Flood disasters have a huge effect on human life, the economy, and the ecosystem. Quickly extracting the spatial extent of flooding is necessary for disaster analysis and rescue planning. Thus, extensive studies have utilized optical or radar data for the extraction of water distribution and monitoring of flood events. As the quality of detected flood inundation coverage by optical images is degraded by cloud cover, the current data products derived from optical sensors cannot meet the needs of rapid flood-range monitoring. The presented study proposes an adaptive thresholding method for extracting water coverage (AT-EWC) regarding rapid flooding from Sentinel-1 synthetic aperture radar (SAR) data with the assistance of prior information from Landsat data. Our method follows three major steps. First, applying the dynamic surface water extent (DSWE) algorithm to Landsat data acquired from the year 2000 to 2016, the distribution probability of water and non-water is calculated through the Google Earth Engine platform. Then, current water coverage is extracted from Sentinel-1 data. Specifically, the persistent water and non-water datasets are used to automatically determine the type of image histogram. Finally, the inundated areas are calculated by combining the persistent water and non-water datasets and the current water coverage as derived from the above two steps. This approach is fast and fully automated for flood detection. In the classification results from the WeiFang and Ji’An sites, the overall classification accuracy of water and land detection reached 95–97%. Our approach is fully automatic. In particular, the proposed algorithm outperforms the traditional method over small water bodies (inland watersheds with few lakes) and makes up for the low temporal resolution of existing water products. Full article

This paper proposes an automated active fire detection framework using Sentinel-2 imagery. The framework is made up of three basic parts including data collection and preprocessing, deep-learning-based active fire detection, and final product generation modules. The active fire detection module is developed on a specifically designed dual-domain channel-position attention (DCPA)+HRNetV2 model and a dataset with semi-manually annotated active fire samples is constructed over wildfires that commenced on the east coast of Australia and the west coast of the United States in 2019–2020 for the training process. This dataset can be used as a benchmark for other deep-learning-based algorithms to improve active fire detection accuracy. The performance of active fire detection is evaluated regarding the detection accuracy of deep-learning-based models and the processing efficiency of the whole framework. Results indicate that the DCPA and HRNetV2 combination surpasses DeepLabV3 and HRNetV2 models for active fire detection. In addition, the automated framework can deliver active fire detection results of Sentinel-2 inputs with coverage of about 12,000 km² (including data download) in less than 6 min, where average intersections over union (IoUs) of 70.4% and 71.9% were achieved in tests over Australia and the United States, respectively. Concepts in this framework can be further applied to other remote sensing sensors with data acquisitions in SWIR-NIR-Red ranges and can serve as a powerful tool to deal with large volumes of high-resolution data used in future fire monitoring systems and as a cost-efficient resource in support of governments and fire service agencies that need timely, optimized firefighting plans. Full article

Lidar data is increasingly available over large spatial extents and can also be combined with satellite imagery to provide detailed vegetation structural metrics. To fully realize the benefits of lidar data, practical and scalable processing workflows are needed. In this study, we used the lidR R software package, a custom forest metrics function in R, and a distributed cloud computing environment to process 11 TB of airborne lidar data covering ~22,900 km² into 28 height, cover, and density metrics. We combined these lidar outputs with field plot data to model basal area, trees per acre, and quadratic mean diameter. We compared lidar-only models with models informed by spectral imagery only, and lidar and spectral imagery together. We found that lidar models outperformed spectral imagery models for all three metrics, and combination models performed slightly better than lidar models in two of the three metrics. One lidar variable, the relative density of low midstory canopy, was selected in all lidar and combination models, demonstrating the importance of midstory forest structure in the study area. In general, this open-source lidar-processing workflow provides a practical, scalable option for estimating structure over large, forested landscapes. The methodology and systems used for this study offered us the capability to process large quantities of lidar data into useful forest structure metrics in compressed timeframes. Full article

