfully identified the patterns associated with slow and fast movements by discerning the unique distributions within the matrices representing each movement class. The experiments included three case studies (from Italy, Portugal, and the United States), noted for their high sensitivity to landslides. We found that the Cosine K-nearest neighbor model achieved the best test accuracy. It is important to note that the test sets were not merely hidden parts of the training set within the same region but also included adjacent areas. We further improved the performance with pseudo-labeling, an approach aimed at evaluating the generalizability and robustness of the trained model beyond its immediate training environment. The lowest test accuracy achieved by the implemented algorithm was 80.1%. Furthermore, we used ArcGIS Pro 3.3 to compare the ground truth with the predictions to visualize the results better. The comparison aimed to explore indications of displacements affecting the main roads in the studied area.
We present the continuous monitoring of ground deformation at regional scale using ESA (European Space Agency) Sentinel-1constellation of satellites. We discuss this operational monitoring service ...through the case study of the Tuscany Region (Central Italy), selected due to its peculiar geological setting prone to ground instability phenomena. We set up a systematic processing chain of Sentinel-1 acquisitions to create continuously updated ground deformation data to mark the transition from static satellite analysis, based on the analysis of archive images, to dynamic monitoring of ground displacement. Displacement time series, systematically updated with the most recent available Sentinel-1 acquisition, are analysed to identify anomalous points (i.e., points where a change in the dynamic of motion is occurring). The presence of a cluster of persistent anomalies affecting elements at risk determines a significant level of risk, with the necessity of further analysis. Here, we show that the Sentinel-1 constellation can be used for continuous and systematic tracking of ground deformation phenomena at the regional scale. Our results demonstrate how satellite data, acquired with short revisiting times and promptly processed, can contribute to the detection of changes in ground deformation patterns and can act as a key information layer for risk mitigation.
Interferometric Synthetic Aperture Radar (InSAR) data processing applications, such as deformation monitoring and topographic mapping, require an interferometric phase filtering step. Indeed, the ...filtering quality significantly impacts the deformation and terrain height estimation accuracy. However, the existing classical and deep learning-based phase filtering methods provide artefacts in the filtered areas where a large amount of noise prevents retrieving the original signal. In this way, we can no longer distinguish the underlying informative signal for the next processing step. This paper proposes a deep convolutional neural network filtering method, developing a novel learning strategy to preserve the initial phase noise input into these crucial areas. Thanks to the encoder–decoder powerful phase feature extraction ability, the network can predict an accurate coherence and filtered interferometric phase, ensuring reliable final results. Furthermore, we also address a novel Synthetic Aperture Radar (SAR) interferograms simulation strategy that, using initial parameters estimated from real SAR images, considers physical behaviors typical of a real acquisition. According to the results achieved on simulated and real InSAR data, the proposed filtering method significantly outperforms the classical and deep learning-based ones.
Deep Learning for SAR Image Despeckling Lattari, Francesco; Gonzalez Leon, Borja; Asaro, Francesco ...
Remote sensing,
07/2019, Letnik:
11, Številka:
13
Journal Article
Recenzirano
Odprti dostop
Speckle filtering is an unavoidable step when dealing with applications that involve amplitude or intensity images acquired by coherent systems, such as Synthetic Aperture Radar (SAR). Speckle is a ...target-dependent phenomenon; thus, its estimation and reduction require the individuation of specific properties of the image features. Speckle filtering is one of the most prominent topics in the SAR image processing research community, who has first tackled this issue using handcrafted feature-based filters. Even if classical algorithms have slowly and progressively achieved better and better performance, the more recent Convolutional-Neural-Networks (CNNs) have proven to be a promising alternative, in the light of the outstanding capabilities in efficiently learning task-specific filters. Currently, only simplistic CNN architectures have been exploited for the speckle filtering task. While these architectures outperform classical algorithms, they still show some weakness in the texture preservation. In this work, a deep encoder–decoder CNN architecture, focused in the specific context of SAR images, is proposed in order to enhance speckle filtering capabilities alongside texture preservation. This objective has been addressed through the adaptation of the U-Net CNN, which has been modified and optimized accordingly. This architecture allows for the extraction of features at different scales, and it is capable of producing detailed reconstructions through its system of skip connections. In this work, a two-phase learning strategy is adopted, by first pre-training the model on a synthetic dataset and by adapting the learned network to the real SAR image domain through a fast fine-tuning procedure. During the fine-tuning phase, a modified version of the total variation (TV) regularization was introduced to improve the network performance when dealing with real SAR data. Finally, experiments were carried out on simulated and real data to compare the performance of the proposed method with respect to the state-of-the-art methodologies.
Detecting and monitoring changes in open-pit mines is crucial for efficient mining operations. Indeed, these changes comprise a broad spectrum of activities that can often lead to significant ...environmental impacts such as surface damage, air pollution, soil erosion, and ecosystem degradation. Conventional optical sensors face limitations due to cloud cover, hindering accurate observation of the mining area. To overcome this challenge, synthetic aperture radar (SAR) images have emerged as a powerful solution, due to their unique ability to penetrate clouds and provide a clear view of the ground. The open-pit mine change detection task presents significant challenges, justifying the need for a model trained for this specific task. First, different mining areas frequently include various features, resulting in a diverse range of land cover types within a single scene. This heterogeneity complicates the detection and distinction of changes within open-pit mines. Second, pseudo changes, e.g., equipment movements or humidity fluctuations, which show statistically reliable reflectivity changes, lead to false positives, as they do not directly correspond to the actual changes of interest, i.e., blasting, collapsing, or waste pile operations. In this paper, to the best of our knowledge, we present the first deep learning model in the literature that can accurately detect changes within open-pit mines using SAR images (TerraSAR-X). We showcase the fundamental role of data augmentations and a coherence layer as a critical component in enhancing the model’s performance, which initially relied solely on amplitude information. In addition, we demonstrate how, in the presence of a few labels, a pseudo-labeling pipeline can improve the model robustness, without degrading the performance by introducing misclassification points related to pseudo changes. The F1-Score results show that our deep learning approach is a reliable and effective method for SAR change detection in the open-pit mining sector.
