High Resolution Optical Satellite Research Articles

Extraction of Coastal Levees Using U-Net Model with Visible and Topographic Images Observed by High-Resolution Satellite Sensors.

Coastal levees play a role in protecting coastal areas from storm surges and high waves, and they provide important input information for inundation damage simulations. However, coastal levee data with uniformity and sufficient accuracy for inundation simulations are not always well developed. Against this background, this study proposed a method to extract coastal levees by inputting high spatial resolution optical satellite image products (RGB images, digital surface models (DSMs), and slope images that can be generated from DSM images), which have high data availability at the locations and times required for simulation, into a deep learning model. The model is based on U-Net, and post-processing for noise removal was introduced to further improve its accuracy. We also proposed a method to calculate levee height using a local maximum filter by giving DSM values to the extracted levee pixels. The validation was conducted in the coastal area of Ibaraki Prefecture in Japan as a test area. The levee mask images for training were manually created by combining these data with satellite images and Google Street View, because the levee GIS data created by the Ibaraki Prefectural Government were incomplete in some parts. First, the deep learning models were compared and evaluated, and it was shown that U-Net was more accurate than Pix2Pix and BBS-Net in identifying levees. Next, three cases of input images were evaluated: (Case 1) RGB image only, (Case 2) RGB and DSM images, and (Case 3) RGB, DSM, and slope images. Case 3 was found to be the most accurate, with an average Matthews correlation coefficient of 0.674. The effectiveness of noise removal post-processing was also demonstrated. In addition, an example of the calculation of levee heights was presented and evaluated for validity. In conclusion, this method was shown to be effective in extracting coastal levees. The evaluation of generalizability and use in actual inundation simulations are future tasks.

Applying Earth Observation Technologies to Economic Consequence Modeling: A Case Study of COVID-19 in Los Angeles County, California

Earth observation (EO) technologies, such as very high-resolution optical satellite data available from Maxar, can enhance economic consequence modeling of disasters by capturing the fine-grained and real-time behavioral responses of businesses and the public. We investigated this unique approach to economic consequence modeling to determine whether crowd-sourced interpretations of EO data can be used to illuminate key economic behavioral responses that could be used for computable general equilibrium modeling of supply chain repercussions and resilience effects. We applied our methodology to the COVID-19 pandemic experience in Los Angeles County, California as a case study. We also proposed a dynamic adjustment approach to account for the changing character of EO through longer-term disasters in the economic modeling context. We found that despite limitations, EO data can increase sectoral and temporal resolution, which leads to significant differences from other data sources in terms of direct and total impact results. The findings from this analytical approach have important implications for economic consequence modeling of disasters, as well as providing useful information to policymakers and emergency managers, whose goal is to reduce disaster costs and to improve economic resilience.

Leveraging Deep Learning for High-Resolution Optical Satellite Imagery From Low-Cost Small Satellite Platforms

Leveraging Deep Learning for High-Resolution Optical Satellite Imagery From Low-Cost Small Satellite Platforms

Ice floe segmentation and floe size distribution in airborne and high-resolution optical satellite images: towards an automated labelling deep learning approach

Abstract. Floe size distribution (FSD) has become a parameter of great interest in observations of sea ice because of its importance in affecting climate change, marine ecosystems, and human activities in the polar ocean. A most effective way to monitor FSD in the ice-covered regions is to apply image processing techniques to airborne and satellite remote sensing data, where the segmentation of individual ice floes is a challenge in obtaining FSD from remotely sensed images. In this study, we adopt a deep learning (DL) semantic segmentation network to fast and adaptive implement the task of ice floe instance segmentation. In order to alleviate the costly and time-consuming data annotation problem of model training, classical image processing technique is applied to automatically label ice floes in local-scale marginal ice zone (MIZ). Several state-of-the-art (SoA) semantic segmentation models are then trained on the labelled MIZ dataset and further applied to additional large-scale optical Sentinel-2 images to evaluate their performance in floe instance segmentation and to determine the best model. A post-processing algorithm is also proposed in our work to refine the segmentation. Our approach has been applied to both airborne and high-resolution optical (HRO) satellite images to derive acceptable FSDs at local and global scales.