Semantic segmentation is a fundamental task in remote sensing image analysis (RSIA). Fully convolutional networks (FCNs) have achieved state-of-the-art performance in the task of semantic segmentation of natural scene images. However, due to distinctive differences between natural scene images and remotely-sensed (RS) images, FCN-based semantic segmentation methods from the field of computer vision cannot achieve promising performances on RS images without modifications. In previous work, we proposed an RS image semantic segmentation framework SDFCNv1, combined with a majority voting postprocessing method. Nevertheless, it still has some drawbacks, such as small receptive field and large number of parameters. In this paper, we propose an improved semantic segmentation framework SDFCNv2 based on SDFCNv1, to conduct optimal semantic segmentation on RS images. We first construct a novel FCN model with hybrid basic convolutional (HBC) blocks and spatial-channel-fusion squeeze-and-excitation (SCFSE) modules, which occupies a larger receptive field and fewer network model parameters. We also put forward a data augmentation method based on spectral-specific stochastic-gamma-transform-based (SSSGT-based) during the model training process to improve generalizability of our model. Besides, we design a mask-weighted voting decision fusion postprocessing algorithm for image segmentation on overlarge RS images. We conducted several comparative experiments on two public datasets and a real surveying and mapping dataset. Extensive experimental results demonstrate that compared with the SDFCNv1 framework, our SDFCNv2 framework can increase the mIoU metric by up to 5.22% while only using about half of parameters. Full article

This study analyzed highly correlated, feature-rich datasets from hyperspectral remote sensing data using multiple statistical and machine-learning methods. The effect of filter-based feature selection methods on predictive performance was compared. In addition, the effect of multiple expert-based and data-driven feature sets, derived from the reflectance data, was investigated. Defoliation of trees (%), derived from in situ measurements from fall 2016, was modeled as a function of reflectance. Variable importance was assessed using permutation-based feature importance. Overall, the support vector machine (SVM) outperformed other algorithms, such as random forest (RF), extreme gradient boosting (XGBoost), and lasso (L1) and ridge (L2) regressions by at least three percentage points. The combination of certain feature sets showed small increases in predictive performance, while no substantial differences between individual feature sets were observed. For some combinations of learners and feature sets, filter methods achieved better predictive performances than using no feature selection. Ensemble filters did not have a substantial impact on performance. The most important features were located around the red edge. Additional features in the near-infrared region (800–1000 nm) were also essential to achieve the overall best performances. Filter methods have the potential to be helpful in high-dimensional situations and are able to improve the interpretation of feature effects in fitted models, which is an essential constraint in environmental modeling studies. Nevertheless, more training data and replication in similar benchmarking studies are needed to be able to generalize the results. Full article

The Nectarian-aged Crisium basin exhibits an extremely thin crust and complicated lunar geological history. This large multi-ring impact basin is characterized by prolonged lunar volcanism ranging from the Imbrian age to the Eratosthenian period, forming the high-Ti mare unit, low-Ti mare basalts, and very low-Ti mare unit. We produced an updated geological map of the Crisium basin and defined four mare units (Im1: 3.74 Ga; Im2: 3.49 Ga; Im3: 3.56 Ga; EIm: 2.49 Ga) in terms of distinct composition and mineralogy. Olivine was widely determined in the Ti-rich Im1, implying the hybridization source in the lunar mantle with the occurrence of small-scale convective overturn. The major phase of low-Ti basaltic volcanism occurred c.a. 3.5 Ga, forming Im2 and Im3 in the western area. The youngest mare unit (EIm) has slight variations of pyroxene compositions, implying a decrease of calcic content of basaltic volcanisms with time. Later, distal material transports from large impact events in highlands could complicate the mixing of local mare basalts in the Copernicus age, especially the Im3 unit. The identified olivine-bearing outcrops and widely Mg-rich materials (Mg# > 70, where Mg# = molar 100 × Mg/(Mg + Fe)) in the western highlands, assumed to be the occurrence of the Mg-suite candidates, require future lunar exploration missions to validate. Full article

