Building collapse arising from destructive earthquakes is often the primary cause of casualties and economic loss. Building damage assessment is one of the top priorities in earthquake emergency work. Quad-polarimetric synthetic aperture radar (PolSAR) data not only has the advantages of radar imaging being neither exposed to sunlight nor blocked by clouds, but also contains the most abundant information of the four polarimetric channels. In many cases, the texture feature even outperforms other kinds of features. The texture features of buildings include not only spatial texture but also frequency texture. We proposed a parameter called the sector texture feature of the Fourier amplitude spectrum (STFFAS) to describe frequency-domain texture features based on the Fourier amplitude spectrum for building damage recognition. Our experimental results show that the recognition performance of the frequency texture feature performs satisfactorily for building damage information extraction.
Hyperspectral unmixing is a crucial step in hyperspectral image processing. Hyperspectral images in real scenes are saturated with spectral variability, and unmixing performance is limited. We propose the Spectral Variability Attention Net (SVA-Net). We have separately designed a Complementary Feature Enhancement Module (CFE) and a Spectral Variability Attention Mechanism to capture both the original material features in the image and other easily overlooked features. In addition, we design the improved mixing model based on augmented linear mixing model (ALMM) to better cope with the effects of spectral variability. Experiments on real datasets demonstrate the effectiveness of our model.
We propose a novel deep learning-based method that adapts the domains of images acquired by different remote sensing sensors. It adapts a lower resolution image to the domain of an an higher resolution targeted sensor. This is effective in the case of change detection, where differences between sensors, such as spatial resolution and radiometry, can hinder the detection performance and where model hallucination artifacts are unwanted. The proposed technique divides the input image into patches and uses a diffusion-based model to generate translated patches in the style of the target sensor. The translated patches are stitched together to form the output image, which provides global generative consistency. Our approach can handle images with different resolutions and tonalities. We show its effectiveness on a Sentinel-II + Planet Dove data set and demonstrate its high generation quality and contribution to enhance change detection performance.
This paper deals with the target detection problem in nonzero-mean compound Gaussian (CG) sea clutter with the generalized inverse Gaussian (GIG) texture. With the improvement of radar resolution, the CG distribution is adopted to model the sea clutter. Then, considering the characteristics of real sea clutter, the CG model with the GIG texture is applied. Furthermore, sea clutter signals are assumed to be nonzero-mean. A novel adaptive two-step maximum a posteriori (MAP) generalized likelihood ratio test (GLRT) detection algorithm is proposed. Firstly, the test statistic of the proposed detector with known GIG texture, mean vector (MV), and covariance matrix (CM) is derived. Secondly, replacing with the estimates of GIG texture, MV, and CM, the adaptive detector can be acquired. The numerical results indicate the performance of the proposed detector.
Rainfall is the primary landslide triggering factor in China, and the spatial-temporal hazard prediction of rainfall-induced landslides is of great practical significance. Currently, most countries and regions establish landslide hazard prediction systems based on rainfall data only, resulting in low spatial precision of hazard prediction results and a high false alarm rate. This paper proposes a hazard prediction model that considers landslide triggering factors, landslide predisposing environment, and the spatial regularity of historical landslides based on multi-modal earth observation data. The proposed model has significantly improved the spatial-temporal hazard prediction performance of rainfall-induced natural terrain landslides in Hong Kong.
Orbital and autonomous radar sounding platforms promise to enable widespread mapping of subglacial topography and englacial layers with greater uniformity of data and observing conditions than the current patchwork of distinct radar systems and surveys. They also have the potential to collect time-series observations of evolving subsurface conditions including ice-shelf melting, ocean access across grounding zones, 3D ice flow, and dynamic ice-sheet hydrology. Here, we investigate the impact of platform altitude and velocity on the detectability of subsurface interfaces beneath ice, sand, and permafrost in the presence of both noise and range sidelobes from surface echoes. Specifically, we evaluate the potential performance of radar sounding from orbital satellites, stratospheric UAVs, and low-altitude UAVs, relative to one another and to existing piloted platforms.
