Sentinel-1 Research Articles

A Copernicus-based evapotranspiration dataset at 100 m spatial resolution over four Mediterranean basins

Abstract. Evapotranspiration (ET) is responsible for regulating the hydrological cycle, with a relevant impact on air humidity and precipitation that is particularly important in the context of acute drought events in recent years. With the intensification of rainfall deficits and extreme heat events, the Mediterranean region requires regular monitoring to enhance water resource management. Even though remote sensing provides spatially continuous information for estimating ET on large scales, existing global products with spatial resolutions ≥ 0.5 km are insufficient for capturing spatial detail at a local level. In the framework of ESA's 4DMED-Hydrology project, we generate an ET dataset at both high spatial and high temporal resolutions using the Priestley–Taylor Two-Source Energy Balance (TSEB-PT) model driven by Copernicus satellite data. We build an automatic workflow to generate a 100 m ET product by combining data from Sentinel-2 (S2) MultiSpectral Instrument (MSI) and Sentinel-3 (S3) land surface temperature (LST) with ERA5 climate reanalysis derived within the period 2017–2021 over four Mediterranean basins in Italy, Spain, France, and Tunisia (Po, Ebro, Hérault, and Medjerda). First, original S2 data are pre-processed before deriving 100 m inputs for the ET estimation. Next, biophysical variables, like leaf area index and fractional vegetation cover, are generated, and then they are temporally composited within a 10 d window according to S3 acquisitions. Consequently, decadal S2 mosaics are used to derive the remaining TSEB-PT inputs. In parallel, we sharpen 1 km S3 by exploiting the dependency between coarse-resolution LST and 100 m S2 reflectances using a decision tree algorithm. Afterwards, climate forcings are utilized to model energy fluxes and then for daily ET retrieval. The daily ET composites demonstrate reasonable TSEB-PT estimates. Based on the validation results against eight eddy covariance (EC) towers between 2017 and 2021, the model predicts 100 m ET with an average RMSE of 1.38 mm d−1 and a Pearson coefficient equal to 0.60. Regardless of some constraints mostly related to the high complexity of EC sites, TSEB-PT can effectively estimate 100 m ET, which opens up new opportunities for monitoring the hydrological cycle on a regional scale. The full dataset is freely available at https://doi.org/10.48784/b90a02d6-5d13-4acd-b11c-99a0d381ca9a, https://doi.org/10.48784/fb631817-189f-4b57-af6a-38cef217bad3, https://doi.org/10.48784/70cd192c-0d46-4811-ad1d-51a09734a2e9, and https://doi.org/10.48784/7abdbd94-ddfe-48df-ab09-341ad2f52e47 for the Ebro, Hérault, Medjerda, and Po catchments, respectively (Bartkowiak et al., 2023a–d).

Estimation of Urban Tree Chlorophyll Content and Leaf Area Index Using Sentinel-2 Images and 3D Radiative Transfer Model Inversion

Urban trees play an important role in mitigating effects of climate change and provide essential ecosystem services. However, the urban environment can stress trees, requiring the use of effective monitoring methods to assess their health and functionality. The objective of this study, which focused on four deciduous tree species in Rennes, France, was to evaluate the ability of hybrid inversion models to estimate leaf chlorophyll content (LCC), leaf area index (LAI), and canopy chlorophyll content (CCC) of urban trees using eight Sentinel-2 (S2) images acquired in 2021. Simulations were performed using the 3D radiative transfer model DART, and the hybrid inversion models were developed using machine-learning regression algorithms (random forest (RF) and gaussian process regression). Model performance was assessed using in situ measurements, and relations between satellite data and in situ measurements were investigated using spatial allocation (SA) methods at the pixel and tree scales. The influence of including environment features (EFs) as model inputs was also assessed. The results indicated that random forest models that included EFs and used the pixel-scale SA method were the most accurate with R2 values of 0.33, 0.29, and 0.46 for LCC, LAI, and CCC, respectively, with notable variability among species.