Droughts are one of the world’s most destructive natural disasters. In large regions of Africa, droughts can have strong environmental and socioeconomic impacts. Understanding the mechanism that drives drought and predicting its variability is important for enhancing early warning and disaster risk management. Taking North and West Africa as the study area, this study adopted multi-source data and various statistical analysis methods, such as the joint probability density function (JPDF), to study the meteorological drought and return years across a long term (1982–2018). The standardized precipitation index (SPI) was used to evaluate the large-scale spatiotemporal drought characteristics at 1–12-month timescales. The intensity, severity, and duration of drought in the study area were evaluated using SPI–12. At the same time, the JPDF was used to determine the return year and identify the intensity, duration, and severity of drought. The Mann-Kendall method was used to test the trend of SPI and annual precipitation at 1–12-month timescales. The pattern of drought occurrence and its correlation with climate factors were analyzed. The results showed that the drought magnitude (D_M) of the study area was the highest in 2008–2010, 2000–2003, and 1984–1987, with the values of 5.361, 2.792, and 2.187, respectively, and the drought lasting for three years in each of the three periods. At the same time, the lowest D_M was found in 1997–1998, 1993–1994, and 1991–1992, with D_M values of 0.113, 0.658, and 0.727, respectively, with a duration of one year each time. It was confirmed that the probability of return to drought was higher when the duration of drought was shorter, with short droughts occurring more regularly, but not all severe droughts hit after longer time intervals. Beyond this, we discovered a direct connection between drought and the North Atlantic Oscillation Index (NAOI) over Morocco, Algeria, and the sub-Saharan countries, and some slight indications that drought is linked with the Southern Oscillation Index (SOI) over Guinea, Ghana, Sierra Leone, Mali, Cote d’Ivoire, Burkina Faso, Niger, and Nigeria. Full article

The F10.7 solar flux index is a measure of microwave solar emissions at a wavelength of 10.7 cm or 2800 MHz. It is widely used in thermosphere and ionosphere models as an indicator of solar activity and is recorded at only one terrestrial observatory in Penticton, Canada during daylight hours. The lack of geographical and temporal coverage of F10.7 measurements and no external redundancy to the existing system has led to the development of the RMCSat mission, which seeks to demonstrate the feasibility of collecting microwave solar flux emissions from a space-based platform. RMCSat is the first CubeSat mission by the Royal Military College of Canada. It offers a training environment for personnel in space mission analysis and design, satellite assembly, integration and testing, and satellite operations. This paper introduces the mission concept and preliminary design of a space-based solution that captures solar density flux measurements during each orbit as the Sun passes through the boresight of the primary payload antenna. In addition to two channels recording the 2800 MHz frequency (2785 MHz and 2815 MHz), a third channel records 2695 MHz using the same calibration standard to determine if the United States Radio Solar Telescope Network (RSTN) could be leveraged to supplement the existing F10.7 solar flux measurements and improve solar flux approximations. The RMCSat mission, satellite design, and system budgets are demonstrated here as being viable. Future design considerations pertain to the payload antennas and achievable launch orbits. Full article

Natural disaster impact assessment is of the utmost significance for post-disaster recovery, environmental protection, and hazard mitigation plans. With their recent usage in landslide susceptibility mapping, deep learning (DL) architectures have proven their efficiency in many scientific studies. However, some restrictions, including insufficient model variance and limited generalization capabilities, have been reported in the literature. To overcome these restrictions, ensembling DL models has often been preferred as a practical solution. In this study, an ensemble DL architecture, based on shared blocks, was proposed to improve the prediction capability of individual DL models. For this purpose, three DL models, namely Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM), together with their ensemble form (CNN–RNN–LSTM) were utilized to model landslide susceptibility in Trabzon province, Turkey. The proposed DL architecture produced the highest modeling performance of 0.93, followed by CNN (0.92), RNN (0.91), and LSTM (0.86). Findings proved that the proposed model excelled the performance of the DL models by up to 7% in terms of overall accuracy, which was also confirmed by the Wilcoxon signed-rank test. The area under curve analysis also showed a significant improvement (~4%) in susceptibility map accuracy by the proposed strategy. Full article

