Advances in Earth Observation and Geosciences

Airborne laser technology produces point clouds that can be used to build 3D models of buildings. However, the work is a laborious process that could benefit from automation. Artificial intelligence (AI) has been widely used in automating building segmentation as one of the initial stages in the 3D modeling process. The algorithms with a high success rate using point clouds for automatic semantic segmentation are random forest (RF) and PointNet++, with each algorithm having its own advantages and disadvantages. However, the training and testing data to develop and test the model usually share similar characteristics. Moreover, producing a good automation model requires a lot of training data, which may become an issue for users with a small amount of training data (limited data). The aim of this research is to test the performance of the RF and PointNet++ models in different regions with limited training and testing data. We found that the RF model developed from a small amount data, in different regions between the training and testing data, performs well compared to PointNet++, yielding an OA score of 73.01% for the RF model. Furthermore, several scenarios have been used in this research to explore the capabilities of RF in several cases. Full article

A critical comprehension of the impact of snow cover on urban bidirectional reflectance is pivotal for precise assessments of energy budgets, radiative forcing, and urban climate change. This study develops a numerical model that employs the Monte Carlo ray-tracing technique and a snow anisotropic reflectance model (ART) to simulate spectral albedo and bidirectional reflectance, accounting for urban structure and snow anisotropy. Validation using three flat surfaces and MODIS data (snow-free, fresh snow, and melting snow scenarios) revealed minimal errors: the maximum domain-averaged BRDF bias was 0.01% for flat surfaces, and the overall model-MODIS deviation was less than 0.05. The model’s performance confirmed its accuracy in reproducing the reflectance spectrum. A thorough investigation of key factors affecting bidirectional reflectance in snow-covered urban canyons ensued, with snow coverage found to be the dominant influence. Urban coverage, building height, and soot pollutant concentration significantly impact visible and infrared reflectance, while snow grain size has the greatest effect on shortwave infrared. The bidirectional reflectance at backward scattering angles (0.5–0.6) at 645 nm is lower than forward scattering (around 0.8) in the principal plane as snow grain size increases. These findings contribute to a deeper understanding of snow-covered urban canyons’ reflectance characteristics and facilitate the quantification of radiation interactions, cloud-snow discrimination, and satellite-based retrieval of aerosol and snow parameters. Full article

Three-dimensional coseismic surface deformation fields are important for quantifying the geometric and kinematic characteristics of earthquake rupture faults. However, traditional geodetic techniques are constrained by intrinsic limitations: Interferometric synthetic aperture radar (InSAR) can only extract far-field deformation fields owing to incoherence; global navigation satellite systems (GNSSs) can only acquire displacement at discrete points. The recently developed optical pixel correlation technique, which is based on high-resolution remote sensing images, can acquire near-field coseismic horizontal deformation. In this study, InSAR line-of-sight (LOS) and azimuth direction far-field deformation, horizontal near-field deformation determined using optical pixel correlation based on pre- and post-earthquake GaoFen (GF)-2/7 images, and vertical deformation determined by differencing pre- and post-earthquake GF-7 digital elevation models (DEMs) were combined to comprehensively provide the three-dimensional deformation field of the 2022 Mw 6.6 Menyuan earthquake. The results show that the near-field deformation field calculated by optical pixel correlation quantified displacements distributed over the rupture fault zone, which were not available from the InSAR deformation maps. We identified significant vertical displacements of ~1–1.5 m at a bend region, which were induced by local compressive stress. The maximum uplift (>2.0 m) occurred near the epicenter, on the southern sides of the main and secondary faults along the middle segment of the ruptured Lenglongling fault. In addition, surface two-dimensional strain derived from the displacement maps calculated by optical pixel correlation revealed high strain concentration on the rupture fault zone. The method described herein provides a new tool for a better understanding of the characteristics of coseismic surface deformation and rupture patterns of faults. Full article

The new generation of satellite hyperspectral (HS) sensors provides remarkable potential for regional-scale mineralogical mapping. However, as with any satellite sensor, mapping results are dependent on a typically complex correction procedure needed to remove atmospheric, topographic and geometric distortions before accurate reflectance spectra can be retrieved. These are typically applied by the satellite operators but use different approaches that can yield different results. In this study, we conduct a comparative analysis of PRISMA, EnMAP, and EMIT hyperspectral satellite data, alongside airborne data acquired by the HyMap sensor, to investigate the consistency between these datasets and their suitability for geological mapping. Two sites in Namibia were selected for this comparison, the Marinkas-Quellen and Epembe carbonatite complexes, based on their geological significance, relatively good exposure, arid climate and data availability. We conducted qualitative and three different quantitative comparisons of the hyperspectral data from these sites. These included correlative comparisons of (1) the reflectance values across the visible-near infrared (VNIR) to shortwave infrared (SWIR) spectral ranges, (2) established spectral indices sensitive to minerals we expect in each of the scenes, and (3) spectral abundances estimated using linear unmixing. The results highlighted a notable shift in inter-sensor consistency between the VNIR and SWIR spectral ranges, with the VNIR range being more similar between the compared sensors than the SWIR. Our qualitative comparisons suggest that the SWIR spectra from the EnMAP and EMIT sensors are the most interpretable (show the most distinct absorption features) but that latent features (i.e., endmember abundances) from the HyMap and PRISMA sensors are consistent with geological variations. We conclude that our results reinforce the need for accurate radiometric and topographic corrections, especially for the SWIR range most commonly used for geological mapping. Full article