Computer vision algorithms are increasingly leveraged to accelerate geospatial analysis for disaster response and recovery. As the diversity of remote sensing imagery grows with optical, SAR, and other modalities, a perquisite for analytics is cross-modal image registration. There is a high potential to harness computer vision for this pre-processing requirement toward enabling downstream analytics such as heterogeneous change detection, automated feature extraction, and data fusion. Advancement in these areas has the potential to simplify data wrangling tasks and further accelerate disaster response timelines. The SpaceNet 9 challenge (launching in mid-2024) focuses on addressing the cross-modal image registration problem and demonstrating the utility of such modules on earthquake impacted scenarios. This paper describes the motivation for the SpaceNet 9 and provides a first overview of the dataset, the baseline algorithm, and implications for seeking cross-modal image registration in Earth observation. Code is available at https://github.com/SpaceNetChallenge/SpaceNet9.
The study introduces a novel data fusion method that leverages diverse data sources for flood extent identification during emergencies, focusing on Hurricane Harvey. By analyzing various data sources, including satellite remote sensing, aerial photography, and ground observations from social media and municipal systems, spatial and temporal maps of inundation are generated for Harris County, TX, particularly Houston. These integrated data produce a multi-scale observation product (MOP) of cumulative inundation over time and space. The MOP is compared with three independent products: the Flood2D-GPU hydrologic model and two FEMA products for maximum inundation extent and building damage assessment.
Above-ground biomass density (AGBD) quantification is crucial for understanding carbon dynamics, climate change, and sustainable forest management. This study integrates Global Ecosystem Dynamics Investigation (GEDI) satellite data with multi-spectral, Synthetic Aperture Radar (SAR) based earth observations and soil data for continuous estimation of forest AGBD. Study was focused on the Indian forest. GEDI’s AGBD data from 10,000 points serves as the dependent variable and independent variables are derived from Sentinel-1, Sentinel-2, Digital Elevation Model (DEM), SoilGrids, and Climate Hazards Group InfraRed Precipitation with Station data (CHIRPS). We evaluated Support Vector Regression, Random Forest Regression, and Light Gradient Boosting Machine algorithms for various feature-set scenarios. Hyperparameter tuning employed grid-search-based cross-validation. Results shows that, LightGBM performed well, being computationally efficient and delivering lower RMSE. For the selected LightGBM model, with Sentinel-1, Sentinel-2, DEM, and forest attributes, an RMSE of 68.02 Mg/ha and R 2 of 0.57 were achieved. Model-generated AGB maps were compared with openly available National Remote Sensing Centre AGBD data at 100m and existing forest AGBD work. Comparison between model predicted AGBD and literature based maps and studies shows that, our model was able to capture the AGBD variations across multiple forest sub-regions from India.
This study applied a decision theory approach to quantify the potential economic Value of Information (VoI) of Earth Observations (EO) based monitoring and forecasting services developed in PrimeWater project, for managing harmful algal bloom events at a recreational lake. VoI was estimated by comparing the expected costs when decisions are taken with limited information relying on regular monitoring campaigns, against the outcomes of decisions taken with "better information" conveyed by the PrimeWater services. Expected costs considered health impacts, monitoring costs, and lost recreational revenues in case of false alarms. Four PrimeWater monitoring and forecasting services were evaluated based on their accuracy in assessing bloom conditions against in-situ data for 2015-2019. Results suggest VoI varies seasonally and between services depending on accuracy metrics and underlying bloom probabilities. Forecasting solutions provide the greatest potential savings, highlighting needs for balanced metrics to avoid excess false alarms. Findings support flexible use of EO information to complement existing programs and inform science-based management aimed at reducing societal vulnerability to HABs.
