Monitoring the Recovery Process After Major Hydrological Disasters with GIS, Change Detection and Open and Free Multi-Sensor Satellite Imagery: Demonstration in Haiti After Hurricane Matthew

<p>Satellite earth observation data has been frequently applied to monitor shoreline change at very large geographic scales. Techniques focus on the extraction of the instantaneous waterline boundary, a shoreline proxy that can be extracted from publicly available multispectral satellite data with sub-pixel accuracy. Interpreting coastal change through this proxy can be uncertain as the position of the waterline is dynamic, a function of beach gradient and constantly fluctuating marine processes, and might not capture information of the full spectrum of drivers influencing change for a given section of coast.</p><p>Satellite data is acquired in raster format and there is useful information stored in each pixel across the entire coastal zone. Applying per-pixel change detection techniques could offer further insights to the role of drivers of coastal change beyond a vectorised land-water boundary. This paper describes a new method for monitoring coastal change at large geographic scales with public satellite remote sensing data through pixel-based change detection. The first step is the classification of pixels into specific coastal landcover classes. This is challenging at large scales owing to complex and diverse physical environmental characteristics. A methodology was developed and applied to New Zealand’s coastline, identifying 9 landcover types including sedimentary coast. A combination of Sentinel multispectral and synthetic-aperture-radar data were used to derive composite imagery for 2019 using Google Earth Engine cloud computing platform. This was classified using a set of hierarchal rules and machine learning in a Python programming environment. This was validated nationally against high-resolution aerial photography and commercial satellite imagery. This produced a coastal specific landcover classification from which per-pixel change detection techniques can be applied. Overall accuracy was 86.38% and exceeded 90% when normalised by class area.</p><p>The outputs and code are available, and the framework has been designed to work with a range of earth observation datasets and can be applied to other regions around the world. Ongoing work includes implementing a framework to assess long-term change, at the coast in New Zealand. By investigating how specific coastal landcover types are changing, useful information can be acquired to better interpret drivers of coastal change and the impacts on coastal geomorphology at large geographic scales.</p><p> </p><p><em>Keywords: Satellite Remote Sensing, Multispectral, Synthetic Aperture Radar, Landcover classification, Change detection, Coastal change.</em></p>

Accurate land cover classification (LCC) is essential for studying global change. Synthetic aperture radar (SAR) has been used for LCC due to its advantage of weather independence. In particular, the dual-polarization (dual-pol) SAR data have a wider coverage and are easier to obtain, which provides an unprecedented opportunity for LCC. However, the dual-pol SAR data have a weak discrimination ability due to limited polarization information. Moreover, the complex imaging mechanism leads to the speckle noise of SAR images, which also decreases the accuracy of SAR LCC. To address the above issues, an improved dual-pol radar vegetation index based on multiple components (DpRVIm) and a new LCC method are proposed for dual-pol SAR data. Firstly, in the DpRVIm, the scattering information of polarization and terrain factors were considered to improve the separability of ground objects for dual-pol data. Then, the Jeffries-Matusita (J-M) distance and one-dimensional convolutional neural network (1DCNN) algorithm were used to analyze the effect of difference dual-pol radar vegetation indexes on LCC. Finally, in order to reduce the influence of the speckle noise, a two-stage LCC method, the 1DCNN-MRF, based on the 1DCNN and Markov random field (MRF) was designed considering the spatial information of ground objects. In this study, the HH-HV model data of the Gaofen-3 satellite in the Dongting Lake area were used, and the results showed that: (1) Through the combination of the backscatter coefficient and dual-pol radar vegetation indexes based on the polarization decomposition technique, the accuracy of LCC can be improved compared with the single backscatter coefficient. (2) The DpRVIm was more conducive to improving the accuracy of LCC than the classic dual-pol radar vegetation index (DpRVI) and radar vegetation index (RVI), especially for farmland and forest. (3) Compared with the classic machine learning methods K-nearest neighbor (KNN), random forest (RF), and the 1DCNN, the designed 1DCNN-MRF achieved the highest accuracy, with an overall accuracy (OA) score of 81.76% and a Kappa coefficient (Kappa) score of 0.74. This study indicated the application potential of the polarization decomposition technique and DEM in enhancing the separability of different land cover types in SAR LCC. Furthermore, it demonstrated that the combination of deep learning networks and MRF is suitable to suppress the influence of speckle noise.