Satellite sea surface temperature (SST) images are valuable for various oceanic applications, including climate monitoring, ocean modeling, and marine ecology. However, cloud cover often obscures SST signals, creating gaps in the data that reduce resolution and hinder spatiotemporal analysis, particularly in the waters near Taiwan. Thus, gap-filling methods are crucial for reconstructing missing SST values to provide continuous and consistent data. This study introduces a gap-filling approach using the Double U-Net, a deep neural network model, pretrained on a diverse dataset of Level-4 SST images. These gap-free products are generated by blending satellite observations with numerical models and in situ measurements. The Double U-Net model excels in capturing SST dynamics and detailed spatial patterns, offering sharper representations of ocean current-induced SST patterns than the interpolated outputs of Data Interpolating Empirical Orthogonal Functions (DINEOFs). Comparative analysis with buoy observations shows the Double U-Net model’s enhanced accuracy, with better correlation results and lower error values across most study areas. By analyzing SST at five key locations near Taiwan, the research highlights the Double U-Net’s potential for high-resolution SST reconstruction, thus enhancing our understanding of ocean temperature dynamics. Based on this method, we can combine more high-resolution satellite data in the future to improve the data-filling model and apply it to marine geographic information science. Full article

Soil salinization has seriously affected agricultural production and ecological balance in the Yellow River Delta region. Rapid and accurate monitoring of soil salinity has become an urgent need. Traditional machine learning models tend to fall into local optimal values during the learning process, which reduces their accuracy. This paper introduces Circle map to enhance the crayfish optimization algorithm (COA), which is then integrated with the regularized extreme learning machine (RELM) model, aiming to improve the accuracy of soil salinity content (SSC) inversion in the Yellow River Delta region. We employed Landsat5 TM remote sensing images and measured salinity data to develop spectral indices, such as the band index, salinity index, vegetation index, and comprehensive index, selecting the optimal modeling variable group through Pearson correlation analysis and variable projection importance analysis. The back propagation neural network (BPNN), RELM, and improved crayfish optimization algorithm–regularized extreme learning machine (ICOA-RELM) models were constructed using measured data and selected variable groups for SSC inversion. The results indicate that the ICOA-RELM model enhances the $R^2$ value by an average of about 0.1 compared to other models, particularly those using groups of variables filtered by variable projection importance analysis as input variables, which showed the best inversion effect (test set $R^2$ value of 0.75, MAE of 0.198, RMSE of 0.249). The SSC inversion results indicate a higher salinization degree in the coastal regions of the Yellow River Delta and a lower degree in the inland areas, with moderate saline soil and severe saline soil comprising 48.69% of the total area. These results are consistent with the actual sampling results, which verify the practicability of the model. This paper’s methods and findings introduce an innovative and practical tool for monitoring and managing salinized soils in the Yellow River Delta, offering significant theoretical and practical benefits. Full article

The clarification of the impact of human activities on vegetation in mining areas contributes to the harmonization of mining and environmental protection. This study utilized Geographically and Temporally Weighted Regression (GTWR) to establish a quantitative relationship among the Normalized Difference Vegetation Index (NDVI), temperature, precipitation, and Digital Elevation Model (DEM). Furthermore, residual analysis was performed to remove the impact of natural factors and separately assess the impact of human activities on vegetation restoration. The experiment was carried out in Shangwan Mine, China, and following results were obtained: (1) During the period of 2000 to 2020, intensified huan activities corresponded to positive vegetation changes (NDVI-HA) that exhibited an upward trend over time. (2) The spatial heterogeneity of vegetation restoration was attributed to the DEM. It is negatively correlated with NDVI in natural conditions, while under the environment of mining activities, there is a positive correlation between NDVI-HA and DEM. (3) The contribution of human activities to vegetation restoration in mining areas has been steadily increasing, surpassing the influences of temperature and precipitation since 2010. The results of this study can provide important references for the assessment of vegetation restoration to some extent in mining areas. Full article

In recent decades, an important number of regional and global digital elevation models (DEMs) have been released publicly. As a consequence, researchers need to choose between several of these models to perform their studies and to use these DEMs as third-party data to compute derived products (e.g., for orthorectification). However, the comparison of DEMs is not trivial. For most quantitative comparisons, DEMs need to be expressed in the same coordinate reference system (CRS) and sampled over the same grid (i.e., be at the same ground sampling distance with the same pixel-is-area or pixel-is-point convention) with heights relative to the same vertical reference system (VRS). Thankfully, many open tools allow us to perform these transformations precisely and easily. Despite these rigorous transformations, local or global planimetric displacements may still be observed from one DEM to another. These displacements or disparities may lead to significant biases in comparisons of DEM elevations or derived products such as slope, aspect, or curvature. Therefore, before any comparison, the control of DEM planimetric accuracy is certainly a very important task to perform. This paper presents the disparity analysis method enhanced to achieve a sub-pixel accuracy by interpolating the linear regression coefficients computed within an exploration window. This new method is significantly faster than oversampling the input data because it uses the correlation coefficients that have already been computed in the disparity analysis. To demonstrate the robustness of this algorithm, artificial displacements have been introduced through bicubic interpolation in an 11 × 11 grid with a 0.1-pixel step in both directionsThis validation method has been applied in four approximately 10 km × 10 km DEMIX tiles showing different roughness (height distribution). Globally, this new sub-pixel accuracy method is robust. Artificial displacements have been retrieved with typical errors (e_b) ranging from 12 to 20% of the pixel size (with the worst case in Croatia). These errors in displacement retrievals are not equally distributed in the 11 × 11 grid, and the overall error E_b depends on the roughness encountered in the different tiles. The second aim of this paper is to assess the impact of the bicubic parameter (slope of the weight function at a distance d = 1 of the interpolated point) on the accuracy of the displacement retrieval. By considering E_b as a quality indicator, tests have been performed in the four DEMIX tiles, making the bicubic parameter vary between −1.5 and 0.0 by a step of 0.1. For each DEMIX tile, the best bicubic (BBC) parameter b* is interpolated from the four E_b minimal values. This BBC parameter b* is low for flat areas (around −0.95) and higher in mountainous areas (around −0.75). The roughness indicator is the standard deviation of the slope norms computed from all the pixels of a tile. A logarithmic regression analysis performed between the roughness indicator and the BBC parameter b* computed in 67 DEMIX tiles shows a high correlation (r = 0.717). The logarithmic regression formula $\tilde{b}\left({\sigma }_{slope}\right)$ estimating the BBC parameter from the roughness indicator is generic and may be applied to estimate the displacements between two different DEMs. This formula may also be used to set up a future Adaptative Best BiCubic (ABBC) that will estimate the local roughness in a sliding window to compute a local BBC $\tilde{b}$. Full article