The Extended Timing Annotation Dataset (ETAD) product consists of a set of correction layers to improve the range and azimuth timing of Sentinel-1 (S1) Synthetic Aperture Radar (SAR) images. Moreover, the ETAD layers also allow the mitigation of the Atmospheric Phase Screen (APS) component which may affect the Interferometric SAR products. In this paper, we present a detailed experimental analysis to investigate the effectiveness of the S1 ETAD correction layers in removing the APS component from Differential Synthetic Aperture Radar (DInSAR) products (interferograms and deformation time series).In particular, the performance analysis of the ETAD APS correction has been carried out by exploiting the Parallel Small Baseline Subset (P-SBAS) approach to process a large dataset of 104 S1 images acquired along ascending orbits during the 2018-2020 time span over Central/Southern Italy. Several statistical metrics have been then applied both to the 278 generated interferograms and to the P-SBAS deformation time series, produced at medium spatial resolution (about 40 m), to quantitatively investigate the validity of the ETAD APS correction.
A multi-criteria spatial analysis within the context of the Horizon 2020 RethinkAction project is presented. RethinkAction is aligned with the EU Green Deal and the Paris Agreement that focuses on the important role of land use planning in achieving long-term climate mitigation and adaptation goals. To that end, the project employs a cross-sectoral planning decision-making platform to empower citizens and decision-makers in fostering climate action across Europe. Focused on the establishment and maintenance of green urban ecosystems and limiting urban sprawl, methods proposed in this paper employs techniques to develop suitability maps for urban land-based adaptation and mitigation solutions, such as establishment and maintenance of green urban ecosystems (GUE) and limiting the urban sprawl (LUS). The methodology, suitability factors applied, and results for each Land-based Adaptation Measure (LAMS), shedding light on the intricate relationship between urban planning and climate action are described.
Peatlands are important carbon sinks however many peatlands have been degraded. This lowers the water level releasing greenhouse gases into the atmosphere. Synthetic aperture radar (SAR) satellite data can be used to monitor the water level in peatlands and therefore identifies areas that are in need of restoration. Using quad-pol L-band data from ALOS-2 shows potential to identify negative change in the water level. Observing eigenvalues and eigenvectors of the change matrix of a bog in Scotland identifies a lower water table (drier peatland) that corresponds with less surface scattering. In addition, observing the coherence regions of different points around peatlands shows variations in the scattering. Improvements to these results would be made by obtaining acquisitions on dates which had a higher water table.
The High Mountain Asia (HMA) continues to witness an increased frequency of glacial lake outburst floods (GLOFs), which is likely in response to continued global warming. In situ measurements to understand the triggers all across the region will remain inadequate given the vastness and lack of accessibility of the region. This work explores a data-driven logistic regression-based framework to evaluate potential GLOF triggers, such as the lake dam type, its surface area, aspect, distance, freeboard, slope, precipitation, and temperature. A comprehensive inventory of past GLOF events in the region has been compiled, with 25 events verified using pre-& post-event multispectral images acquired between 2016 and 2022. The logistic regression model is developed using samples of the positive class (lakes with confirmed GLOFs) and of the negative class (potentially dangerous lakes that have not experienced a GLOF event). The samples of the negative lake class were collected with resembling characteristics from the nearby areas of the positive class. We randomly keep 80% of the samples for training. The models performance is assessed using adjusted R 2 and the Akaike Information Criterion (AIC) on the test samples, which are 79% and 21.5, respectively. The classification accuracy is 90%, which is promising. In short, the proposed method is a useful tool to investigate risk of outburst flooding of glacial lakes.
