Sentinel-2 Multispectral Instrument Research Articles

Mapping upland crop–rice cropping systems for targeted sustainable intensification in South China

Upland crop-rice cropping systems (UCR) facilitate sustainable agricultural intensification. Accurate UCR cultivation mapping is needed to ensure food security, sustainable water management, and rural revitalization. However, datasets describing cropping systems are limited in spatial coverage and crop types. Mapping UCR is more challenging than crop identification and most existing approaches rely heavily on accurate phenology calendars and representative training samples, which limits its applications over large regions. We describe a novel algorithm (RRSS) for automatic mapping of upland crop–rice cropping systems using Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 Multispectral Instrument (MSI) data. One indicator, the VV backscatter range, was proposed to discriminate UCR and another two indicators were designed by coupling greenness and pigment indices to further discriminate tobacco or oilseed UCR. The RRSS algorithm was applied to South China characterized by complex smallholder rice cropping systems and diverse topographic conditions. This study developed 10-m UCR maps of a major rice bowl in South China, the Xiang-Gan-Min (XGM) region. The performance of the RRSS algorithm was validated based on 5197 ground-truth reference sites, with an overall accuracy of 91.92%. There were 7348 km2 areas of UCR, roughly one-half of them located in plains. The UCR was represented mainly by oilseed-UCR and tobacco-UCR, which contributed respectively 69% and 15% of UCR area. UCR patterns accounted for only one-tenth of rice production, which can be tripled by intensification from single rice cropping. Application to complex and fragmented subtropical regions suggested the spatiotemporal robustness of the RRSS algorithm, which could be further applied to generate 10-m UCR datasets for application at national or global scales.

Synergistic use of Sentinel-2 and UAV-derived data for plant fractional cover distribution mapping of coastal meadows with digital elevation models

Abstract. Coastal wetlands provide a range of ecosystem services, yet they are currently under threat from global change impacts. Thus, their monitoring and assessment is vital for evaluating their status, extent and distribution. Remote sensing provides an excellent tool for evaluating coastal ecosystems, whether with small-scale studies using drones or national-/regional-/global-scale studies using satellite-derived data. This study used a fine-scale plant community classification of coastal meadows in Estonia derived from a multispectral camera on board unoccupied aerial vehicles (UAVs) to calculate the plant fractional cover (PFC) in Sentinel-2 MultiSpectral Instrument (MSI) sensor grids. A random forest (RF) algorithm was trained and tested with vegetation indices (VIs) calculated from the spectral bands extracted from the MSI sensor to predict the PFC. Additional RF models were trained and tested after adding a digital elevation model (DEM). After comparing the models, results show that using DEM with VIs can increase the prediction accuracy of PFC up to 2 times (R2 58 %–70 %). This suggests the use of ancillary data such as DEM to improve the prediction of empirical machine learning models, providing an appropriate approach to upscale local studies to wider areas for management and conservation purposes.

A novel water optical types framework for Chinese inland waters with the application of multitype satellite sensor

ABSTRACT Optical Water Type (OWT) analysis is crucial for comprehending water composition and quality, key factors in assessing water quality over extensive areas. However, China’s inland waters lack a standardized system for such analysis. To quantitatively analyze the classification results, our study compared three K-means clustering methods, for analyzing 1310 spectral data from various Chinese lakes and reservoirs, thereby addressing this gap. The innovative split-merge K-means method identified 13 distinct OWTs that more closely adhere to the principles of minimizing intra-class distance and maximizing inter-class distance. These were categorized into four groups: clear water, turbid water, eutrophic water, and special type water. Additionally, we developed a method based on Spectral Angle Distance (SAD) to evaluate the classification capabilities of 12 satellite sensors. The results show that Sentinel-3 OLCI (Ocean and Land Color Instrument), MERIS (Medium Resolution Imaging Spectrometer), and Sentinel-2 MSI (Multispectral Instrument) have the best water classification capabilities, making them well-suited for large-scale monitoring of OWT changes. Conversely, other sensors, such as the Sustainable Development Scientific Satellite-1 (SDGSAT-1), Landsat-8, GaoFen-6, GaoFen-1, GaoFen-2, Landsat-5, Landsat-7, Moderate Resolution Imaging Spectroradiometer (MODIS), and HuanJing-1, necessitate the consolidation of water types for effective categorization, indicative of their more limited classification capabilities.