The satellite imagery of nighttime lights (NTLs) has been studied to understand human activities, economic development, and more recently, the ecological impact of brighter night skies. The Visible Infrared Imaging Radiometer Suite (VIIRS) Day–Night Band (DNB) offers perhaps the most advanced nighttime imaging capabilities to date, but its large pixel size and single band capture large-scale changes in NTL while missing granular but important details, such as lighting type and brightness. To better understand individual NTL sources in a region, the spectra of nighttime lights captured by the DLR Earth Sensing Imaging Spectrometer (DESIS) were extracted and compared against near-coincident VIIRS DNB imagery. The analysis shows that DESIS’s finer spatial and spectral resolutions can detect individual NTL locations and types beyond what is possible with the DNB. Extracted night light spectra, validated against ground truth measurements, demonstrate DESIS’s ability to accurately detect and identify narrow-band atomic emission lines that characterize the spectra of high-intensity discharge (HID) light sources and the broader spectral features associated with different light-emitting diode (LED) lights. These results suggest the possible application of using hyperspectral data from moderate-resolution sensors to identify lamp construction details, such as illumination source type and light quality in low-light contexts. NTL data from DESIS and other hyperspectral sensors may improve the scientific understanding of light pollution, lighting quality, and energy efficiency by identifying, evaluating, and mapping individual and small groups of light sources. Full article

Slant range geometry plays a crucial role in interpreting synthetic aperture radar (SAR) observations, especially in converting line-of-sight (LOS) surface deformations to actual vertical subsidence. This paper proposes a new conversion model to retrieve vertical settlements of the embankment slopes using the geometrical parameters of the dam and the SAR sensor. The simulation results highlight the impact of slope foreshortening and heading direction of the satellite on deformation retrieval. Various SAR data with different resolutions and bands are used to analyze the model’s performance, revealing a high conformity of the model with practical conversion parameters exceeding 80% for TerraSAR-X and Cosmo-SkyMed data. Full article

Global Earth observation is becoming increasingly important in understanding and addressing critical aspects of life on our planet, including environmental issues, natural disasters, sustainable development, and others. Finding similarities in landscapes may provide useful information regarding applying contiguous policies, by making similar decisions or learning from best practices for events and occurrences that previously occurred in similar landscapes in the past. However, current applications of similar landscape retrieval are limited by a moderate performance and the need for time-consuming and costly annotations. We propose splitting the similar landscape retrieval task into a set of smaller tasks that aim to identify individual concepts inherent to satellite images. Our approach relies on several models trained using unsupervised representation learning on Google Earth images to identify these concepts. We show the efficacy of matching individual concepts for retrieving landscape(s) similar to a user-selected satellite image of the geographical territory of the Republic of Cyprus. Our results demonstrate the benefits of breaking up the landscape similarity task into individual concepts closely related to remote sensing, instead of applying a single model targeting all underlying concepts. Full article

The stripmap mode is a basic and important mode for spaceborne synthetic aperture radars (SARs). Estimating the time-varying area observed by spaceborne SARs operating in stripmap mode is a practical but challenging field of research. In this article, we propose a novel method that parameterizes the time-varying area observed by the spaceborne SAR operating in the boresight stripmap mode into a fixed antenna attitude. Based on the principle of minimizing the dihedral angle between the plane containing the ideal estimated scatterers and the plane containing the actual parabolic antenna edge of a spaceborne SAR, an objective function is established for estimating the area observed by a spaceborne SAR operating in the boresight stripmap mode. Then, simulation experiments are designed to validate the feasibility and the robustness of the proposed method. The experimental simulation results show that the proposed method is feasible, and even under low signal-to-noise ratio (SNR) conditions of 10 dB, the proposed method still has good robustness. Full article

Based on subdaily kinematic GNSS solutions, the fault slip properties during the very early postseismic phase after the 2021 M 8.2 Chignik earthquake are investigated in this paper. The very early postseismic deformations captured by near-field GNSS sites can be well depicted by the power model. The comparison of afterslip determined by daily and subdaily GNSS solutions suggests that neglecting very early afterslip can result in the underestimation of postseismic slip. Compared with coseismic slip, the cumulative afterslip of the first 24 h is mainly focused in the southeast of the hypocenter, and the shallow updip afterslip appears after this earthquake. The spatio-temporal evolution of the afterslip reveals that the patch of afterslip is immediately generated after the earthquake, and then the postseismic slip gradually grows along the afterslip patch. The magnitude of the afterslip patch varies remarkably within the 24 h following the earthquake, especially in the first several hours. Meanwhile, the spatio-temporal patterns of aftershocks and afterslip exhibit strong similarity during the first 24 h, suggesting that very early afterslip may be a possible driving factor of aftershocks. Moreover, most of the afterslip patches and aftershocks occurring immediately after this earthquake are situated in the area covered by positive Coulomb Stress Change (CSC), which implies that the immediate afterslip and aftershock activities can be influenced by the coseismic CSC. The following afterslip process further releases coseismic CSC and then influences the spatio-temporal variations of aftershock activities. Thus, the afterslip may be a possible triggering mechanism of very early aftershocks for this earthquake, alongside the effects of the CSC generated by coseismic rupture. Full article