Incidence Angle Normalization of C-Band Radar Backscattering Coefficient over Agricultural Surfaces Using Dynamic Cosine Method

The radar-backscattering coefficient (σ0) depends on surface characteristics and instrumental parameters (wavelength, polarization, and incidence angle). For Sentinel-1 (S1), with incidence angles ranging from 25° to 45°, σ0 for similar targets typically differs by a few dB depending on their localization in the S1 swath. Overcoming this angular dependence is crucial for the operational applications of radar data. In theory, σ0 follows a cosine function with an exponent “N” that represents the degree of dependence between σ0 and the incidence angle. In order to reduce the effect of the incidence angle on σ0, dynamic N normalizations based on vegetation descriptors, NDVI and SAR Ratio (VV/VH), were applied and then compared to the results obtained with temporally fixed N normalizations. N was estimated at each S1 date during the period of the study for three main summer crops: corn, soybean, and sunflower. Analysis shows that the angular dependence of the S1 σ0 is similar for all three crops. N varies from 3.0 for low NDVI values to 2.0 for high NDVI values (stage of maximal vegetation development) in the VV polarization and from 2.5 to 1.5 for the VH polarization. Furthermore, N fluctuates strongly during the periods before plant emergence and after harvesting, due to variations in the soil roughness. Finally, the results demonstrated that the dynamic normalization of σ0 significantly reduces its angular dependence compared to fixed N (N = 1 and N = 2), with SAR ratio-based normalization performing similarly to NDVI-based normalization.

A multi-source approach to mapping habitat diversity: Comparison and combination of single-date hyperspectral and multi-date multispectral satellite imagery in a Mediterranean Natural Reserve

The increasing availability of spaceborne hyperspectral satellite imagery opens new opportunities for forest habitat mapping and monitoring, but the limitation of its generally low temporal resolution must be considered. In this study, we compare the ability of single-date PRISMA (PRecursore IperSpettrale della Missione Applicativa), the hyperspectral satellite from the Italian Space Agency, with that of both single-date and multi-date Sentinel-2 (S2) and PlanetScope (PS) to detect and correctly classify various EUNIS habitat types distributed over a relatively small spatial extent (6000 ha) in a natural reserve in Central Italy. The case study deals with multiple levels of spectral similarity, as the dominant canopy species of the target forest habitat classes belong to the same genus (Quercus spp., both deciduous and evergreen species) as well as of different taxa (Pinus and Fraxinus spp.). We performed a pixel-based classification with the Random Forest algorithm using a set of 28 spectral indices computed on PRISMA bands, 22 on S2, and 12 on PS. A Canopy Height Model (CHM) was also used as an input variable for the classification. Our results showed that PRISMA considerably outperforms the two multispectral satellites in single-date classifications, with an overall accuracy of 84 % compared to PlanetScope's 69 % and Sentinel-2's 72 %. Regarding the comparison between multi-date multispectral and single-date hyperspectral, 10-fold cross-validation results revealed that S2 achieves an out-of-bag error rate of approximately 16 %, while PRISMA achieves 17 % and PS 19 %. This demonstrates that a combination of spectral indices calculated during the growing season can capture phenological or physiological differences among the target species, which consequently results in a significant improvement in the classification accuracy of the multispectral sensors. Ultimately, classification results from all three sensors were combined to create probability maps for each forest class, identifying areas classified with a higher degree of certainty by each satellite tested and potentially contributing to forest management by defining areas with varying conservation levels.

Crop cover identification based on different vegetation indices by using machine learning algorithms

In this article, three different indices NDVI (Normalized Difference Vegetation Index), BNDVI (Blue Normalized Difference Vegetation Index) and GNDVI (Green Normalized Difference Vegetation Index) are used for the identification of wheat, mustard and sugarcane crop of Saharanpur district’s region of Uttar Pradesh. Sentinel 2B satellite images are collected from October 02, 2018 to April 15, 2019. These images are processed using Google Earth Engine. These sentinel images are used to generate NDVI, BNDVI and GNDVI images using GEE. These three different indices images are further processed using SNAP software and particular indices values for 210 different locations are calculated. The same process is used for calculating BNDVI and GNDVI values. ARIMA, LSTM and Prophet models are used to train the time series indices values (NDVI, BNDVI and GNDVI) of wheat, mustard and sugarcane crop. these models are used to analyse MSE (mean absolute percentage error) and RMSE values by considering various parameters. Using ARIMA Model, for wheat crop GNDVI indices shows minimum RMSE 0.020, For Sugarcane crop NDVI indices shows minimum RMSE 0.053, For Mustard crop GNDVI indices shows minimum RMSE 0.024. Using LSTM model, for wheat crop NDVI indices shows minimum RMSE 0.036, For Sugarcane crop BNDVI indices shows minimum RMSE 0.054, For Mustard crop GNDVI indices shows minimum RMSE 0.026. Using Prophet model, for wheat crop GNDVI indices shows minimum RMSE 0.055, For Sugarcane crop NDVI indices shows minimum RMSE 0.088, For Mustard crop GNDVI indices using Prophet model shows minimum RMSE 0.101.