Effect of Urbanization Through Land Coverage Classification

AbstractLand cover changes from rural or natural habitats to impervious surfaces that support various human activities are called urbanization. The evaluation of policy alternatives for future expansion and the promotion of sustainable urban development therefore place great emphasis on the mapping, analysis, and monitoring of land cover changes in metropolitan environments. By assessing changes in relevant environmental indicators at a range of scales, from local to regional, this study seeks to determine the rate of urbanization and analyze its impact on the environment in and around two key cities in Tamilnadu. Chennai and Madurai are the urban areas under investigation. The results are based on classifications of medium to high spatial resolution optical satellite images from 1995 to 2020. Various classification approaches with combinations of spectral, shape, and texture input information were combined to achieve high classification accuracy. Based on the categories, environmental indicators were created and used to calculate the impact of urbanization on the environment. The findings show that each research area experienced varying degrees of urban expansion and environmental impact. Urban areas grew tenfold between 1995 and 2015, according to a study comparing Chennai and Madurai. To evaluate the spatiotemporal dynamics of urbanization and its environmental impact in various metropolitan regions, this research shows the value of combining urban and environmental indicators with remote sensing data.

GEOMETRIC PROCESSING OF VERY HIGH-RESOLUTION SATELLITE IMAGERY: QUALITY ASSESSMENT FOR 3D MAPPING NEEDS

Abstract. In recent decades, the geospatial domain has benefitted from technological advances in sensors, methodologies, and processing tools to expand capabilities in mapping applications. Airborne techniques (LiDAR and aerial photogrammetry) generally provide most of the data used for this purpose. However, despite the relevant accuracy of these technologies and the high spatial resolution of airborne data, updates are not sufficiently regular due to significant flight costs and logistics. New possibilities to fill this information gap have emerged with the advent of Very High Resolution (VHR) optical satellite images in the early 2000s. In addition to the high temporal resolution of the cost-effective datasets and their sub-meter geometric resolutions, the synoptic coverage is an unprecedented opportunity for mapping remote areas, multi-temporal analyses, updating datasets and disaster management. For all these reasons, VHR satellite imagery is clearly a relevant study for National Mapping and Cadastral Agencies (NMCAs). This work, supported by EuroSDR, summarises a series of experimental analyses carried out over diverse landscapes to explore the potential of VHR imagery for large-scale mapping.

Land cover and crop types mapping using different spatial resolution imagery in a Mediterranean irrigated area.

Crop type identification is critical for agricultural sustainability policy development and environmental assessments. Therefore, it is important to obtain their spatial distribution via different approaches. Medium-, high- and very high-resolution optical satellite sensors are efficient tools for acquiring this information, particularly for challenging studies such as those conducted in heterogeneous agricultural fields. This research examined the ability of four multitemporal datasets (Sentinel-1-SAR (S1), Sentinel-2-MSI (S2), RapidEye (RE), and PlanetScope (PS)) to identify land cover and crop types (LCCT) in a Mediterranean irrigated area. To map LCCT distribution, a supervised pixel-based classification is adopted using Support Vector Machine with a radial basis function kernel (SVMRB) and Random Forest (RF). Thus, LCCT maps were generated into three levels, including six (Level I), ten (Level II), and fourteen (Level III) classes. Overall, the findings revealed high overall accuracies of >92%, >83%, and > 81% for Level I, Level II, and Level III, respectively, except for Sentinel-1. It was found that accuracy improves considerably when the number of classes decreases, especially when cropland or non-cropland classes are grouped into one. Furthermore, there was a similarity in performance between S2 alone and S1S2. PlanetScope LCCT classifications outperform other sensors. In addition, the present study demonstrated that SVM achieved better performances against RF and can thereby effectively extract LCCT information from high-resolution imagery as PlanetScope.

The Use of Deep Learning Methods for Object Height Estimation in High Resolution Satellite Images.