<p>Rapid mapping of the extent of the affected area as well as type and grade of damage after a landslide event is crucial to enable fast crisis response, i.e., to support rescue and humanitarian operations. Change detection between pre- and post-event very high resolution (VHR) optical imagery is the state-of-the-art in operational rapid mapping of landslides. However, the suitability of optical data relies on clear sky conditions, which is not often the case after landslides events, as heavy rain is one of the most frequent triggers of landslides. In contrast to this, the acquisition of synthetic aperture radar (SAR) imagery is independent of atmospheric conditions. SAR data-based landslide detection approaches reported in the literature use change detection techniques, requiring VHR SAR imagery acquired shortly before the landslide event, which is commonly not available. Modern VHR SAR missions, e.g., Radarsat-2, TerraSAR-X, or COSMO-SkyMed, do not systematically cover the entire world, due to limitations in onboard disk space and downlink transmission rates. Here, we present a fast and transferable procedure for mapping of landslides in vegetated areas, based on change detection between pre-event optical imagery and the polarimetric entropy derived from post-event VHR polarimetric SAR data. Pre-event information is derived from high resolution optical imagery of Landsat-8 or Sentinel-2, which are freely available and systematically acquired over the entire Earth’s landmass. The landslide mapping is refined by slope information from a digital elevation model generated from bi-static TanDEM-X imagery. The methodology was successfully applied to two landslide events of different characteristics: A rotational slide near Charleston, West Virginia, USA and a mining waste earthflow near Bolshaya Talda, Russia.</p>

Change detection from remotely sensed images: From pixel-based to object-based approaches

Image change detection is established for extracting changed regions in multiple images of the same scene captured at different times. Recent research has demonstrated that the change detection methodologies using satellite images, such as multi-temporal visible light remote sensing image and synthetic aperture radar (SAR) image, are particularly useful for damage assessment after various disasters, e.g., earthquakes, fires, floods, and landslides. The level set method, because of its implicit handling of topological changes and low sensitivity to noise, is one of the most effective unsupervised change detection techniques for satellite images. The signed pressure force function (SPF) improved the performances of conventional level set methods through including two grayscale parameters, i.e., the average pixel intensity inside and outside the contour, respectively. However, the mean of region pixel intensity is not a good indicator in case that the images are inhomogeneities grayscale, e.g., confused-edge objects in satellite images. In order to address this problem, we propose a novel model, denoted as dynamic SPF (D-SPF) model, which can dynamically learn a discriminative indicator for distinguishing the pixels inside or outside the contour. Specifically, the principle of maximizing entropy between the regions inside and outside the contour is used to learn the K distinguish parameters, which help to guide the segmentation contour to end on the object’s edge. The experiments are conducted on a public satellite image dataset, i.e., ERS, which contain 670 SAR and 670 optical images; each image covers approximately 150 m2 area including forests, lakes, and cities, etc. These images are challenging due to the inhomogeneities of landforms and unknown natural disasters. The experimental results demonstrate that D-SPF model reduces almost 30.4% missed detection rate on the optical images and 41.2% missed detection rate on the SAR images in comparison with SPF and obtains the best detection performances in ERS dataset.

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.

Agricultural land use and land cover (LULC) classification using synthetic aperture radar (SAR) data is a fundamental application in remote sensing and precision agriculture. Leveraging the abilities of SAR, which can enter over cloud cover and deliver detailed data about surface features, allows a robust analysis of agricultural landscapes. By harnessing the control of SAR data and innovative deep learning (DL) methods, this technique provides a complete solution for effectual and automatic agricultural land classification, paving the method for informed decision-making in present farming systems. This study introduces a new gradient based optimizer with deep learning based agricultural land use and land cover classification (GBODL-ALULC) technique on SAR data. The GBODL-ALULC technique aims to detect and classify distinct types of land cover that exist in the SAR data. In the GBODL-ALULC technique, the feature extraction process takes place by a residual network with a convolutional block attention mechanism (ResNet-CBAM) model. At the same time, the GBO system has been executed for the best hyperparameter choice of the ResNet-CBAM model which helps to improve the overall LULC classification results. Finally, a regularized extreme learning machine (RELM) algorithm has been for the detection and classification of land covers. The performance study of the GBODL-ALULC method is carried out on the SAR dataset. The simulation outcome depicted that the GBODL-ALULC methodology reaches effectual LULC classification outcomes over compared methods.