Landscape transition-induced ecological risk modeling using GIS and remote sensing techniques: a case of Saint Martin Island, Bangladesh.

Uncontrolled human activity and nature are causing the deterioration of Saint Martin Island, Bangladesh's only tropical island, necessitating sustainable land use strategies and ecological practices. Therefore, the present study measures the land use/cover transition from 1974 to 2021, predicts 2032 and 2042, and constructs the spatiotemporal features of the Landscape Ecological Risk Index based on land use changes. The study utilized Maximum Likelihood Classification (MLC) on Landsat images from 1974, 1988, 2001, 2013, and Sentinel 2B in 2021, achieving ≥ 80% accuracy. The MLP-MC approach was also used to predict 2032 and 2042 LULC change patterns. The eco-risk index was developed using landscape disturbance and vulnerability indices, Bayesian Kriging interpolation, and spatial autocorrelations to indicate spatial clustering. The research found that settlements increased from 2.06 to 28.62ha between 1974 and 2021 and would cover 41.22ha in 2042, causing considerable losses in agricultural areas, waterbodies, sand, coral reefs, and vegetation. The area under study showed a more uniform and homogenous environment as Shannon's diversity and evenness scores decreased. The ecological risk of Saint Martin Island increased from 4.31 to 31.05ha between 1974 and 2042 due to natural and human factors like erosion, tidal bores, population growth, coral mining, habitat destruction, and intensive agricultural practices and tourism, primarily in Nazrul Para, Galachipa, and Western Dakhin Para. The findings will benefit St. Martin Island stakeholders and policymakers by providing insights into current and potential landscape changes and land eco-management.

FBA-DPAttResU-Net: Forest burned area detection using a novel end-to-end dual-path attention residual-based U-Net from post-fire Sentinel-1 and Sentinel-2 images

Forest burned area (FBA) detection using remote sensing (RS) data is critical for timely forest management and recovery attempts after wildfires. This study introduces a dual-path attention residual-based U-Net (DPAttResU-Net), a novel end-to-end deep learning (DL) model tailored for FBA detection using dual-source post-fire Sentinel-1 (S1) and Sentinel-2 (S2) satellite RS imagery. To better distinguish FBAs from other land cover types, DPAttResU-Net incorporates a dual-pathway structure to exploit complementary geometrical/physical and spectral features from S1 and S2, respectively. An integral component in the proposed architecture is the channel-spatial attention residual (CSAttRes) block, which emphasizes salient features through the channel and spatial attention modules, thus improving the burned area feature representation. To compare DPAttResU-Net to state-of-the-art DL models, experiments were conducted on benchmark FBA datasets collected over 12 areas, where ten datasets were used as training data and two datasets were used to test the trained DL models. The experimental results demonstrate the high proficiency of the proposed deep model in meticulously delineating FBAs. In further detail, DPAttResU-Net, with a PFN of 17.96 (%) in the first case and an IoU of 89.31 (%) in the second case, outperformed the existing U-Net-based models. Accordingly, through dual-path integration and attention mechanisms, DPAttResU-Net contributes to accurately identifying FBAs by preserving their geometrical details, making it a promising tool for post-wildfire forest management.