Processing single high-resolution satellite images may provide a lot of important information about the urban landscape or other applications related to the inventory of high-altitude objects. Unfortunately, the direct extraction of specific features from single satellite scenes can be difficult. However, the appropriate use of advanced processing methods based on deep learning algorithms allows us to obtain valuable information from these images. The height of buildings, for example, may be determined based on the extraction of shadows from an image and taking into account other metadata, e.g., the sun elevation angle and satellite azimuth angle. Classic methods of processing satellite imagery based on thresholding or simple segmentation are not sufficient because, in most cases, satellite scenes are not spectrally heterogenous. Therefore, the use of classical shadow detection methods is difficult. The authors of this article explore the possibility of using high-resolution optical satellite data to develop a universal algorithm for a fully automated estimation of object heights within the land cover by calculating the length of the shadow of each founded object. Finally, a set of algorithms allowing for a fully automatic detection of objects and shadows from satellite and aerial imagery and an iterative analysis of the relationships between them to calculate the heights of typical objects (such as buildings) and atypical objects (such as wind turbines) is proposed. The city of Warsaw (Poland) was used as the test area. LiDAR data were adopted as the reference measurement. As a result of final analyses based on measurements from several hundred thousand objects, the global accuracy obtained was ±4.66 m.

Summer sea ice floe perimeter density in the Arctic: high-resolution optical satellite imagery and model evaluation

Abstract. Size distribution of sea ice floes is an important component for sea ice thermodynamic and dynamic processes, particularly in the marginal ice zone. Recently processes related to the floe size distribution (FSD) have been incorporated into sea ice models, but the sparsity of existing observations limits the evaluation of FSD models, thus hindering model improvements. In this study, perimeter density has been applied to characterise the floe size distribution for evaluating three FSD models – the Waves-in-Ice module and Power law Floe Size Distribution (WIPoFSD) model and two branches of a fully prognostic floe size-thickness distribution model: CPOM-FSD and FSDv2-WAVE. These models are evaluated against a new FSD dataset derived from high-resolution satellite imagery in the Arctic. The evaluation shows an overall overestimation of floe perimeter density by the models against the observations. Comparison of the floe perimeter density distribution with the observations shows that the models exhibit a much larger proportion for small floes (radius <10–30 m) but a much smaller proportion for large floes (radius >30–50 m). Observations and the WIPoFSD model both show a negative correlation between sea ice concentration and the floe perimeter density, but the two prognostic models (CPOM-FSD and FSDv2-WAVE) show the opposite pattern. These differences between models and the observations may be attributed to limitations in the observations (e.g. the image resolution is not sufficient to detect small floes) or limitations in the model parameterisations, including the use of a global power-law exponent in the WIPoFSD model as well as too weak a floe welding and enhanced wave fracture in the prognostic models.

Windthrow damage detection in Nordic forests by 3D reconstruction of very high-resolution stereo optical satellite imagery

ABSTRACT We tested whether windthrow damage to Nordic conifer forest stands could be reliably detected as canopy height decrease between a pre-storm LiDAR (Light Detection and Ranging) digital surface model (DSM) and a photogrammetric DSM derived from a post-storm WorldView-3 stereo pair. The post-storm ground reference data consisted of field and unmanned aerial vehicle (UAV) observations of windthrow combined with no-damage areas collected by visual interpretation of the available very high resolution (VHR) satellite imagery. We trained and tested a thresholding model using canopy height change as the sole predictor. We undertook a two-step accuracy assessment by (1) running k-fold cross-validation on the ground reference dataset and examining the effect of the potential imperfections in the ground reference data, and (2) conducting rigorous accuracy assessment of the classified map of the study area using an extended set of VHR imagery. The thresholding model produced accurate windthrow maps in dense, productive forest stands with a sensitivity of 96%, specificity of 71%, and Matthews correlation coefficient (MCC) over 0.7. However, in sparse and high elevation stands, the classification accuracy was poor. Despite certain collection challenges during the winter months in the Nordic region, we consider VHR stereo satellite imagery to be a viable source of forest canopy height information and sufficiently accurate to map windthrow disturbance in forest stands of high to moderate density.