Change detection implies quantifying temporal effects using multi temporal dataset. The Remote sensing data has become a heart of change detection technique because of its high temporal frequency, digital computation, synoptic view and wider selection of spatial and spectral resolution. The general objectives of change detection in remote sensing include recognizing the geographical location and type of changes, quantifying the changes, and assessing the accuracy of change detection results. In this paper analyses the various change detection techniques using satellite images. Three remote sensing techniques, including Image Differencing, Principal Component Analysis and Change Vector Analysis used to detect the changes. To carry out these techniques, Landsat8 satellite images were used to recognize changes in study area. The efficiency of these method in study area were compared using post classification method and carry out accuracy assessment. The results shows that change vector analysis perform better for change detection to other methods.

Due to spatial and temporal variability an effective monitoring system for water resources must consider the use of remote sensing to provide information. Synthetic Aperture Radar (SAR) is useful due to timely data acquisition and sensitivity to surface water and flooded vegetation. The ability to map flooded vegetation is attributed to the double bounce scattering mechanism, often dominant for this target. Dong Ting Lake in China is an ideal site for evaluating SAR data for this application due to annual flooding caused by mountain snow melt causing extensive changes in flooded vegetation. A curvelet-based approach for change detection in SAR imagery works well as it highlights the change and suppresses the speckle noise. This paper addresses the extension of this change detection technique to polarimetric SAR data for monitoring surface water and flooded vegetation. RADARSAT-2 images of Dong Ting Lake demonstrate this curvelet-based change detection technique applied to wetlands although it is applicable to other land covers and for post disaster impact assessment. These tools are important to Digital Earth for map updating and revision.

Mapping of landslides, quickly providing information about the extent of the affected area and type and grade of damage, is crucial to enable fast crisis response, i.e., to support rescue and humanitarian operations. Most synthetic aperture radar (SAR) data-based landslide detection approaches reported in the literature use change detection techniques, requiring very high resolution (VHR) SAR imagery acquired shortly before the landslide event, which is commonly not available. Modern VHR SAR missions, e.g., Radarsat-2, TerraSAR-X, or COSMO-SkyMed, do not systematically cover the entire world, due to limitations in onboard disk space and downlink transmission rates. Here, we present a fast and transferable procedure for mapping of landslides, based on change detection between pre-event optical imagery and the polarimetric entropy derived from post-event VHR polarimetric SAR data. Pre-event information is derived from high resolution optical imagery of Landsat-8 or Sentinel-2, which are freely available and systematically acquired over the entire Earth’s landmass. The landslide mapping is refined by slope information from a digital elevation model generated from bi-static TanDEM-X imagery. The methodology was successfully applied to two landslide events of different characteristics: A rotational slide near Charleston, West Virginia, USA and a mining waste earthflow near Bolshaya Talda, Russia.

This work aims to clarify the potential of incoherent and coherent change detection (CD) approaches for detecting and monitoring ground surface changes using sequences of synthetic aperture radar (SAR) images. Nowadays, the growing availability of remotely sensed data collected by the twin Sentinel-1A/B sensors of the European (EU) Copernicus constellation allows fast mapping of damage after a disastrous event using radar data. In this research, we address the role of SAR (amplitude) backscattered signal variations for CD analyses when a natural (e.g., a fire, a flash flood, etc.) or a human-induced (disastrous) event occurs. Then, we consider the additional pieces of information that can be recovered by comparing interferometric coherence maps related to couples of SAR images collected between a principal disastrous event date. This work is mainly concerned with investigating the capability of different coherent/incoherent change detection indices (CDIs) and their mutual interactions for the rapid mapping of “changed” areas. In this context, artificial intelligence (AI) algorithms have been demonstrated to be beneficial for handling the different information coming from coherent/incoherent CDIs in a unique corpus. Specifically, we used CDIs that synthetically describe ground surface changes associated with a disaster event (i.e., the pre-, cross-, and post-disaster phases), based on the generation of sigma nought and InSAR coherence maps. Then, we trained a random forest (RF) to produce CD maps and study the impact on the final binary decision (changed/unchanged) of the different layers representing the available synthetic CDIs. The proposed strategy was effective for quickly assessing damage using SAR data and can be applied in several contexts. Experiments were conducted to monitor wildfire’s effects in the 2021 summer season in Italy, considering two case studies in Sardinia and Sicily. Another experiment was also carried out on the coastal city of Houston, Texas, the US, which was affected by a large flood in 2017; thus, demonstrating the validity of the proposed integrated method for fast mapping of flooded zones using SAR data.