Application of PS-InSAR and Diagnostic Train Measurement Techniques for Monitoring Subsidence in High-Speed Railway in Konya, Türkiye

Large-scale man-made linear structures like high-speed railway lines have become increasingly important in modern life as a faster and more comfortable transportation option. Subsidence or longitudinal levelling deformation problems along these railway lines can prevent the line from operating effectively and, in some cases, require speed reduction, continuous maintenance or repairs. In this study, the longitudinal levelling deformation of the high-speed railway line passing through Konya province (Central Turkey) was analyzed for the first time using the Persistent Scatter Synthetic Aperture Radar Interferometry (PS-InSAR) technique in conjunction with diagnostic train measurements, and the correlation values between them were found. In order to monitor potential levelling deformation along the railway line, medium-resolution, free-of-charge C-band Sentinel-1 (S-1) data and high-resolution, but paid, X-band Cosmo-SkyMed (CSK) Synthetic Aperture Radar (SAR) data were analyzed from the diagnostic train and reports received from the relevant maintenance department. Comparison analyses of the results obtained from the diagnostic train and radar measurements were carried out for three regions with different deformation scenarios, selected from a 30 km railway line within the whole analysis area. PS-InSAR measurements indicated subsidence events of up to 40 mm/year along the railway through the alluvial sediments of the Konya basin, which showed good agreement with the diagnostic train. This indicates that the levelling deformation of the railway and its surroundings can be monitored efficiently, rapidly and cost-effectively using the InSAR technique.

An Algorithm to Retrieve Range Ocean Current Speed under Tropical Cyclone Conditions from Sentinel-1 Synthetic Aperture Radar Measurements Based on XGBoost

In this study, a novel algorithm to retrieve the current speed along the range direction under extreme sea states is developed from C-band synthetic aperture radar imagery. To this aim, a Sentinel-1 (S-1) dual-polarized synthetic aperture radar (SAR) dataset consisting of 2300 images is collected during 200 tropical cyclones (TCs). The dataset is complemented with collocated wave simulations from the Wavewatch-III (WW3) model and reanalysis currents from the HYbrid Coordinate Ocean Model (HYCOM). The corresponding TC winds are officially released by IFRMER, while the Stokes drift following the wave propagation direction is estimated from the waves simulated by WW3. In this study, first the dependence of wind, Stokes drift, and range current on the Doppler centroid anomaly is investigated, and then the extreme gradient boosting (XGBoost) machine learning model is trained on 87% of the S-1 dataset for range current retrieval purposes. The rest of the dataset is used for testing the retrieval algorithm, showing a root mean square error (RMSE) and a correlation coefficient (r) of 0.11 m/s and 0.97, respectively, with the HYCOM outputs. A validation against measurements collected from two high-frequency (HF) phased-array radars is also performed, resulting in an RMSE and r of 0.12 m/s and 0.75, respectively. Those validation results are better than the 0.22 m/s RMSE and 0.28 r achieved by the empirical CDOP model. Hence, the experimental results confirm the soundness of the XGBoost, exhibiting a certain improvement over the empirical model.

Spatio-temporal assessment of land use and land cover dynamics in Urmia lake basin of Iran: A bi-directional approach using optical and radar data on the Google Earth Engine platform

Sustainable development, a cornerstone in responsible land resource management, occupies a critical role in global efforts to balance economic progress with ecological preservation. This research explores the intricate dynamics of sustainable development and land resource management in the Lake Urmia watershed, northwestern Iran, with a specific focus on Land Use and Land Cover (LULC) alterations. Leveraging cutting-edge methodologies within the Google Earth Engine (GEE) framework, the study employs the Random Forest (RF) model, and multi-sensor satellite data to achieve meticulous LULC classification from the years 2016 to 2020.This strategy incorporates satellite images from Sentinel-1 (S1), Sentinel-2 (S2), coupled with ancillary data, and the implementation of the RF algorithm. It highlighted the intricate synergy between optical and Synthetic Aperture Radar (SAR) data for LULC classification in the Lake Urmia watershed. The Overall Accuracy (OA) values ranging from 88.28 % to 92.00 % affirmed the robustness of the RF model, demonstrating its potential for research objectives. In addition, Dynamic World, a near real-time global dataset, was applied to the study area, provides a convenient view to detect changes from the years 2016 to 2023, while enabling comparison with the widely used RF algorithm in past studies. Notably, this study goes beyond methodological developments to examine the concrete consequences of the observed changes. The decline in water bodies within the Urmia Lake basin and the parallel expansion of cultivated lands underscore the profound impact of human activities, particularly agricultural practices, on the ecological equilibrium. As we navigate the intricate terrain of sustainable development, this research serves as a clarion call for remote sensing approaches to monitor and manage land resources, emphasizing the delicate balance between economic growth and ecological preservation.