Prediction of Unpaved Road Conditions Using High-Resolution Optical Satellite Imagery and Machine Learning

Rural roads play a crucial role in fostering economic and social development in Africa. Local Road Authorities (LRAs) struggle to collect road condition data using conventional means due to logistical and resource issues. Poor road conditions and restricted mobility have severe economic consequences for the transport of goods and services. Lack of maintenance can increase costs three-fold. In this work, a novel framework is proposed in which earth observations using high-resolution optical satellite imagery are applied to measure the condition of unpaved roads, providing a vital input to maintenance planning and prioritisation. A trial was conducted using this method on 83 roads in Tanzania totalling 131.7 km. The experimental results demonstrate that, by analysing variations in pixel intensity of the road surface, the condition can be estimated with an accuracy of 71.9% when compared to ground truth information. Machine Learning techniques are applied to the same network to test the performance of the system in predicting road conditions. A blended classifier approach achieves an accuracy of 88%. The proposed framework enables LRAs to define the information they receive based on their specific priorities, offering a rapid, objective, consistent and potentially cost-effective system that overcomes the current challenges faced by LRAs.

The effect of pixel heterogeneity on surface heat and water vapor flux estimated by the remote sensing-based model coupled with deep learning

Accurate quantification of sensible (H) and latent (LE) heat fluxes are desperately crucial for agricultural irrigation strategy, drought monitoring, water resource management, and climate change. Regional-scale H and LE were derived generally from satellite remote sensing data using relevant modeling methods. However, one of the challenges of modeling methods is to deal with sub-pixel heterogeneity, because the model usually assumes homogeneous conditions within a pixel. In this study, a hybrid model, which coupled deep neural network (DNN) and the remote sensing-based two-source energy balance (TSEB) model, was developed to estimate H and LE at multiple spatial resolutions to further quantify the influence of pixel size on the modeled fluxes. First, the DNN-based land surface temperature (LST) estimation model was developed and validated. LST at multiple spatial resolutions (i.e., 1, 5, 10, 30, 100, and 1000 m) were generated by the DNN method using multi-source satellite data including the GaoFen-2 (GF-2, a Chinese high-resolution optical remote-sensing satellite), Sentinel-2, and Landsat-8 images, respectively. Then, the hybrid DNN-TSEB model was used to estimate H and LE at multi-pixel sizes. Finally, modeled H and LE at 1 ∼ 1000 m were validated by eddy covariance (EC) and optical-microwave scintillometer (OMS) flux observation. Results revealed that the DNN-based LST model was a potential approach to generate LST at multiple pixel sizes. The hybrid DNN-TSEB model can produce more accurate H and LE when different land cover types were discriminated over heterogeneous farmland (e.g., the average bias for H and LE at a spatial resolution of 1 m were −9 and −6 W/m−2, respectively). Besides, the deviation of modeled fluxes from the observations increased as the spatial resolution became coarser, particularly the pixel size was greater than 30 m (average bias for H and LE were −34 and 30 W m−2, respectively). However, the magnitude of bias of fluxes estimates remained unchanged when the pixel sizes of satellite data were between 100 and 1000 m. The more important finding was that the hybrid model was a promising approach, which can obtain accurate estimates of H and LE at a high spatial resolution. In addition, the performance of the model based on GF-2 data was better than that based on Sentinel-2 and Landsat-8 data. The results suggest that pixel heterogeneity should be considered when estimating H and LE over heterogeneous landscapes with various surface types.

Cloud shadow removal for optical satellite data

An improved cloud shadow removal algorithm for high spatial resolution optical satellite data over land is presented. The method is based on the matched filter method, which consists of the calculation of a covariance matrix and the corresponding zero-reflectance matched filter vector and the computation of the shadow function. The new additions consist of the usage of an improved cloud shadow map and further evaluations performed on the shadow function. The performance of the cloud shadow removal algorithm incorporated in the software package Python-based atmospheric correction (PACO) is compared to the deshadowing algorithm in atmospheric correction on a set of 25 Sentinel-2 scenes distributed over the globe covering a wide variety of environments and climates. Furthermore, an evaluation of the relative ratio between clear and shadow pixels with and without deshadowing is performed. The visual, spectral, and statistical results show that the new additions performed on the deshadowing algorithm can improve the cloud shadow removal performance used so far.