The segmentation of remote sensing images by deep learning technology is the main method for remote sensing image interpretation. However, the segmentation model based on a convolutional neural network cannot capture the global features very well. A transformer, whose self-attention mechanism can supply each pixel with a global feature, makes up for the deficiency of the convolutional neural network. Therefore, a multi-scale adaptive segmentation network model (MSST-Net) based on a Swin Transformer is proposed in this paper. Firstly, a Swin Transformer is used as the backbone to encode the input image. Then, the feature maps of different levels are decoded separately. Thirdly, the convolution is used for fusion, so that the network can automatically learn the weight of the decoding results of each level. Finally, we adjust the channels to obtain the final prediction map by using the convolution with a kernel of 1 × 1. By comparing this with other segmentation network models on a WHU building data set, the evaluation metrics, mIoU, F1-score and accuracy are all improved. The network model proposed in this paper is a multi-scale adaptive network model that pays more attention to the global features for remote sensing segmentation. Full article

The vegetative cover in and surrounding the Rohingya refugee camps in Ukhiya-Teknaf is highly vulnerable since millions of refugees moved into the area, which led to severe environmental degradation. In this research, we used a supervised image classification technique to quantify the vegetative cover changes both in Ukhiya-Teknaf and thirty-four refugee camps in three time-steps: one pre-refugee crisis (January 2017), and two post-refugee crisis (March 2018, and February 2019), in order to identify the factors behind the decline in vegetative cover. The vegetative cover vulnerability of the thirty-four refugee camps was assessed using the Per Capita Greening Area (PCGA) datasets and K-means classification techniques. The satellite-based monitoring result affirms a massive loss of vegetative cover, approximately 5482.2 hectares (14%), in Ukhiya-Teknaf and 1502.56 hectares (79.57%) among the thirty-four refugee camps, between 2017 and 2019. K-means classification revealed that the vegetative cover in about 82% of the refugee camps is highly vulnerable. In the end, a recommendation as to establishing the studied region as an ecological park is proposed and some guidelines discussed. This could protect and reserve forests from further deforestation in the area, and foster future discussion among policymakers and researchers. Full article

Big optical Earth observation (EO) data analytics usually start from numerical, sub-symbolic reflectance values that lack inherent semantic information (meaning) and require interpretation. However, interpretation is an ill-posed problem that is difficult for many users to solve. Our semantic EO data cube architecture aims to implement computer vision in EO data cubes as an explainable artificial intelligence approach. Automatic semantic enrichment provides semi-symbolic spectral categories for all observations as an initial interpretation of color information. Users graphically create knowledge-based semantic models in a convergence-of-evidence approach, where color information is modelled a-priori as one property of semantic concepts, such as land cover entities. This differs from other approaches that do not use a-priori knowledge and assume a direct 1:1 relationship between reflectance values and land cover. The semantic models are explainable, transferable, reusable, and users can share them in a knowledgebase. We provide insights into our web-based architecture, called Sen2Cube.at, including semantic enrichment, data models, knowledge engineering, semantic querying, and the graphical user interface. Our implemented prototype uses all Sentinel-2 MSI images covering Austria; however, the approach is transferable to other geographical regions and sensors. We demonstrate that explainable, knowledge-based big EO data analysis is possible via graphical semantic querying in EO data cubes. Full article