A Geographic Object-Based Image Approach Based on the Sentinel-2 Multispectral Instrument for Lake Aquatic Vegetation Mapping: A Complementary Tool to In Situ Monitoring

Aquatic vegetation is an essential component of lake ecosystems, used as a biological indicator for in situ monitoring within the Water Framework Directive. We developed a hierarchical object-based image classification model with multi-seasonal Sentinel-2 imagery and suitable spectral indices in order to map the aquatic vegetation in a Mediterranean oligotrophic/mesotrophic deep lake; we then applied the model to another lake with similar abiotic and biotic characteristics. Field data from a survey of aquatic macrophytes, undertaken on the same dates as EO data, were used within the accuracy assessment. The aquatic vegetation was discerned into three classes: emergent, floating, and submerged aquatic vegetation. Geographic object-based image analysis (GEOBIA) proved to be effective in discriminating the three classes in both study areas. Results showed high effectiveness of the classification model in terms of overall accuracy, particularly for the emergent and floating classes. In the case of submerged aquatic vegetation, challenges in their classification prompted us to establish specific criteria for their accurate detection. Overall results showed that GEOBIA based on spectral indices was suitable for mapping aquatic vegetation in oligotrophic/mesotrophic deep lakes. EO data can contribute to large-scale coverage and high-frequency monitoring requirements, being a complementary tool to in situ monitoring.

A novel linear spectral unmixing-based method for tree decline monitoring by fusing UAV-RGB and optical space-borne data

ABSTRACT Remote sensing-assisted monitoring of forest health entails methods that can provide up-to-date and accurate information on decline and mortality of individual trees, while maintaining time and cost efficiency. However, the trade-off of applying consumer-grade UAV-RGB data as the most affordable and accessible data source at the catchment level is constrained by its poor spectral information content. We developed a method based on the fusion of UAV-RGB data with space-borne Sentinel-2 Multispectral Instrument (MSI) at the level of tree crowns, with the specific target of supporting studies on semi-arid tree decline. We applied linear spectral unmixing (Spectral Unmixing-Based data Fusion method, LSUBF) by considering a limited number of endmembers and calculating the abundances (fractional covers) from the UAV data, and evaluated the results by high-resolution MSI space-borne data including SPOT-6 (1.5 m spatial resolution) and PlanetScope (3 m spatial resolution). This method suggested an increase in the coefficient of determination of the applied generalized additive model for decline severity estimation at tree crown level from 0.61 to 0.69, while it was improved from 0.70 to 0.91 when fitting a non-parametric random forest model. The results of sensitivity analysis demonstrated that the additional spectral information obtained from the proposed method results in higher accuracy in estimating decline severity. We suggest this method as a cost-effective alternative to monitor periodical tree decline, in particular across semi-arid ecosystems.

Temporal and Spatial Distribution of Phytoplankton and Role of Environment Factors in the Shending River Backwater in the Danjiangkou Reservoir Area