Toward carbon neutral cities: A comparative analysis between Sentinel 2 and WorldView 3 satellite image processing for tree carbon stock mapping in Brussels

Because of the high costs associated with data sources, urban policymakers struggle to employ cost-effective remote sensing methods for evaluating trees and their potential contributions to atmospheric Carbon Stock (CS). While free data sources like Copernicus Sentinel satellite data could be explored, there are a few studies illustrating its potential for mapping urban tree C. Here, the Sentinel 2 (S2)-derived Normalized Difference Vegetation Index (NDVI) was used to model CS for street trees in Brussels. In parallel, the WorldView 3 (WV3)-derived NDVI layer was also used for a similar study area to compare the CS mapping outcomes regarding dominant tree species. The accuracy level was around 90 % (R²=0.89, r=0.94, and RMSE= 97 kg) in the case of WV3 data, whereas it was about 60 % (R²=0.60, r=0.79, and RMSE = 189.6 kg), even with a coarse resolution regarding the S2 data. This study also shows the strength and scope of using S2 data over WV3 data, illustrating the convenience in terms of accuracy and cost-effectiveness compared to existing methods. The applied methodology could be utilized to monitor urban trees and predict the level of possible carbon sequestration, even considering a larger city like Brussels with a complex agglomeration. It could be a solid additional support for the authorities of European towns and developing countries, especially in terms of being cost-efficient and readily embraced by users.

Assessment of Machine Learning Algorithms for Land Cover Classification in a Complex Mountainous Landscape

Mapping land cover (LC) in mountainous regions, such as the Gilgit-Baltistan (GB) area of Pakistan, presents significant challenges due to complex terrain, limited data availability, and accessibility constraints. This study addresses these challenges by developing a robust, data-driven approach to classify LC using high-resolution Sentinel-2 (S-2) satellite imagery from 2019 within Google Earth Engine (GEE). The research evaluated the performance of various machine learning (ML) algorithms, including classification and regression tree (CART), maximum entropy (gmoMaxEnt), minimum distance (minDistance), support vector machine (SVM), and random forest (RF), without extensive hyperparameter tuning. Additionally, ten different scenarios based on various band combinations of S-2 data were used as input for running the ML models. The LC classification was performed using 2759 sample points, with 70% for training and 30% for validation. The results indicate that the RF algorithm outperformed all other classifiers under scenario S1 (using 10 bands), achieving an overall accuracy (OA) of 0.79 and a kappa coefficient of 0.76. The final RF-based LC mapping shows the following percentage distribution: barren land (46.7%), snow cover (22.9%), glacier (7.9%), grasses (7.2%), water (4.7%), wetland (2.9%), built-up (2.7%), agriculture (1.9%), and forest (1.2%). It is suggested that the best identified RF classifier within the GEE environment should be used for advanced multi-source data image classification with hyperparameter tuning to increase OA. Additionally, it is suggested to build the capacity of various stakeholders in GB for better monitoring of LC changes and resource management using geospatial big data.

Digital mapping of soil quality and salt-affected soil indicators for sustainable agriculture in the Nile Delta region

The study addresses the challenge of sustainable land management, which is crucial for agricultural production and soil quality (SQ), in the face of land degradation that negatively impacts crop production and SQ. The goal of the current work is to assess SQ using digital soil mapping (DSM) in Kafr El-Sheikh province, Egypt, to develop a framework employing two methods for soil quality index (SQI) assessment: the total data set (SQI-TDS) and a selected minimum data set (SQI-MDS) to choose indicators, along with a weighted additive SQI (SQIw), and a Random Forest (RF) model to predict and map the SQI, as well as the salt-affected soil indicators (EC, pH, and ESP). This framework uses remote sensing data: time series of Sentinel-1 (S-1) and Sentinel-2 (S-2) greenest pixel composite. Additionally, we incorporated environmental covariates derived from S-1 and S-2 imagery to understand their influence on SQ, which in turn informs land management practices, land degradation assessment, and crop productivity. The findings reveal a clear negative impact of salinity and alkalinity on SQ. We demonstrate the importance of Variance Inflation Factor (VIF) and Sequential Feature Selection (SFS) techniques for improving the performance of the RF model used for prediction. Notably, the greenest pixel composite imagery proved promising for SQI assessment using DSM beneath vegetation cover, crop mapping, and land-use dynamics. The precise SQI obtained is essential for decision-makers to detect land degradation, develop sustainable agricultural management strategies, and assess their appropriateness for developing plans and strategies to increase agricultural productivity.