Vegetation encroachment in power line corridors remains a major challenge for modern energy-dependent societies, as it can cause power outages and lead to significant financial losses. Unmanned Aerial Vehicles (UAVs) have emerged as a promising solution for monitoring infrastructure, owing to their ability to acquire high-resolution overhead images of these areas quickly and affordably. However, accurate segmentation of the vegetation encroachment in this imagery is a challenging task, due to the complexity of the scene and the high pixel imbalance between the power lines, the vegetation and the background classes. In this paper, we propose a deep learning-based approach to tackle this problem caused by the original and different geometry of the objects. Specifically, we use DeepLabV3, U-Net and a modified version of the U-Net architecture with VGG-16 weights to train two separate models. One of them segments the dominant classes, the vegetation from the background, achieving an IoU of 0.77. The other one segments power line corridors from the background, obtaining an IoU of 0.64. Finally, ensembling both models into one creates an “encroachment” zone, where power lines and vegetation are intersected. We train our models using the Vegetation Encroachment in Power Line Corridors dataset (VEPL), which includes RGB orthomosaics and multi-label masks for segmentation. Experimental results demonstrate that our approach outperforms individual networks and original prominent architectures when applied to this specific problem. This approach has the potential to significantly improve the efficiency and accuracy of vegetation encroachment monitoring using UAV, thus helping to ensure the reliability and sustainability of power supply. Full article

This study explored the innovative use of multiple remote sensing satellites and unmanned aerial vehicles to calculate soil losses in the Loess Plateau of Iran. This finding emphasized the importance of using advanced technologies to develop accurate and efficient soil erosion assessment techniques. Accordingly, this study developed an approach to compare sinkholes and gully heads in hilly regions on the Loess Plateau of northeast Iran using convolutional neural network (CNN or ConvNet). This method involved coupling data from UAV, Sentinel-2, and SPOT-6 satellite data. The soil erosion computed using UAV data showed AUC values of 0.9247 and 0.9189 for the gully head and the sinkhole, respectively. The use of SPOT-6 data in gully head and sinkhole computations showed AUC values of 0.9105 and 0.9123, respectively. The AUC values were 0.8978 and 0.9001 for the gully head and the sinkhole using Sentinel-2, respectively. Comparison of the results from the calculated UAV, SPOT-6, and Sentinel-2 data showed that the UAV had the highest accuracy for calculating sinkhole and gully head soil features, although Sentinel-2 and SPOT-6 showed good results. Overall, the combination of multiple remote sensing satellites and UAVs offers improved accuracy, timeliness, cost effectiveness, accessibility, and long-term monitoring capabilities, making it a powerful approach for calculating soil loss in the Loess Plateau of Iran. Full article

The Pamir, situated in central Asia, is a result of the ongoing northward advance of the Indian continent, leading to compression of the Asian landmass. While geodetic and seismic data typically indicate that the most significant deformation in Pamir is along its northern boundary, an M_w 7.2 earthquake on 7 December 2015 and an M_w 6.8 earthquake on 23 February 2023 have occurred in the remote interior of Pamir. These two M_w ≥ 6.5 earthquakes, with good observations of satellite synthetic aperture radar data, provide a rare opportunity to gain insights into rupture mechanics and deformation patterns in this challenging-to-reach region. Here, we utilize spaceborne synthetic aperture radar data to determine the seismogenic faults and finite slip models for these two earthquakes. Our results reveal that the 2015 earthquake ruptured a ~88 km long, left-lateral strike-slip fault that dips to northwest. The rupture of the 2015 earthquake extended to the ground surface over a length of ~50 km with a maximum slip of ~3.5 m. In contrast, the 2023 earthquake did not rupture the ground surface, with a maximum slip of ~2.2 m estimated at a depth of ~9 km. Notably, the seismogenic fault of the 2015 earthquake does not align with the primary strand of the Sarez–Karakul fault system (SKFS), and the 2023 earthquake occurred on a previously unmapped fault. The well-determined seismogenic faults for the 2015 and 2023 earthquakes, along with the SKFS and other distributed faults in the region, suggest the existence of a wide shear zone extending from south to north within the central Pamir. Full article

The appearance and development of new construction materials, technology and accurate geodetic instruments have led to the necessity of their inevitable use in the health monitoring, maintenance, and restoration of civil structures and special structures such as high-rise cooling towers. This paper presents an accurate practical and analytical method for determining the structural deformation and axis inclination of high rise cooling towers using terrestrial laser scanner (TLS) observations through the projection of tower surface points coordinates on a vertical plane. Four cooling towers in El-Mahla El-Kubra city, Egypt are observed and studied. Two of them with height 56 m, and the others were 36 m height. The studied four towers have different cross-section diameters along the tower height. Each tower has a cone shape with a curved wall. The equation of the tower wall is determined using TLS observations and least squares adjustment techniques. The equations of cone projection with a curved wall are derived and presented in this paper. From TLS observations, the radii and accuracy of each 2 m tower height are determined with center coordinates, and then the inclination of the tower axis is calculated and drawn. From the results of TLS observations, data processing, and analysis using the suggested techniques, it is deduced that there is a deformation in tower walls with small values. The specified technique for observations collection and TLS data analysis through projection on a vertical plane is significant and valuable for determining the structural deformation of circular high rise buildings and towers. From the results, there are obvious deformation values in some cooling towers, so maintenance work must be included. The towers also must be checked and monitored several times at brief intervals. Full article