Potential landslides risk assessment based on remote sensing technique-a cause study from Dorset, southern England, United Kingdom

This paper presents a method of potential landslide risk assessment from the Dorset Southern England, United Kingdom. It concentrated on potential geological hazards and vulnerability to build a quantitative landslide risk framework in Dorset. In this study, the landslides risk assessment is centered on three components: identification of risks, calculation of risks, and evaluation of risks. Therefore, different natural environmental situations were collected using a large set of optical high-resolution satellite images and remote sensing to determine the probability of landslide occurrence and provide the quantitative model by combining the remote sensing technique. The result shows Dorset area risk level is high. The possibility of landslides mainly comes from natural conditions and human actions. The calculation of the possibility of potential landslides is based on the Bayes’ theorem. Moreover, the limitation of the probability potential risk calculation is insensitivity. The challenge is related to the temporal resolution of precipitation information.

GPU-Accelerated PCG Method for the Block Adjustment of Large-Scale High-Resolution Optical Satellite Imagery Without GCPs

The precise geo-positioning of high-resolution satellite imagery (HRSI) without ground control points (GCPs) is an important and fundamental step in global mapping, three-dimensional modeling, and so on. In this paper, to improve the efficiency of large-scale bundle adjustment (BA), we propose a combined Preconditioned Conjugate Gradient (PCG) and Graphic Processing Unit (GPU) parallel computing approach for the BA of large-scale HRSI without GCPs. The proposed approach consists of three main components: 1) construction of a BA model without GCPs ; 2) reduction of memory consumption using the Compressed Sparse Row sparse matrix format; and 3) improvement of the computational efficiency by the use of the combined PCG and GPU parallel computing method. The experimental results showed that the proposed method: 1) consumes less memory consumption compared to the conventional full matrix format method; 2) demonstrates higher computational efficiency than the single-core, Ceres-solver and multi-core central processing unit computing methods, with 9.48, 6.82, and 3.05 times faster than the above three methods, respectively; 3) obtains comparable BA accuracy with the above three methods, with image residuals of about 0.9 pixels; and 4) is superior to the parallel bundle adjustment method in the reprojection error.

Freely accessible inventory and spatial distribution of large-scale landslides in Xianyang City, Shaanxi Province, China

In this study, we used high-resolution optical satellite images on the Google Earth platform to map large-scale landslides in Xianyang City, Shaanxi Province, China. After mapping, a comprehensive and detailed large-scale landslide inventory that contains 2924 large-scale landslides was obtained. We analyzed the spatial distribution of landslides with seven influencing factors, including elevation, slope angle, aspect, curvature, lithology, distance to a river, and distance to the fault. Landslide Number, Landslide Area, Landslide Number Density (LND), and Landslide Area Percentage (LAP) were selected as indexes for the spatial distribution analysis. The results show that the number and area of landslides in the elevation range of 1000–1200 ​m is the highest. The highest number of landslides was observed in the slope angle of 25°–30°. North-facing slopes are prone to sliding. The area and number of landslides are the largest when the slope curvature ranges from −1.28 to 0. The LND and LAP reach their maxima when the slope curvature is less than −2.56. Areas covered by the Tertiary stratum with weakened fine-grained sandstone and siltstone show the highest LND and LAP values. Regarding distance to a river, the LAP peaks in the range of 300–600 ​m, whereas the LND peaks in an area larger than 2100 ​m. The values of LND and LNP rise as the distance from the faults increases, except for the locations 30 ​km away from active faults. This phenomenon is because active faults in this area pass through the plain areas, while landslides mostly occur in mountainous areas. The cataloging of landslide development in Xianyang City provides a significant scientific foundation for future research on landslides. In addition, the spatial distribution results are useful for landslide hazard prevention decisions and provide valuable references in this area.

Irrigation Timing Retrieval at the Plot Scale Using Surface Soil Moisture Derived from Sentinel Time Series in Europe