We resolve deformation at The Geysers Geothermal Field using two distinct sets of interferometric synthetic aperture radar (InSAR) data. The first set of observations utilize archived European Space ...Agency C‐band synthetic aperture radar data from 1992 through 1999 to image the long‐term and large‐scale subsidence at The Geysers. The peak range velocity of approximately 50 mm/year agrees with previous estimates from leveling and global positioning system observations. Data from a second set of measurements, acquired by TerraSAR‐X satellites, extend from May 2011 until April 2012 and overlap the C‐band data spatially but not temporally. These X‐band data, analyzed using a combined permanent and distributed scatterer algorithm, provide a higher density of scatterers (1122 per square kilometer) than do the C‐band data (12 per square kilometer). The TerraSAR‐X observations resolve 1 to 2 cm of deformation due to water injection into a Northwest Geysers enhanced geothermal system well, initiated on October 2011. The temporal variation of the deformation is compatible with estimates from coupled numerical modeling.
Key Points
X-band data provides improved coverage of deformation at The Geysers
The C-band deformation rate agrees with past estimates
The estimates are supported by modeling
The Mediterranean region is frequently struck by severe rainfall events causing numerous casualties and several million euros of damages every year. Thus, improving the forecast accuracy is a ...fundamental goal to limit social and economic damages. Numerical Weather Prediction (NWP) models are currently able to produce forecasts at the km scale grid spacing but unreliable surface information and a poor knowledge of the initial state of the atmosphere may produce inaccurate simulations of weather phenomena. The STEAM (SaTellite Earth observation for Atmospheric Modelling) project aims to investigate whether Sentinel satellites constellation weather observation data, in combination with Global Navigation Satellite System (GNSS) observations, can be used to better understand and predict with a higher spatio-temporal resolution the atmospheric phenomena resulting in severe weather events. Two heavy rainfall events that occurred in Italy in the autumn of 2017 are studied—a localized and short-lived event and a long-lived one. By assimilating a wide range of Sentinel and GNSS observations in a state-of-the-art NWP model, it is found that the forecasts benefit the most when the model is provided with information on the wind field and/or the water vapor content.
Interferometric SAR (InSAR) algorithms exploit synthetic aperture radar (SAR) images to estimate ground displacements, which are updated at each new satellite acquisition, over wide areas. The ...analysis of the resulting time series finds its application, among others, in monitoring tasks regarding seismic faults, subsidence, landslides, and urban structures, for which an accurate and timely response is required. Typical analyses consist of identifying among the numerous time series the ones that exhibit an anomalous displacement, thus deserving to be further investigated. In practice, this is realized by selecting the time series that is characterized by trend changes w.r.t. the historical behavior. In this work, we propose a deep learning approach for change point detection in the InSAR time series. The designed architecture combines long short-term memory (LSTM) cells, to model the temporal correlation among samples in the input time series, and time-gated LSTM (TGLSTM) cells, to consider the sampling rate as additional information during learning. We further propose a solution to the lack of ground truth by developing a suitable pipeline for realistic data simulation. The method has been developed and validated through a large suite of experiments. Both quantitative and qualitative analyses have been conducted to demonstrate the detection capabilities of the learned model and how it is a valid alternative to the statistical reference algorithm. We further applied the developed method in a real continuous monitoring project to analyze the InSAR time series over the Tuscany region in Italy, proving its effectiveness in the real domain.
On 13 January 2012, the Italian vessel, Costa Concordia, wrecked offshore Giglio Island, along the coast of Tuscany (Italy). The ship partially sunk, lying on the starboard side on a 22 degree steep ...rocky seabed, making the stability conditions of the ship critically in danger of sliding, shifting and settling. The tilted position of the ship created also pernicious conditions for the divers involved in the search and rescue operations. It became immediately clear that a continuous monitoring of the position and movements of the ship was of paramount importance to guarantee the security of the people working around and within the wreck. Starting from January 19, the Italian constellation of synthetic aperture radar (SAR) satellites, COSMO-SkyMed (CSK), was tasked to acquire high resolution images of the wreck. Thanks to CSK's short response and revisiting time and its capability to acquire high resolution images in Spotlight mode, satellite data were integrated within the real time, ground-based monitoring system implemented to provide the civil protection authorities with a regular update on the ship stability. Exploitation of both the phase (satellite radar interferometry, InSAR) and amplitude (speckle tracking) information from CSK images, taken along the acquisition orbit, Enhanced Spotlight (ES)-29, revealed a general movement of the translation of the vessel, consistent with sliding toward the east of the hull on the seabed. A total displacement, with respect to the coastline, of 1666 mm and 345 mm of the bow and stern, respectively, was recorded, over the time period of 19 January-23 March 2012.