Land Surface Temperature (LST) is a key variable used across various applications, including irrigation monitoring, vegetation health assessment and urban heat island studies. While satellites offer moderate-resolution LST data, unmanned aerial vehicles (UAVs) provide high-resolution thermal infrared measurements. However, the continuous and rapid variation in LST makes the production of orthomosaics from UAV-based image collections challenging. Understanding the environmental and meteorological factors that amplify this variation is necessary to select the most suitable conditions for collecting UAV-based thermal data. Here, we capture variations in LST while hovering for 15–20 min over diverse surfaces, covering sand, water, grass, and an olive tree orchard. The impact of different flying heights and times of the day was examined, with all collected thermal data evaluated against calibrated field-based Apogee SI-111 sensors. The evaluation showed a significant error in UAV-based data associated with wind speed, which increased the bias from −1.02 to 3.86 °C for 0.8 to 8.5 m/s winds, respectively. Different surfaces, albeit under varying ambient conditions, showed temperature variations ranging from 1.4 to 6 °C during the flights. The temperature variations observed while hovering were linked to solar radiation, specifically radiation fluctuations occurring after sunrise and before sunset. Irrigation and atmospheric conditions (i.e., thin clouds) also contributed to observed temperature variations. This research offers valuable insights into LST variations during standard 15–20 min UAV flights under diverse environmental conditions. Understanding these factors is essential for developing correction procedures and considering data inconsistencies when processing and interpreting UAV-based thermal infrared data and derived orthomosaics. Full article

Soil moisture plays a crucial role in various environmental processes and is essential for agricultural management, hydrological modeling, and climate studies. Synthetic Aperture Radar (SAR) remote sensing presents significant potential for estimating soil moisture due to its ability to operate in all weather conditions and provide day-and-night imaging capabilities. Among the SAR configurations, the Compact Polarimetric (CP) mode has gained increasing interest as it relaxes system constraints, improves coverage, and enhances target information compared to conventional dual polarimetric SAR systems. This paper introduces a novel approach for soil moisture retrieval utilizing machine learning algorithms and CP SAR features. The CP SAR features are derived from a series of RADARSAT Constellation Mission (RCM) CP SAR imagery acquired over Canadian experimental sites equipped with Real-Time In Situ Soil Monitoring for Agriculture (RISMA) stations. This study employs a diverse dataset of compact polarimetric SAR features and corresponding ground truth soil moisture measurements for training and validation purposes. The results of our study achieved a Root Mean Square Error (RMSE) of 6.88% with a coefficient of determination R² equal to 0.60, which corresponds to a correlation R between true and predicted soil moisture values of 0.75, using optimized Ensemble Learning Regression (ELR) with a decision-tree-based model. These results improved, yielding an RMSE of 5.67% and an R² equal to 0.73 (R = 0.85), using an optimized Gaussian Process Regression (GPR) model. Full article

Satellite-derived bathymetry (SDB) techniques are increasingly valuable for deriving high-quality bathymetric maps of coral reefs. Investigating the performance of the related SDB algorithms in purely spaceborne active–passive fusion bathymetry contributes to formulating reliable bathymetric strategies, particularly for areas such as the Spratly Islands, where in situ observations are exceptionally scarce. In this study, we took Anda Reef as a case study and evaluated the performance of eight common SDB approaches by integrating Sentinel-2 images with Ice, Cloud, and Land Elevation Satellite-2 (ICESat-2). The bathymetric maps were generated using two classical and six machine-learning algorithms, which were then validated with measured sonar data. The results illustrated that all models accurately estimated the depth of coral reefs in the 0–20 m range. The classical algorithms (Lyzenga and Stumpf) exhibited a mean absolute error (MAE), root mean square error (RMSE), and mean absolute percentage error (MAPE) of less than 0.990 m, 1.386 m, and 11.173%, respectively. The machine learning algorithms generally outperformed the classical algorithms in accuracy and bathymetric detail, with a coefficient of determination (R²) ranging from 0.94 to 0.96 and an RMSE ranging from 1.034 m to 1.202 m. The multilayer perceptron (MLP) achieved the highest accuracy and consistency with an RMSE of as low as 1.034 m, followed by the k-nearest neighbor (KNN) (1.070 m). Our results provide a practical reference for selecting SDB algorithms to accurately obtain shallow water bathymetry in subsequent studies. Full article

Due to the constrained processing capabilities of real-time detection techniques in remote sensing applications, it is often difficult to obtain detection results with high accuracy in practice. To address this problem, we introduce a new real-time anomaly detection algorithm for hyperspectral images called cloud–edge RX (CE-RX). The algorithm combines the advantages of cloud and edge computing. During the data acquisition process, the edge performs real-time detection on the data just captured to obtain a coarse result and find the suspicious anomalies. At regular intervals, the suspicious anomalies are sent to the cloud for further detection with a highly accurate algorithm, then the cloud sends back the (high-accuracy) results to the edge for information updating. After receiving the results from the cloud, the edge updates the information of the detector in the real-time algorithm to improve the detection accuracy of the next acquired piece of data. Our experimental results demonstrate that the proposed cloud–edge collaborative algorithm can obtain more accurate results than existing real-time detection algorithms. Full article