Ukraine is an associate member of the European Union, and in the coming years, it is expected that all the data and services already used by European Union countries will become available for Ukraine. An important program, which is the basis for building European monitoring services for smart cities, is the Copernicus program. The two most important services of this program are the Copernicus Land Monitoring Service (CLMS) and the Copernicus Atmosphere Monitoring Service (CAMS). CLMS provides important information on land use in Europe. In the context of smart cities, the most valuable tool is the Urban Atlas service, which is related to local CLMS services and provides a detailed digital city plan in vector form, which is segmented into small functional areas classified by Coordinate Information on the Environment (CORINE) nomenclature. The Urban Atlas is a geospatial layer with high resolution, built for all European cities with a population of more than 100,000. It combines high-resolution satellite data, city segmentation by blocks and functional urban areas (FUAs), important city infrastructure, etc. This product is used as a basis for city planning and obtaining analytics on the most important indicators of city development, including air quality monitoring. For Ukraine, such geospatial products are not provided under the Copernicus program. In this article, FUAs are developed for Ukrainian cities using European technology. It is important to start work on this program’s implementation as early as possible so that when the first city atlas appears, Ukraine will be ready to work with it together with the European community. This requires preparing the basis for national research and training national stakeholders and consumers to use this product. To make this happen, it is necessary to have a national geospatial product that can be used as an analogue of the city atlas. In this article, the authors analyzed the existing methods of air quality assessment and the Global Sustainable Development Goal (SDG) indicator 11.6.2, “Annual mean levels of fine particulate matter (e.g., PM_2.5 and PM₁₀) in cities (population weighted)”, achieved for European cities. Based on this, indicator 11.6.2 was then evaluated for the first time in Ukraine, considering the next 5 years. For the correct use of global products for Ukraine, CAMS global satellite data and population data (Global Human Settlement Layer and NASA population data) for Ukrainian cities were validated. These studies showed a statistically significant result and, therefore, demonstrated that global products can be used to monitor air quality both at the city level and for Ukraine as a whole. The obtained results were analyzed, and the values of indicator 11.6.2 for Ukraine were compared with those for other European countries. Full article

Seagrass meadows are one of the blue carbon ecosystems that continue to decline worldwide. Frequent mapping is essential to monitor seagrass meadows for understanding change processes including seasonal variations and influences of meteorological and oceanic events such as typhoons and cyclones. Such mapping approaches may also enhance seagrass blue carbon strategy and management practices. Although unmanned aerial vehicle (UAV) aerial photography has been widely conducted for this purpose, there have been challenges in mapping accuracy, efficiency, and applicability to subtidal water meadows. In this study, a novel method was developed for mapping subtidal and intertidal seagrass meadows to overcome such challenges. Ground truth seagrass orthophotos in four seasons were created from the Futtsu tidal flat of Tokyo Bay, Japan, using vertical and oblique UAV photography. The feature pyramid network (FPN) was first applied for automated seagrass classification by adjusting the spatial resolution and normalization parameters and by considering the combinations of seasonal input data sets. The FPN classification results ensured high performance with the validation metrics of 0.957 overall accuracy (OA), 0.895 precision, 0.942 recall, 0.918 F1-score, and 0.848 IoU, which outperformed the conventional U-Net results. The FPN classification results highlighted seasonal variations in seagrass meadows, exhibiting an extension from winter to summer and demonstrating a decline from summer to autumn. Recovery of the meadows was also detected after the occurrence of Typhoon No. 19 in October 2019, a phenomenon which mainly happened before summer 2020. Full article

Mixed forests make up the majority of natural forests, and they are conducive to improving the resilience and resistance of forest ecosystems. Moreover, it is in the crown of the trees where the effect of inter- and intra-specific interaction between them is evident. However, our knowledge of changes in crown morphology caused by density, competition, and mixture of specific species is still limited. Here, we provide insight on stand structural complexity based on the study of four response crown variables (Maximum Crown Width Height, MCWH; Crown Base Height, CBH; Crown Volume, CV; and Crown Projection Area, CPA) derived from multiple terrestrial laser scans. Data were obtained from six permanent plots in Northern Spain comprising of two widespread species across Europe; Scots pine (Pinus sylvestris L.) and sessile oak (Quercus petraea (Matt.) Liebl.). A total of 193 pines and 256 oaks were extracted from the point cloud. Correlation test were conducted (ρ ≥ 0.9) and finally eleven independent variables for each target tree were calculated and categorized into size, density, competition and mixture, which was included as a continuous variable. Linear and non-linear multiple regressions were used to fit models to the four crown variables and the best models were selected according to the lowest AIC Index and biological sense. Our results provide evidence for species plasticity to diverse neighborhoods and show complementarity between pines and oaks in mixtures, where pines have higher MCWH and CBH than oaks but lower CV and CPA, contrary to oaks. The species complementarity in crown variables confirm that mixtures can be used to increase above ground structural diversity. Full article