The Danjiangkou Reservoir supplies drinking water to most residents in northern China. However, signs of eutrophication have been observed in the inlet tributaries of the reservoir, including the Shending River backwater. This research used data from the Sentinel-2 Multispectral instrument and findings from a 2021 aquatic ecological survey to analyze the spatial and temporal characteristics of phytoplankton distribution in the Shending River backwater region. The average chlorophyll a (Chl-a) concentrations by season, ranked from largest to smallest, are as follows: summer (63.96 μg/L) > autumn (41.26 μg/L) > spring (27.47 μg/L) > winter (16.21 μg/L); the upstream of the backwater area and the near-shore tributary bay had relatively higher Chl-a concentration. Bacillariophyceae (Cyclotella meneghiniana and Synedra sp.) and Cryptophyceae species (Chroomonas acuta) were dominant in spring, whereas Chlorophyceae (Scenedesmus sp. and Chlorella vulgaris) and Cyanophyceae (Dactylococcopsis acicularis, Microcystis aeruginosa and Oscillatoria tenuis) species were dominant in summer. The seasonal succession characteristics of the phytoplankton community were consistent with those of the Plankton Ecology Group model. The average phytoplankton cell density was 4.80 × 107 cells/L, and the Shannon–Wiener average diversity index was 1.95, indicating that the Shending River backwater area was moderately eutrophic. According to Pearson correlation analysis and Mantel test, the main factors causing temporal and spatial differences in phytoplankton production in the Shending River’s backwater were water level (WL), water temperature (WT), ammonia nitrogen (NH3-N) and total nitrogen (TN). In particular, WL was significantly positively correlated with Bacillariophyceae, Chlorophyceae and Cyanophyceae, whereas WT was significantly correlated with Cryptophyceae and Chlorophyceae. NH3-N and TN were significantly correlated with Cyanophyceae. Therefore, intensive nitrogen removal from the tailwater of sewage treatment plants may be considered a feasible measure to prevent cyanobacterial bloom in the Shending River backwater of the Danjiangkou Reservoir.

Monitoring global cement plants from space

As an energy-intensive industry, cement production can emit significant air pollutants that negatively impact human health and the environment. Geospatial data on cement plants are crucial for managing the cement industry and designing effective policies to mitigate ever-increasing air pollution. However, the available fundamental asset-level datasets of global cement plants are generally incomplete and may not adequately satisfy the above requirements. To address this gap, (i) we proposed an innovative semi-automatic framework, which is based on the high-temperature signal from active kilns in time-series Landsat-8 Operational Land Imager (OLI) and Sentinel-2 Multispectral Instrument (MSI) imagery and the iconic characteristics of cement processing equipment in high-resolution imagery, to identify global cement plants, assess their operational status, and evaluate relevant activity levels. (ii) We compiled a state-of-the-art inventory of global cement plants, enriched with detailed attributes, using multi-source spaceborne observations/products. We identified 3075 cement plants with rotary/shaft kilns and pinpointed 1960 locations for cement grinding and storage facilities. (iii) We investigated the status of global cement plants using time-series Sentinel-2 MSI imagery. Our results show that from 2016 to date, 69.3% of cement plants are continuously operating, 4.3% were newly constructed, and 26.4% were decommissioned. (iv) We proposed two normalized metrics, namely the occurrence rate and the mean detected area, to assess the activity level of cement plants. The results showed that the rotary kilns in wet-process cement plants had the highest activity level due to the higher energy consumption. The activity level of global cement plants increased by ∼9% during 2016–2021 and then decreased by ∼4% in 2022, possibly due to the influence of COVID-19 and weak market demand. The proposed framework provides valuable insights for investigating the locations and dynamics of other industrial hot sources, such as those in steel mills, coke ovens, refineries, and oil/gas development areas, to improve the estimates of CO2 emissions and air pollutants and then to promote climate action.

Cascading Machine Learning to Monitor Volcanic Thermal Activity Using Orbital Infrared Data: From Detection to Quantitative Evaluation

Several satellite missions are currently available to provide thermal infrared data at different spatial resolutions and revisit time. Furthermore, new missions are planned thus enabling to keep a nearly continuous ‘eye’ on thermal volcanic activity around the world. This massive volume of data requires the development of artificial intelligence (AI) techniques for the automatic processing of satellite data in order to extract significant information about volcano conditions in a short time. Here, we propose a robust machine learning approach to accurately detect, recognize and quantify high-temperature volcanic features using Sentinel-2 MultiSpectral Instrument (S2-MSI) imagery. We use the entire archive of high spatial resolution satellite data containing more than 6000 S2-MSI scenes at ten different volcanoes around the world. Combining a ‘top-down’ cascading architecture, two different machine learning models, a scene classifier (SqueezeNet) and a pixel-based segmentation model (random forest), we achieved a very high accuracy, namely 95%. These results show that the cascading approach can be applied in near-real time to any available satellite image, providing a full description of the scene, with an important contribution to the monitoring, mapping and characterization of volcanic thermal features.