Integrating temporal-aggregated satellite image with multi-sensor image fusion for seasonal land-cover mapping of Shilansha watershed, rift valley basin of Ethiopia

Accurate land-cover mapping in regions with frequent cloud-cover and rapidly changing agricultural land cover by crop growth cycles cannot be guaranteed by use of single sensor images, or an image from a single-acquisition-date. This study addressed these challenges by applying temporal-aggregation of single sensor image features that is integrated with multi-sensor image fusion. Results of land-cover classification target fallow, growing, and harvest/post-harvest agricultural seasons. Satellite based features used were frequency bands of Sentinel-1 (S1) and Sentinel-2 (S2), including vegetation indices (VIs) and biophysical variables (BPVs). Temporal aggregation improved classification accuracy. The single-acquisition-date S2 image, overall accuracy (OA) ranged from 0.81 to 0.85, increased to 0.86 to 0.87 after temporal-aggregation. Meanwhile, for single-acquisitions of S1, OA ranged from 0.44 to 0.79 increased to 0.6 to 0.86 across respective seasons. Fusing temporally aggregated S1 and S2 image features including VIs and BPVs increased OA up to 0.90. Selecting 11, 8, and 10 out of 18 optimum numbers of features for fallow, growing, and harvest/post-harvest seasons respectively improved OA by 3%, 2%, and 1.86%. PCA fusion of the temporally aggregated best performing feature set enhanced harvest/post-harvest season, fallow, and growing seasons with OA of 0.98, 0.96 and 0.94 respectively. Accuracy was enhanced when selecting different best performing feature set for the three seasons. The study enhanced knowledge of advanced remote sensing for agricultural land cover mapping, with practical implications of land monitoring and management.

How Phenology Shapes Crop-Specific Sentinel-1 PolSAR Features and InSAR Coherence across Multiple Years and Orbits

Spatial information about plant health and productivity are essential when assessing the progress towards Sustainable Development Goals such as life on land and zero hunger. Plant health and productivity are strongly linked to a plant’s phenological progress. Remote sensing, and since the launch of Sentinel-1 (S1), specifically, radar-based frameworks have been studied for the purpose of monitoring phenological development. This study produces insights into how crop phenology shapes S1 signatures of PolSAR features and InSAR coherence of wheat, canola, sugar beet. and potato across multiple years and orbits. Hereby, differently smoothed time series and a base line of growing degree days are stacked to estimate the patterns of occurrence of extreme values and break points. These patterns are then linked to in situ observations of phenological developments. The comparison of patterns across multiple orbits and years reveals that a single optimized fit hampers the tracking capacities of an entire season monitoring framework, as does the sole reliance on extreme values. VV and VH backscatter intensities outperform all other features, but certain combinations of phenological stage and crop type are better covered by a complementary set of PolSAR features and coherence. With regard to PolSAR features, alpha and entropy can be replaced by the cross-polarization ratio for tracking certain stages. Moreover, a range of moderate incidence angles is better suited for monitoring crop phenology. Also, wheat and canola are favored by a late afternoon overpass. In sum, this study provides insights into phenological developments at the landscape level that can be of further use when investigating spatial and temporal variations within the landscape.