With satellite quantity and quality development in recent years, remote sensing products in vast areas are becoming widely used in more and more fields. The acquisition of large regional images requires the scientific and efficient utilization of satellite resources through imaging satellite task planning technology. However, for imaging satellite task planning in a vast area, a large number of decision variables are introduced into the imaging satellite task planning model, making it difficult for existing optimization algorithms to obtain reliable solutions. This is because the search space of the solution increases the exponential growth with the increase in the number of decision variables, which causes the search performance of optimization algorithms to decrease significantly. This paper proposes a large-scale multi-objective optimization algorithm based on efficient competition learning and improved non-dominated sorting (ECL-INS-LMOA) to efficiently obtain satellite imaging schemes for large areas. ECL-INS-LMOA adopted the idea of two-stage evolution to meet the different needs in different evolutionary stages. In the early stage, the proposed efficient competitive learning particle update strategy (ECLUS) and the improved NSGA-II were run alternately. In the later stage, only the improved NSGA-II was run. The proposed ECLUS guarantees the rapid convergence of ECL-INS-LMOA in the early evolution by accelerating particle update, introducing flight time, and proposing a binary competitive swarm optimizer BCSO. The results of the simulation imaging experiments on five large areas with different scales of decision variables show that ECL-INS-LMOA can always obtain the imaging satellite mission planning scheme with the highest regional coverage and the lowest satellite resource consumption within the limited evaluation times. The experiments verify the excellent performance of ECL-INS-LMOA in solving vast area mapping planning problems. Full article

Historical maps represent a unique and irreplaceable source of information about the history of a country, be it large (historical) regions, individual geomorphological units or specifically defined sites. Using a methodologically correct, critical historical analysis, old maps provide both the horizontal and vertical analysis of a landscape and its transformation in different time periods. These maps represent some of the oldest, but relatively easily accessible, historical pictorial documents (plausibly) depicting historical landscapes. This study provides the methodology for processing and georeferencing old mine maps with the possibility of their further use for the purposes of mining tourism. The 1696 Marsigli mine map has been chosen for the case study in question. It depicts a cross-section of the copper mines in Smolník and shows in detail the process of cementation water mining. Through an analysis and a detailed study, two-dimensional parts of a georeferenced historical map have been plotted in Google Earth’s three-dimensional space. Full article

A tropical cyclone is a significant natural phenomenon that results in substantial socio-economic and environmental damage. These catastrophes impact millions of people every year, with those who live close to coastal areas being particularly affected. With a few coastal cities with large population densities, Tamil Nadu’s coast is the third-most cyclone-prone state in India. This study involves the generation of a cyclone risk map by utilizing four distinct components: hazards, exposure, vulnerability, and mitigation. The study employed a Geographical Information System (GIS) and an Analytical Hierarchical Process (AHP) technique to compute an integrated risk index considering 16 spatial variables. The study was validated by the devastating cyclone GAJA in 2018. The resulting risk assessment shows the cyclone risk is higher in zones 1 and 2 in the study area and emphasizes the variations in mitigation impact on cyclone risk in zones 4 and 5. The risk maps demonstrate that low-lying areas near the coast, comprising about 3%, are perceived as having the adaptive capacity for disaster mitigation and are at heightened risk from cyclones regarding population and assets. The present study can offer valuable guidance for enhancing natural hazard preparedness and mitigation measures in the coastal region of Tamil Nadu. Full article

The evaluation of satellite soil moisture is a big challenge owing to the large spatial mismatch between pixel-based satellite soil moisture products and point-based in situ measurements. Upscaling in situ measurements to obtain the “true value” of soil moisture content at the satellite grid/footprint scale can make up for the scale difference and improve the validation. Many existing upscaling methods have strict requirements regarding the spatial distribution and quantity of soil moisture sensors. However, in reality, soil-moisture-monitoring networks are commonly sparse with low sensor density, which increases the difficulty of obtaining accurate upscaled soil moisture data and limits the validation of satellite products. For this reason, this paper proposes a scheme to upscale in situ measurements using five machine learning methods along with Landsat 8 datasets and DEM data to validate the accuracy of a SMAP-enhanced passive soil moisture product for a sparse network on the Qinghai–Tibet Plateau. The proposed scheme realizes the upscaling of in situ soil moisture data to the pixel scale (30 m × 30 m) and then to the coarse grid scale (9 km × 9 km) by using multi-source remote sensing data as the bridge of scale conversion. The long-time SMAP SM products since April 2015 on the Qinghai–Tibet Plateau were validated based on upscaled soil moisture data. The results show that (1) random forest regression performs the best, and the upscaled soil moisture data reflect the region-average soil moisture conditions that can be used for evaluating SMAP data; (2) the SMAP product meets its scientific measurement requirements; and (3) the SMAP product generally underestimates the soil moisture in the study area. Full article

Agricultural intensification practices have been adopted in the Brazilian savanna (Cerrado), mainly in the transition between Cerrado and the Amazon Forest, to increase productivity while reducing pressure for new land clearing. Due to the growing demand for more sustainable practices, more accurate information on geospatial monitoring is required. Remote sensing products and artificial intelligence models for pixel-by-pixel classification have great potential. Therefore, we developed a methodological framework with spectral indices (Normalized Difference Vegetation Index (NDVI), Normalized Difference Water Index (NDWI), and Soil-Adjusted Vegetation Index (SAVI)) derived from the Harmonized Landsat Sentinel-2 (HLS) and machine learning algorithms (Random Forest (RF), Artificial Neural Networks (ANNs), and Extreme Gradient Boosting (XGBoost)) to map agricultural intensification considering three hierarchical levels, i.e., temporary crops (level 1), the number of crop cycles (level 2), and the crop types from the second season in double-crop systems (level 3) in the 2021–2022 crop growing season in the municipality of Sorriso, Mato Grosso State, Brazil. All models were statistically similar, with an overall accuracy between 85 and 99%. The NDVI was the most suitable index for discriminating cultures at all hierarchical levels. The RF-NDVI combination mapped best at level 1, while at levels 2 and 3, the best model was XGBoost-NDVI. Our results indicate the great potential of combining HLS data and machine learning to provide accurate geospatial information for decision-makers in monitoring agricultural intensification, with an aim toward the sustainable development of agriculture. Full article