Development of an algal bloom satellite and in situ metadata hub with case studies in Canada

Satellite remote sensing of algal blooms has been in use for almost five decades and has advanced with an increasing number of sensors, improvements in sensor performance, and developments in algorithms. This progress has enabled the detection and monitoring of blooms in increasingly optically complex water bodies and small lakes, and at finer spatial and temporal resolutions. With climatic and anthropogenic stressors impacting bloom occurrence, duration, and severity, it is critical to understand and characterize blooms across a wide range of spatial and temporal scales. However, resolving blooms at both fine spatial and temporal scales, and simultaneously across broad spatial extents, provides challenges to the limitations of current sensors. This study introduces the Algal Bloom Metadata Hub, an application that can be used to investigate freely available remote sensing data from contemporary satellite sensors to streamline data management and acquisition, particularly when interested in data from multiple satellite sensors. Optical sensors hosted by the hub include the Sentinel-3 Ocean and Land Colour Instrument (OLCI), Sentinel-2 MultiSpectral Instrument (MSI), LANDSAT-8 Operational Land Imager (OLI) and LANDSAT-9 OLI-2; SAR sensors include Sentinel-1, RADARSAT-2, and RADARSAT Constellation Mission (RADARSAT-CM). The application also includes an opportunity for in situ reporting of blooms, providing the potential to improve understanding of bloom occurrence distribution at a wide spatial scale. Case studies in the Western Basin of Lake Erie and Ramsey Lake in Ontario, Canada, demonstrate its utility in identifying suitable remote sensing data. Particularly in Ramsey Lake, the opportunity to leverage scenes from multiple sensors, and the integration of synthetic aperture radar (SAR) data on cloudy days, improved the temporal resolution of bloom monitoring at higher spatial resolutions. This finding was corroborated by performing an investigation into data availability for all small water bodies in Ontario. Further work can be done to integrate data from additional satellite sensors, update the application to add data in real-time, and to quality test in situ data submitted by (citizen) scientists.

Quantitative Assessment of Factors Influencing the Spatiotemporal Variation in Carbon Dioxide Fluxes Simulated by Multi-Source Remote Sensing Data in Tropical Vegetation

Vegetation plays a vital role in the global carbon cycle, a function of particular significance in regulating carbon dioxide fluxes within tropical ecosystems. Therefore, it is crucial to enhance the precision of carbon dioxide flux estimates for tropical vegetation and to explore the determinants influencing carbon sequestration. In this study, Landsat series images and Sentinel-2 Multispectral Instrument satellite data were used to invert vegetation biophysical parameters, thereby improving the timeliness and resolution of state variables from the boreal ecosystem productivity simulator (BEPS). The BEPS model at a 30 m resolution was developed to accurately capture tropical vegetation carbon dioxide fluxes across Hainan Island (HN) over the preceding two decades. The impacts of climate variations and anthropogenic activities on the carbon dioxide fluxes of tropical vegetation were further quantified using quantile regression models and a land-use transfer matrix. Results indicate significant increases in both net primary productivity (NPP) and net ecosystem productivity (NEP) in HN during the period 2000–2020, by 5.81 and 4.29 g C/m2 year, respectively. Spatial trends in vegetation carbon dioxide fluxes exhibited a consistent decline from inland regions to coastal zones. Anthropogenic activities were the dominant factor in the reduced stability of coastal NPP, while the post-2005 vegetation restoration promoted the southward expansion of high NPP (>1200 g C/m2) in the central part of HN. NPP in this tropical island was more sensitive to temperature than to precipitation, with a 1 °C temperature increase resulting in 4.1 g C/m2 reduction in dry-season NPP compared to wet-season NPP. Upgrades of cropland quality and grassland restoration have improved NPP yields, and land use transfers have resulted in a 0.301 Tg C net increase in NPP. This study provides new insight into the improvement of the carbon dioxide flux model at a finer scale for tropical vegetation and highlights ecological construction as an adaptation strategy to enhance the carbon sinks of tropical vegetation under negative climate change conditions.