Efficient and timely assessment of road network dynamic changes is crucial for the comprehensive evaluation of urban development, transportation accessibility, and environmental impacts. While existing methods mainly focus on optimizing performance with very-high-resolution remote sensing images on public road datasets, their practical applicability remains to unlock when confronted with large-scale real-world applications utilizing multi-spectral remote sensing images. The limitations manifest in unsatisfactory model generalization and fragmented segmentation, reducing the effectiveness of road extraction outcomes. To address these challenges, this study introduces a novel connectivity-aware approach tailored to address road extraction challenges in real-world scenarios. Leveraging Sentinel-2 multi-spectral imagery, this study conducts a 6-year road change mapping over an expansive 10,097 square kilometers in Xi’an, China. Experimental and evaluation results underscore the efficacy of the proposed methodology for widespread applications in urban planning and environmental management, offering a robust solution for practical and efficient road extraction in diverse and extensive large-scale urban investigation.
With regard to the Sustainable Development Goals (SDGs), which address a range of social, economic and environmental challenges faced by the world today, the present work is targeting a specific indicator of relevance for security. A methodology to support the calculation of the SDG indicator 13.1.1 (Number of deaths, missing persons and directly affected persons attributed to disasters per 100,000 population) is presented; while the indicator is currently based on data from national demographic agencies, the proposed method incorporates the use of Earth Observation (EO) data. The workflow has been tested in the Sahel region (Niger), one of the hot-spots for Climate Security concerns.
This paper investigates the adaptive target detection problem in FDA-MIMO radar embedded in Gaussian noise with an unknown covariance matrix, considering the scenario of mismatched steering vectors. Firstly, we assume that the covariance matrix of the test data and training data has the same structure with different magnitude levels. Next, the subspace model is adopted to enhance the robustness of the detector against mismatched signals. Furthermore, TS-GLRT detector is designed based on the generalized likelihood ratio test (GLRT), then we validated its constant false alarm rate (CFAR) property. Finally, simulation results demonstrate the effectiveness of the proposed approach.
With the continuous development of deep learning, a large number of deep learning models are gradually emerging in the field of SAR target recognition. However, SAR targets usually have complex textures and noises, and it is difficult to directly extract effective feature information and rich contextual information between the target object and the background, which inhibits the potential of deep learning models to further improve the recognition ability in the SAR domain. To ameliorate this problem, a GIC-Mechanism that improves the ability to capture global and local feature information interactively is proposed in this paper and applied to the Resnet family of models. In the recognition task of two SAR target datasets, the mechanism designed in this paper with the ability of multi-scale losing feature information interaction and cross-feature mapping layer information interaction improves the recognition performance of the Resnet series model by 2.16%-2.81%, which is effective.
In this study, the potential of the newly developed Hybrid Retrieval Workflow, integrated into the EnMAP-Box, is demonstrated by quantifying NPV using hyperspectral data. Due to its diverse functions in agricultural and natural ecosystems, NPV mapping is becoming increasingly important. The emergence of new-generation spaceborne spectrometers like PRISMA and EnMAP, providing largescale and potentially multi-temporal hyperspectral data, opens up new possibilities for NPV mapping on a global scale. The EnHyR facilitates NPV mapping using hybrid machine learning approaches that use simulated spectral training data optimized via Active Learning supported by in-situ data. Preliminary results for Slovakia and Southern Germany highlight the potential of the EnHyR using PRISMA and EnMAP data for global NPV mapping.
Pole-like objects represent important street infrastructures for road inventory and road mapping. Existing supervised point cloud classification methods cannot correctly classify underrepresented pole-like objects in airborne laser scanning (ALS) or photogrammetric datasets due to the limited number of the annotated points. In this article, we proposed an unsupervised method to overcome the challenge of automatically extracting pole-like objects using point clouds. Firstly, the non-ground scattered points are segmented into meaningful segments. Then, DBSCAN clusters are generated form the layered points as the nodes for hierarchical directed graph construction. Finally, a graph-based connectivity analysis in combination with depth-first search is proposed to count the number of directed edges and extract pole-like road furniture candidates. The proposed method has been tested on the Hessigheim 3D dataset at segment- and point-scale. The precision of segment and point scale reached 81.08% and 96.84%, respectively. The experimental results demonstrated that our method can automatically extract pole-like objects robustly and efficiently.