Harmonized Landsat and Sentinel-2 Data with Google Earth Engine

Continuous and dense time series of satellite remote sensing data are needed for several land monitoring applications, including vegetation phenology, in-season crop assessments, and improving land use and land cover classification. Supporting such applications at medium to high spatial resolution may be challenging with a single optical satellite sensor, as the frequency of good-quality observations can be low. To optimize good-quality data availability, some studies propose harmonized databases. This work aims at developing an ‘all-in-one’ Google Earth Engine (GEE) web-based workflow to produce harmonized surface reflectance data from Landsat-7 (L7) ETM+, Landsat-8 (L8) OLI, and Sentinel-2 (S2) MSI top of atmosphere (TOA) reflectance data. Six major processing steps to generate a new source of near-daily Harmonized Landsat and Sentinel (HLS) reflectance observations at 30 m spatial resolution are proposed and described: band adjustment, atmospheric correction, cloud and cloud shadow masking, view and illumination angle adjustment, co-registration, and reprojection and resampling. The HLS is applied to six equivalent spectral bands, resulting in a surface nadir BRDF-adjusted reflectance (NBAR) time series gridded to a common pixel resolution, map projection, and spatial extent. The spectrally corresponding bands and derived Normalized Difference Vegetation Index (NDVI) were compared, and their sensor differences were quantified by regression analyses. Examples of HLS time series are presented for two potential applications: agricultural and forest phenology. The HLS product is also validated against ground measurements of NDVI, achieving very similar temporal trajectories and magnitude of values (R2 = 0.98). The workflow and script presented in this work may be useful for the scientific community aiming at taking advantage of multi-sensor harmonized time series of optical data.

Time Series Prediction of Reservoir Bank Slope Deformation Based on Informer and InSAR: A Case Study of Dawanzi Landslide in the Baihetan Reservoir Area, China

Reservoir impoundment significantly impacts the hydrogeological conditions of reservoir bank slopes, and bank slope deformation or destruction occurs frequently under cyclic impoundment conditions. Ground deformation prediction is crucial to the early warning system for slow-moving landslides. Deep learning methods have developed rapidly in recent years, but only a few studies are on combining deep learning and landslide warning. This paper proposes a slow-moving landslide displacement prediction method based on the Informer deep learning model. Firstly, the Sentinel-1 (S1) data are processed to obtain the cumulative displacement time-series image of the bank slope by the Small-BAseline Subset Interferometric Synthetic Aperture Radar (SBAS-InSAR) method. Then, combining data on rainfall, humidity, and horizontal and vertical distances of pixel points from the water table line, this study created a dataset with landslide displacement as the target feature. After that, this paper improves the Informer model to make it applicable to our dataset. This study chose the Dawanzi landslide in the Baihetan reservoir area, China, for validation. After training with 50-time series deformation data points, the model can predict the displacement results of 12-time series deformation data points using 12-time series multi-feature data, and compared with the monitoring values, its Mean Square Error (MSE) was 11.614. The results show that the multivariate dataset is better than the deformation univariate data in predicting the displacement in the large deformation zone of bank slopes, and our model has better complexity and prediction performance than other deep learning models. The prediction results show that among zones I–IV, where the Dawanzi Tunnel is located, significant deformation with the maximum deformation rate detected exceeding –100mm/year occurs in Zones I and III. In these two zones, the initiation of deformation relates to the drop in water level after water storage, with the deformation rate of Zone III exhibiting a stronger correlation with the change in water level. It is expected that deformation in Zone III will either remain slow or stop, while deformation in Zone I will continue at the same or a decreased rate. Our proposed method for slow-moving landslide displacement forecasting offers fast, intuitive, and economically feasible advantages. It can provide a feasible research idea for future deep learning and landslide warning research.

Mapping reservoir water quality from Sentinel-2 satellite data based on a new approach of weighted averaging: Application of Bayesian maximum entropy