Tracking the behavior of an accidental oil spill and its impacts on the marine environment in the Eastern Mediterranean

The eastern Mediterranean region is a vital hub for oil transportation and production because of its strategic location between Europe, Asia, and Africa. But its unique attributes, including narrow shipping routes, heavy marine traffic, and proximity to vulnerable ecosystems, render it particularly susceptible to accidental oil spills. In this research, an oil spill detection model, along with bathymetric and oceanographic parameters, was used to track oil spills that occurred at the Syrian Baniyas Station in the Eastern Mediterranean on August 23, 2021. Furthermore, the study employed a pairwise comparison matrix (PWCM) to assess the relative importance of wind speed and direction, water depth, and sea surface temperature (SST) in the dispersion of oil spills. Analysis of Sentinel-1 data obtained prior to, during, and after the incident revealed the accumulation of oil slicks along the Syrian coast from Baniyas to Latakia for up to twenty days. The spilled oil reached the coast of Cyprus six days after the incident. The study determined that wind speed and direction played a critical role in the dispersion of spilled oil, while water depth and SST were comparatively less significant factors in this process. The overall accuracy (OA) and Kappa coefficient (KC) for land, water, and oil slick classes derived from the random forest (RF) algorithm ranged from 90 % to 98 % and from 0.86 to 0.98, respectively. The spread of oil slicks at the incident location was revealed by the decorrelation stretch and band ratios of Sentinel-2 MultiSpectral Instrument (MSI) data. The accidental oil spill could have negative effects on the organic carbon cycle, chlorophyll production, and ecosystem productivity. It is essential to consider the vulnerability of specific regions in the Eastern Mediterranean to oil spills when developing adaptation strategies.

1D Convolutional Neural Network-based Chlorophyll-a Retrieval Algorithm for Sentinel-2 MultiSpectral Instrument in Various Trophic States

1D Convolutional Neural Network-based Chlorophyll-a Retrieval Algorithm for Sentinel-2 MultiSpectral Instrument in Various Trophic States

Fusion of sentinel-1 SAR and sentinel-2 MSI data for accurate Urban land use-land cover classification in Gondar City, Ethiopia

Effective urban planning and management rely on accurate land cover mapping, which can be achieved through the combination of remote sensing data and machine learning algorithms. This study aimed to explore and demonstrate the potential benefits of integrating Sentinel-1 SAR and Sentinel-2 MSI satellite imagery for urban land cover classification in Gondar city, Ethiopia. Synthetic Aperture Radar (SAR) data from Sentinel-1A and Multispectral Instrument (MSI) data from Sentinel-2B for the year 2023 were utilized for this research work. Support Vector Machine (SVM) and Random Forest (RF) machine learning algorithms were utilized for the classification process. Google Earth Engine (GEE) was used for the processing, classification, and validation of the remote sensing data. The findings of the research provided valuable insights into the performance evaluation of the Support Vector Machine (SVM) and Random Forest (RF) algorithms for image classification using different datasets, namely Sentinel 2B Multispectral Instrument (MSI) and Sentinel 1A Synthetic Aperture Radar (SAR) data. When applied to the Sentinel 2B MSI dataset, both SVM and RF achieved an overall accuracy (OA) of 0.69, with a moderate level of agreement indicated by the Kappa score of 0.357. For the Sentinel 1A SAR data, SVM maintained the same OA of 0.69 but showed an improved Kappa score of 0.67, indicating its suitability for SAR image classification. In contrast, RF achieved a slightly lower OA of 0.66 with Sentinel 1A SAR data. However, when the datasets of Sentinel 2B MSI and Sentinel 1A SAR were combined, SVM achieved an impressive OA of 0.91 with a high Kappa score of 0.80, while RF achieved an OA of 0.81 with a Kappa score of 0.809. These findings highlight the potential of fusing satellite data from multiple sources to enhance the accuracy and effectiveness of image classification algorithms, making them valuable tools for various applications, including land use mapping and environmental monitoring.