<p>Change detection has been widely used in many flood-mapping algorithms using pairs of Synthetic Aperture Radar (SAR) intensity images. The rationale is that when the right conditions are met, the appearance of floodwater results in a significant decrease of backscatter.  However, limitations still exist in areas where the SAR backscatter is not sufficiently impacted by surface changes due to floodwater. For example, in shadow areas, the backscatter is stable over time because the SAR signal does not reach the ground due to prominent topography or obstacles on the ground (e.g., buildings). Densely vegetated forest is another insensitive region due to low capability of SAR C-band wavelengths to penetrate its canopy. Moreover, although in principle SAR can sense water over different land cover classes such as arid regions, streets and buildings, the backscatter changes over time could not be detected because in such areas the scattering variation caused by the presence of water might be negligible with respect to the normal “unflooded” state. The identification of the abovementioned areas where SAR does not allow detecting water based on change detection methods, hereafter called exclusion map, is crucial for providing reliable SAR-based flood maps.</p><p>In this study, insensitive areas are identified using long time-series of Sentinel-1 data and the final exclusion map is classified in four distinctive classes: shadow, layover, urban areas and dense forest. In the proposed method the identification of insensitive areas is based on the use of pixel-based time series backscatter statistics (minimum, maximum, median and standard deviation) coupled with a local spatial autocorrelation analysis (i.e. Moran’s I, Getis-Ord Gi and Geary’s C). In order to evaluate the extracted exclusion map, which is quite unique, we employ a comprehensive ground truth dataset that is obtained by combining different products: 1) a shadow/layover map generated using a 25m-resolution DEM and the geometric acquisition parameters of the SAR data; 2) 20m resolution imperviousness map provided by Copernicus, as well as a high-resolution global urban footprint (GUF) data provided by DLR; 3) a 20m tree cover density (TCD) map provided by Copernicus. In the end, the exclusion map is used to mask out unclassified areas in the flood maps derived by an automatic change detection method, which is expected to enhance flood maps by removing areas where the presence or absence of floodwater cannot be evidenced. In addition, we argue that our insensitive area map provides valuable information for improving the calibration, validation and regular updating of hydraulic models using SAR derived flood extent maps.</p>

Change detection is a process of identifying changes in the state of objects between the reference and test images. This letter presents a target prescreening method that employs the change detection technique for automatic target recognition in synthetic aperture radar (SAR) images. First, four translated versions of an original SAR image are generated, and the corresponding four likelihood ratio images are computed. Then, a robust threshold is derived from the ratio of the histogram at two adjacent gray-level values of the likelihood ratio images. Finally, the threshold is applied to perform the prescreening. The proposed method implements the procedure without any prior knowledge and overcomes the weak adaptability of traditional algorithms. Two different real X-band airborne SAR images acquired over Beijing are used to quantitatively and qualitatively demonstrate the effectiveness of the proposed method.

Satellite images provide an accurate, continuous, and synoptic view of seamless global extent. Within the fields of remote sensing and image processing, land surface change detection (CD) has been amongst the most discussed topics. This article reviews advances in bitemporal and multitemporal two-dimensional CD with a focus on multispectral images. In addition, it reviews some CD techniques used for synthetic aperture radar (SAR). The importance of data selection and preprocessing for CD provides a starting point for the discussion. CD techniques are, then, grouped based on the change analysis products they can generate to assist users in identifying suitable procedures for their applications. The discussion allows users to estimate the resources needed for analysis and interpretation, while selecting the most suitable technique for generating the desired information such as binary changes, direction or magnitude of changes, “from-to” information of changes, probability of changes, temporal pattern, and prediction of changes. The review shows that essential and innovative improvements are being made in analytical processes for multispectral images. Advantages, limitations, challenges, and opportunities are identified for understanding the context of improvements, and this will guide the future development of bitemporal and multitemporal CD methods and techniques for understanding land cover dynamics.

ABSTRACTUrban areas in developing countries are experiencing rapid growth, and monitoring short-term changes has become increasingly important. For short-term monitoring, constant observation and generation of high-accuracy urban distribution maps without noise disturbance are key issues. Synthetic aperture radar (SAR) satellite images are suitable for day and night regardless of atmospheric weather condition observations for monitoring changes. We propose a method to generate high-accuracy urban distribution maps for urban change detection via SAR satellite images based using a convolutional neural network (CNN). To increase accuracy, several improvements relative to SAR polarisation combinations and dataset construction are considered in the proposed method. In addition, digital surface model (DSM) data, which are useful in the classification of land cover, were included to improve accuracy. The results demonstrate that high-accuracy urban distribution maps suitable for short-term monitoring were generated. In an evaluation, urban change data were extracted by taking the difference of urban distribution maps. A change analysis with time-series images revealed the locations of short-term urban change, and comparisons with optical satellite images validated the analysis results.