In regions like Oman, which are characterized by aridity, enhancing the water quality discharged from reservoirs poses considerable challenges. This predicament is notably pronounced at Wadi Dayqah Dam (WDD), where meeting the demand for ample, superior water downstream proves to be a formidable task. Thus, accurately estimating and mapping water quality indicators (WQIs) is paramount for sustainable planning of inland in the study area. Since traditional procedures to collect water quality data are time-consuming, labor-intensive, and costly, water resources management has shifted from gathering field measurement data to utilizing remote sensing (RS) data. WDD has been threatened by various driving forces in recent years, such as contamination from different sources, sedimentation, nutrient runoff, salinity intrusion, temperature fluctuations, and microbial contamination. Therefore, this study aimed to retrieve and map WQIs, namely dissolved oxygen (DO) and chlorophyll-a (Chl-a) of the Wadi Dayqah Dam (WDD) reservoir from Sentinel-2 (S2) satellite data using a new procedure of weighted averaging, namely Bayesian Maximum Entropy-based Fusion (BMEF). To do so, the outputs of four Machine Learning (ML) algorithms, namely Multilayer Regression (MLR), Random Forest Regression (RFR), Support Vector Regression (SVRs), and XGBoost, were combined using this approach together, considering uncertainty. Water samples from 254 systematic plots were obtained for temperature (T), electrical conductivity (EC), chlorophyll-a (Chl-a), pH, oxidation–reduction potential (ORP), and dissolved oxygen (DO) in WDD. The findings indicated that, throughout both the training and testing phases, the BMEF model outperformed individual machine learning models. Considering Chl-a, as WQI, and R-squared, as evaluation indices, BMEF outperformed MLR, SVR, RFR, and XGBoost by 6%, 9%, 2%, and 7%, respectively. Furthermore, the results were significantly enhanced when the best combination of various spectral bands was considered to estimate specific WQIs instead of using all S2 bands as input variables of the ML algorithms.

Enhanced Satellite Analytics for Mussel Platform Census Using a Machine-Learning Based Approach

Mussel platforms are big floating structures made of wood (normally about 20 m × 20 m or even a bit larger) that are used for aquaculture. They are used for supporting the growth of mussels in suitable marine waters. These structures are very common near the Galician coastline. For their maintenance and tracking, it is quite convenient to be able to produce a periodic census of these structures, including their current count and position. Images from Earth observation satellites are, a priori, a convenient choice for this purpose. This paper describes an application capable of automatically supporting such a census using optical images taken at different wavelength intervals. The images are captured by the two Sentinel 2 satellites (Sentinel 2A and Sentinel 2B, both from the Copernicus Project). The Copernicus satellites are run by the European Space Agency, and the produced images are freely distributed on the Internet. Sentinel 2 images include thirteen frequency bands and are updated every five days. In our proposal, remote-sensing normalized (differential) indexes are used, and machine-learning techniques are applied to multiband data. Different methods are described and tested. The results obtained in this paper are satisfactory and prove the approach is suitable for the intended purpose. In conclusion, it is worth noting that artificial neural networks turn out to be particularly good for this problem, even with a moderate level of complexity in their design. The developed methodology can be easily re-used and adapted for similar marine environments.

Analysis of Urbanization-Induced Land Subsidence in the City of Recife (Brazil) Using Persistent Scatterer SAR Interferometry

The article addresses anthropogenic and geological conditions related to the development of soil subsidence in the western zone of Recife (Brazil). Over the past 50 years, human activity has intensified in areas previously affected by soft soils (clay, silt, and sandstone) resulting in subsidence due to additional loads (landfills and constructions). The duration of the settlement process can be significantly influenced by the specific characteristics of the soil composition and geological conditions of the location. This work presents, for the first time, accurate InSAR time series maps that describe the spatial pattern and temporal evolution of the settlement, as well as the correlation with the geological profile, and validation with Global Navigation Satellite System (GNSS) data. Persistent Scatterer Interferometry (PS-InSAR) was employed in the analysis of Single Look Complex (SLC) images generated by 100 ascending COSMO-SkyMed (CSK) and 65 PAZ (32 ascending, and 33 descending) from the X-band, along with 135 descending Sentinel-1 (S1) acquisitions from the C-band. These data were acquired over the period from 2011 to 2023. The occurrence of subsidence was identified in several locations within the western region, with the most significant displacement rates observed in the northern, central, and southern areas. In the northern region, the displacement rates were estimated to be approximately −20 mm/year, with the Várzea and Caxangá neighborhoods exhibiting the highest rates. In the central region, the displacement rates were estimated to be approximately −15 mm/year, with the Engenho do Meio, Cordeiro, Torrões, and San Martin neighborhoods exhibiting the highest rates. Finally, in the southern region, the displacement rates were estimated to be up to −25 mm/year, with the Caçote, Ibura, and Ipsep neighborhoods exhibiting the highest rates. Additionally, east–west movements were observed, with velocities reaching up to −7 mm/year toward the west. These movements are related to the lowering of the land. The study highlights that anthropogenic effects in the western zone of Recife contribute to the region’s vulnerability to soil subsidence.