GF-1 WFV Surface Reflectance Quality Evaluation in Countries along “the Belt and Road”

The GaoFen-1 wide field of view (GF-1 WFV) has produced level 1 digital number data globally; however, most applications have focused on China, and data quality outside China has not been validated. This study presents a preliminary assessment of the 2020 GF-1 WFV surface reflectance data for Nepal, Azerbaijan, Kenya, and Sri Lanka along “the Belt and Road” route using Sentinel-2 Multi-Spectral Instrument (MSI), Landsat-8 Operational Land Image (OLI), and Moderate Resolution Imaging Spectroradiometer (MODIS) data. A method for obtaining the GF-1 WFV surface reflectance data was also proposed, with steps including atmospheric correction, cross-radiation calibration, and bidirectional reflectance distribution function correction. The results showed that WFV surface reflectance data was not significantly different from MSI, OLI, and MODIS surface reflectance data. In the visible and near-infrared bands, for most landcover types, the bias was less than 0.02, and the precision and root mean square error were less than 0.04. When the landcover types were forest and water, the MSI, OLI, and MODIS surface reflectance data were higher than that of WFV in the near-infrared band. The results of this study provide a basis for assessing the global application potential of GF-1 WFV.

Mapping cropland rice residue cover using a radiative transfer model and deep learning

Accurate determination of rice residue cover (RRC) can improve the monitoring of tillage information. Currently, the accurate determination of RRC using optical remote sensing is hindered by variations in cropland moisture and cover of following crops. The fractional cover (FC) of the soil (fS), crop (fC), and crop residue (fCR) changes (fS + fC + fCR = 1) after the following crop is planted, which increases the difficulty of remote-sensing RRC estimation. Cropland soil moisture and crop residue moisture affect the values of cropland and crop residue spectral indices (CRSIs), thereby reducing the accuracy of remote-sensing RRC estimation. Deep learning techniques (e.g., convolutional neural networks [CNN] and transfer learning [TL]) have been proven to extract the deep features of input images with distortion invariance, such as displacement and scaling, which are similar to moisture and the following crop effects on remote-sensing CRSIs.This study aimed to evaluate the combined use of deep features of cropland spectra extracted by deep learning techniques to estimate the cropland RRC under the effects of variations in cropland moisture and cover of the following crops. This study proposes an RRCNet CNN that fuses deep and shallow features to improve RRC estimation. A PROSAIL radiative transfer model was employed to simulate a cropland “soil–crop–crop residue” mixed spectra dataset (n = 103,068), considering the variations in cropland moisture and the cover of the following crop. The RRCNet was first pre-trained using the simulated dataset, and then the knowledge from the pre-trained RRCNet was updated based on field experimental FCs, RRCs, and Sentinel-2 image spectra using the TL technique. Our study indicates that RRCNet can incorporate shallow and deep spectral features of cropland “soil–crop–crop residue” mixed spectra, providing high-performance FCs and RRC estimation. The FCs and RRC estimates from RRCNet + TL (FCs: R2 = 0.939, root mean squared error (RMSE) = 0.071; RRC: R2 = 0.891, RMSE = 0.083) were more accurate than those from CRSI + multiple linear regression, CRSI + random forest, and CRSI + support vector machine (FCs: R2 = 0.877–907, RMSE = 0.086–0.101; RRC: R2 = 0.378–0.714, RMSE = 0.133–0.229). We mapped the multistage RRC based on Sentinel-2 multispectral instrument (MSI) images and RRCNet. Tillage information can be inferred from RRC and RRC difference maps changes.