The difficulty of calculating the daily water budget of irrigated fields is often due to the uncertainty surrounding irrigation amounts and timing. The automated detection of irrigation events has the potential to greatly simplify this process, and the combination of high-resolution SAR (Sentinel-1) and optical satellite observations (Sentinel-2) makes the detection of irrigation events feasible through the use of a surface soil moisture (SSM) product. The motivation behind this study is to utilize a large irrigation dataset (collected during the ESA Irrigation + project over five sites in three countries over three years) to analyze the performance of an established algorithm and to test potential improvements. The study’s main findings are (1) the scores decrease with SSM observation frequency; (2) scores decrease as irrigation frequency increases, which was supported by better scores in France (more sprinkler irrigation) than in Germany (more localized irrigation); (3) replacing the original SSM model with the force-restore model resulted in an improvement of about 6% in the F-score and narrowed the error on cumulative seasonal irrigation; (4) the Sentinel-1 configuration (incidence angle, trajectory) did not show a significant impact on the retrieval of irrigation, which supposes that the SSM is not affected by these changes. Other aspects did not allow a definitive conclusion on the irrigation retrieval algorithm: (1) the lower scores obtained with small NDVI compared to large NDVI were counter-intuitive but may have been due to the larger number of irrigation events during high vegetation periods; (2) merging different runs and interpolating all SSM data for one run produced comparable F-scores, but the estimated cumulative sum of irrigation was around −20% lower compared to the reference dataset in the best cases.

InSAR Displacement with High-Resolution Optical Remote Sensing for the Early Detection and Deformation Analysis of Active Landslides in the Upper Yellow River

Frequent landslides and other geological disasters pose a serious threat to human life and infrastructure in the Upper Yellow River. Detecting active landslides and ascertaining their impact necessitate the determination of deformation characteristics. In this study, we developed an integrated method combining interferometric synthetic aperture radar and high-resolution optical satellite remote sensing to detect active landslides in the Upper Yellow River region from Longyang Gorge to Lijia Gorge. Sentinel-1 satellite data from January 2019 to April 2021 with ascending and descending orbits were adopted to obtain deformation using the STACKING and interferometric point target analysis techniques. A 97.08% overlap rate in the detected results from the two InSAR technologies confirmed the suitability of both approaches. The missing detection rates (6.79% & 8.73%) from single line-of-sight (LOS) InSAR results indicate the necessity of different orbit direction data. Slight deformation rate changes (<4 mm/month) before and after rainy seasons of the Lijia Gorge landslide group indicate that precipitation exerted little impact on slope activity. This study supports the feasibility of integrated methods for the detection and analysis of active landslides in the Upper Yellow River and other regions.

Identifying Alpine Lakes in the Eastern Himalayas Using Deep Learning

Alpine lakes, which include glacial and nonglacial lakes, are widely distributed in high mountain areas and are sensitive to climate and environmental changes. Remote sensing is an effective tool for identifying alpine lakes over large regions, but in the case of small lakes, the complex terrain and extreme weather make their accurate identification extremely challenging. This paper presents an automated method for alpine lake identification developed by leveraging deep learning algorithms and multi-source high-resolution satellite data. The method is able to detect the outlines and types of alpine lakes from high-resolution optical and Synthetic Aperture Radar (SAR) satellite data. In this study, a total of 4584 alpine lakes (including 2795 glacial lakes) were identified in the Eastern Himalayas from Sentinel-1 and Sentinel-2 data acquired during 2016–2020. The average area of the lakes was 0.038 km2, and the average elevation was 4974 m. High accuracy was reported for the dataset for both segmentation (mean Intersection Over Union (MIoU) > 72%) and classification (Overall Accuracy, User’s and Producer’s Accuracies, and F1-Score are all higher than 85%). A higher accuracy was found for the combination of optical and SAR data than relying on single-sourced data, for which the MIoU increased by at least 12%, suggesting that the combination of optical and SAR data is critical for improving the identification of alpine lakes. The deep learning-based method demonstrated a significant improvement over traditional spectral extraction methods.

Annotating very high-resolution satellite imagery: A whale case study

The use of very high-resolution (VHR) optical satellites is gaining momentum in the field of wildlife monitoring, particularly for whales, as this technology is showing potential for monitoring the less studied regions. However, surveying large areas using VHR optical satellite imagery requires the development of automated systems to detect targets. Machine learning approaches require large training datasets of annotated images. Here we propose a standardised workflow to annotate VHR optical satellite imagery using ESRI ArcMap 10.8, and ESRI ArcGIS Pro 2.5., using cetaceans as a case study, to develop AI-ready annotations.•A step-by-step protocol to review VHR optical satellite images and annotate the features of interest.•A step-by-step protocol to create bounding boxes encompassing the features of interest.•A step-by-step guide to clip the satellite image using bounding boxes to create image chips.