The Sendai Framework for Disaster Risk Reduction 2015–2030 (SFDRR) proposed seven targets comprising 38 quantified indicators and various sub-indicators to monitor the progress of disaster risk and loss reduction efforts. However, challenges persist regarding the availability of disaster-related data and the required resources to address data gaps. A promising way to address this issue is the utilization of Earth observation (EO). In this study, we proposed an EO-based disaster evaluation framework in service of the SFDRR and applied it to the context of tropical cyclones (TCs). We first investigated the potential of EO in supporting the SFDRR indicators, and we then decoupled those EO-supported indicators into essential variables (EVs) based on regional disaster system theory (RDST) and the TC disaster chain. We established a mapping relationship between the measurement requirements of EVs and the capabilities of EO on Google Earth Engine (GEE). An end-to-end framework that utilizes EO to evaluate the SFDRR indicators was finally established. The results showed that the SFDRR contains 75 indicators, among which 18.7% and 20.0% of those indicators can be directly and indirectly supported by EO, respectively, indicating the significant role of EO for the SFDRR. We provided four EV classes with nine EVs derived from the EO-supported indicators in the proposed framework, along with available EO data and methods. Our proposed framework demonstrates that EO has an important contribution to supporting the implementation of the SFDRR, and that it provides effective evaluation solutions. Full article

We applied teleseismic tomography to investigate the 3D P-wave velocity (Vp) structure of the crust and upper mantle at depths of 50–400 km beneath the Yarlung–Tsangpo suture (YTS), by using 6164 P-wave relative travel-time residuals collected from 495 teleseismic events recorded at 20 three-component broadband seismograms. A modified multi-channel cross-correlation method was adopted to automatically calculate the relative arrival-time residuals of all teleseismic events, which significantly improved the efficiency and precision of the arrival-time data collection. Our results show that alternating low- and high-Vp anomalies are visible beneath the Himalayan and Lhasa blocks across the YTS, indicating that strong lateral heterogeneities exist beneath the study region. A significant high-Vp zone is visible beneath the southern edge of the Lhasa block at 50–100 km depths close to the YTS, which might indicate the rigid Tibetan lithosphere basement. There exists a prominent low-Vp zone beneath the Himalayan block to the south of the YTS extending to ~150 km depth, which might be associated with the fragmentation of the underthrusting Indian continental lithosphere (ICL) and induce localized upwelling of asthenospheric materials from the upper mantle. In addition, significant low-Vp anomalies were observed beneath the Yadong–Gulu rift and the Cona–Sangri rift extending to ~300 km depth, indicating that the tearing of the subducted ICL might provide pathways for the localized asthenospheric materials upwelling, which contributes to the widespread distribution of north–south trending rifts and geothermal activities in southern Tibet. Full article

Normalized difference vegetation index (NDVI) time series data, derived from optical images, play a crucial role for crop mapping and growth monitoring. Nevertheless, optical images frequently exhibit spatial and temporal discontinuities due to cloudy and rainy weather conditions. Existing algorithms for reconstructing NDVI time series using multi-source remote sensing data still face several challenges. In this study, we proposed a novel method, an enhanced gap-filling and Whittaker smoothing (EGF-WS), to reconstruct NDVI time series (EGF-NDVI) using Google Earth Engine. In EGF-WS, NDVI calculated from MODIS, Landsat-8, and Sentinel-2 satellites were combined to generate high-resolution and continuous NDVI time series data. The MODIS NDVI was employed as reference data to fill missing pixels in the Sentinel–Landsat NDVI (SL-NDVI) using the gap-filling method. Subsequently, the filled NDVI was smoothed using a Whittaker smoothing filter to reduce residual noise in the SL-NDVI time series. With reference to the all-round performance assessment (APA) metrics, the performance of EGF-WS was compared with the conventional gap-filling and Savitzky–Golay filter approach (GF-SG) in Fusui County of Guangxi Zhuang Autonomous Region. The experimental results have demonstrated that the EGF-WS can capture more accurate spatial details compared with GF-SG. Moreover, EGF-NDVI of Fusui County exhibited a low root mean square error (RMSE) and a high coefficient of determination (R²). In conclusion, EGF-WS holds significant promise in providing NDVI time series images with a spatial resolution of 10 m and a temporal resolution of 8 days, thereby benefiting crop mapping, land use change monitoring, and various ecosystems, among other applications. Full article

Terrain significantly influences the physical processes and human activities occurring on the Earth’s surface, especially in mountainous areas. The classification and clarification of topographic structures are essential for the quantitative analysis of surface patterns. In this paper, we propose a new method based on the digital elevation model to classify the binary terrain structure. The slope accumulation is constructed to emphasize the accumulated topographic characteristics and is applied to support the segmenting process. The results show that this new method is efficient in increasing the completeness of the segmented results and reducing the classification uncertainty. We verify this method in three areas in South America, North America and Asia to evaluate the method’s robustness. Comparison experiments suggest that this new method outperforms the traditional method in areas with different landforms. In addition, quantitative indices are calculated based on the segmented results. The results indicate that the binary terrain structure benefits the understanding of surface patterns from the perspectives of topographic characteristics, category composition, object morphology and landform spatial distribution. We also assess the transferability of the proposed method, and the results suggest that this method is transferable to different digital elevation models. The proposed method can support the quantitative analysis of land resources, especially in mountainous areas and benefit land management. Full article