Machine learning based classification of lake ice and open water from Sentinel-3 SAR altimetry waveforms

The aim of the study was to evaluate, for the first time, the capability of different machine learning (ML) algorithms in classifying along-track lake surface conditions (open water and ice types) across ice seasons (freeze-up, ice growth and break-up periods) from Sentinel-3 A/B synthetic aperture radar altimeter (SRAL) data. To achieve this goal, over 107,500 radar waveforms extracted from 11 large lakes across the Northern Hemisphere and three ice seasons (2018–2021) were manually labelled using complementary satellite data (Sentinel-1 imaging Synthetic Aperture Radar (SAR), Sentinel-2 Multispectral Instrument (MSI) Level 1C, and MODIS Aqua/Terra data) for the training and testing of the ML algorithms in discriminating between open water, young (thin) ice, growing ice and melting ice. The four ML algorithms tested include Random Forest (RF), Gradient Boosting Trees (GBT), K Nearest Neighbor (KNN) and Support Vector Machine (SVM). To characterize the waveforms, seven waveform parameters were derived: Leading Edge Width (LEW), Offset Center of Gravity (OCOG) Width, Pulse Peakiness (PP), backscatter coefficient (Sigma0), late tail to peak power (LTPP), early tail to peak power (ETPP) and the maximum value of the echo power (Max). Accuracies >95% were achieved across all classifiers using a 4-parameter combination (Sigma0, PP, OCOG Width, and LEW). Among all waveform parameters, Sigma0, OCOG width and PP were found to be the most important parameters for discriminating between lake ice types and open water. Despite showing comparable classification performances in the overall classification, RF and KNN are found to be a better fit for global lake ice mapping as both are less sensitive to their internal hyperparameters. Additionally, consistent results (>93.7% accuracy in all classifiers) achieved on the accuracy assessment carried out for each lake (out-of-sample testing) revealed the strength of the classifiers for spatial transferability. Implementation of RF and KNN could be valuable in a pre-or post-processing step for identifying lake surface conditions under which the retrieval of water level and ice thickness may be limited or not possible and, therefore, inform algorithms currently used for the generation of operational or research products. While the research focused on 11 of the largest lakes of the Northern Hemisphere, the classification approach presented herein has potential for application on smaller lakes too since data in SAR mode (∼300 m along-track resolution) are used.

Semi-Supervised Urban Change Detection Using Multi-Modal Sentinel-1 SAR and Sentinel-2 MSI Data

Urbanization is progressing at an unprecedented rate in many places around the world. The Sentinel-1 synthetic aperture radar (SAR) and Sentinel-2 MultiSpectral Instrument (MSI) missions, combined with deep learning, offer new opportunities to accurately monitor urbanization at a global scale. Although the joint use of SAR and optical data has recently been investigated for urban change detection, existing data fusion methods rely heavily on the availability of sufficient training labels. Meanwhile, change detection methods addressing label scarcity are typically designed for single-sensor optical data. To overcome these limitations, we propose a semi-supervised urban change detection method that exploits unlabeled Sentinel-1 SAR and Sentinel-2 MSI data. Using bitemporal SAR and optical image pairs as inputs, the proposed multi-modal Siamese network predicts urban changes and performs built-up area segmentation for both timestamps. Additionally, we introduce a consistency loss, which penalizes inconsistent built-up area segmentation across sensor modalities on unlabeled data, leading to more robust features. To demonstrate the effectiveness of the proposed method, the SpaceNet 7 dataset, comprising multi-temporal building annotations from rapidly urbanizing areas across the globe, was enriched with Sentinel-1 SAR and Sentinel-2 MSI data. Subsequently, network performance was analyzed under label-scarce conditions by training the network on different fractions of the labeled training set. The proposed method achieved an F1 score of 0.555 when using all available training labels, and produced reasonable change detection results (F1 score of 0.491) even with as little as 10% of the labeled training data. In contrast, multi-modal supervised methods and semi-supervised methods using optical data failed to exceed an F1 score of 0.402 under this condition. Code and data are made publicly available.