The landslide early warning system (LEWS) relies on various models for data processing, prediction, forecasting, and warning level discrimination. The potential different programming implementations and dependencies of these models complicate the deployment and integration of LEWS. Moreover, the coupling between LEWS and models makes it hard to modify or replace models rapidly and dynamically according to changes in business requirements (such as updating the early warning business process, adjusting the model parameters, etc.). This paper proposes a framework for dynamic management and integration of models in LEWS by using WebAPIs and Docker to standardize model interfaces and facilitate model deployment, using Kubernetes and Istio to enable microservice architecture, dynamic scaling, and high availability of models, and using a model repository management system to manage and orchestrate model-related information and application processes. The results of applying this framework to a real LEWS demonstrate that our approach can support efficient deployment, management, and integration of models within the system. Furthermore, it provides a rapid and feasible implementation method for upgrading, expanding, and maintaining LEWS in response to changes in business requirements. Full article

As UAV technology has been leaping forward, small consumer-grade UAVs equipped with optical sensors are capable of easily acquiring high-resolution images, which show bright prospects in a wide variety of terrains and different fields. First, the crater rim landscape of the Dinosaur Valley ring formation located on the central Yunnan Plateau served as the object of the surface change detection experiment, and two repetitive UAV ground observations of the study area were performed at the same altitude of 180 m with DJI Phantom 4 RTK in the rainy season (P1) and the dry season (P2). Subsequently, the UAV-SfM digital three-dimensional (3D) modeling method was adopted to build digital models of the study area at two points in time, which comprised the Digital Surface Model (DSM), Digital Orthomosaic Model (DOM), and Dense Image Matching (DIM) point cloud. Lastly, a quantitative analysis of the surface changes at the pit edge was performed using the point-surface-body surface morphological characterization method based on the digital model. As indicated by the results, (1) the elevation detection of the corresponding check points of the two DSM periods yielded a maximum positive difference of 0.2650 m and a maximum negative value of −0.2279 m in the first period, as well as a maximum positive difference of 0.2470 m and a maximum negative value of −0.2589 m in the second period. (2) In the change detection of the two DOM periods, the vegetation was 9.99% higher in the wet season than in the dry season in terms of coverage, whereas the bare soil was 10.54% more covered than the wet season. (3) In general, the M3C2-PM distances of the P1 point cloud and the P2 point cloud were concentrated in the interval (−0.2,0.2), whereas the percentage of the interval (−0.1,0) accounted for 26.69% of all intervals. The numerical model of UAV-SfM was employed for comprehensive change detection analysis. As revealed by the result of the point elevation difference in the constant area, the technique can conform to the requirements of earth observation with certain accuracy. The change area suggested that the test area can be affected by natural conditions to a certain extent, such that the multi-source data can be integrated to conduct more comprehensive detection analysis. Full article

Seabed sediment classification is of great significance in acoustic remote sensing. To accurately classify seabed sediments, big data are needed to train the classifier. However, acquiring seabed sediment information is expensive and time-consuming, which makes it crucial to design a well-performing classifier using small-sample seabed sediment data. To avoid data shortage, a self-attention generative adversarial network (SAGAN) was trained for data augmentation in this study. SAGAN consists of a generator, which generates data similar to the real image, and a discriminator, which distinguishes whether the image is real or generated. Furthermore, a new classifier for seabed sediment based on self-attention densely connected convolutional network (SADenseNet) is proposed to improve the classification accuracy of seabed sediment. The SADenseNet was trained using augmented images to improve the classification performance. The self-attention mechanism can scan the global image to obtain global features of the sediment image and is able to highlight key regions, improving the efficiency and accuracy of visual information processing. The proposed SADenseNet trained with the augmented dataset had the best performance, with classification accuracies of 92.31%, 95.72%, 97.85%, and 95.28% for rock, sand, mud, and overall, respectively, with a kappa coefficient of 0.934. The twelve classifiers trained with the augmented dataset improved the classification accuracy by 2.25%, 5.12%, 0.97%, and 2.64% for rock, sand, mud, and overall, respectively, and the kappa coefficient by 0.041 compared to the original dataset. In this study, SAGAN can enrich the features of the data, which makes the trained classification networks have better generalization. Compared with the state-of-the-art classifiers, the proposed SADenseNet has better classification performance. Full article

The kinetic features of a slow-moving landslide situated above the Wudongde hydropower station were analyzed using particle flow code 3D (PFC3D) software. This research was based on geological investigations, remote sensing interpretation, and digital elevation models to build the structure of the Jinpingzi landslide. Finite element analysis (FEM) was used to determine the sliding surface. Strength reduction theory (SRT) and particle flow code coupling were used to invert the macro-strength parameters into micro-strength parameters. Finally, the slope failure process was simulated. Meanwhile, the displacement vector angle (DVA) and velocity were used for stability analysis. The simulation results of the kinetic features of slow-moving landslides show that the initial stage begins with accelerated movement, followed by constant-velocity movement and instability failure. The larger the reduction coefficient is, the shorter the duration of each stage is. A two-parameter instability criterion is proposed based on velocity, DVA, and reduction coefficient. Using this criterion, the critical velocity was 200 mm/s, and the critical DVA was 28.15°. The analysis results agree with the actual field monitoring results and motion process. This work confirms that the PFC3D modeling method is suitable for simulating the motion features of landslides. Full article