Evaluation of Spectral Indices for Mapping Burned Areas using Unsupervised Classification in Different Ecosystems using Spectral Indices from Sentinel-2 images

Fire is one of the natural agents that has the greatest impact on the terrestrial ecosystem and plays an important ecological function in a huge portion of the Earth's surface. Remote sensing is an important source for mapping and monitoring forests as well as environmental damage to the landscape caused by fire.To estimate the severity of the fire, the temporal distinction between the spectral indices before and after the fire is critical. This study examines the performance of spectral indices derived from Sentinel-2 Multi Spectral Instrument (MSI) bands for the detection of fire-affected areas in forest fires in regions with different ecosystems located in Brazil, the United States, and Portugal. Separability Index (M) and the Reed-Xiaoli Detection (RXD) Anomaly automatic classifier allowed us to assess the spectral separability and the thematic accuracy of the burned area for the different spectral indices. The analysis parameters were based on spatial dispersion with validation data, Commission Errors (CE), Omission Errors (OE), and Sorensen–Dice Coefficient (DC). The results indicated that the indices based exclusively on the longer shortwave infrared (SWIR1), shorter SWIR (SWIR2), and red-edge bands showed a high degree of separability and were more suitable for detecting the burned areas, although it was observed that the diversity of land use affects the performance of the indices. The evaluation of the performance of the spectral indices based on Sentinel-2 data was important in the analyzes of potentialities and limitations in the detection of burned areas in the face of the different global biomes.

Monitoring of chlorophyll-a and suspended sediment concentrations in optically complex inland rivers using multisource remote sensing measurements

In recent decades, phytoplankton proliferation and sediment input to rivers (especially urban rivers) have become more dramatic under the compound pressure of climate change and human activities. Given the generally narrow width of rivers and current high spatial resolution satellites, which are limited by band settings, bandwidth, and the signal-to-noise ratio, UAVs with their exceptional spatiotemporal resolution can be used as a useful tool for river environmental monitoring and inversion uncertainty assessment. In this study, UAV-based hyperspectral (X20P) and multispectral (P4M) images, along with Sentinel-2 MultiSpectral Instrument (MSI), Landsat-8 Operational Land Imager (OLI) and Landsat-9 OLI2 data, were used to assess the uncertainty in retrieving chlorophyll-a (Chla) and suspended sediment (SS) concentrations in rivers. Chla and SS models based on UAV and satellite data were constructed using stepwise multiple regression and typical Chla and SS retrieval algorithms, respectively, and the performance of the models was the focus of our research. The results demonstrated that in the Chla concentration inversion, each sensor performed as follows: X20P > P4M > Landsat9 OLI2 > Sentinel-2 MSI > Landsat8 OLI, and the performance in the SS concentration inversion was as follows: X20P > Sentinel-2 MSI > P4M > Landsat9 OLI2 > Landsat8 OLI. In addition, the uncertainty of high spatial resolution satellite retrievals was analyzed with the assistance of the UAV-based model. Results showed that narrow bandwidths and finely tuned band settings are more essential for the Chla inversion. The typical Chla retrieval algorithm, NDCI, is only effective in certain bands (band 1 from 684 to 724 nm and band 2 from 660 to 680 nm). It is also noted that Landsat8 and Landsat9 lack some key band settings (e.g., the red-edge band of 700–710 nm), severely limiting practical application in relation to Chla. However, specific variances in different sensor bands have a relatively small impact on SS inversion, for example, the correlation between SS and the R/B (a typical SS retrieval algorithm) constructed by each sensor ranged from 0.68 to 0.77. Chla monitoring, on the other hand, necessitates a higher spatial resolution than SS monitoring. The accuracy decreased markedly when UAV images were resampled to 10 m and 30 m spatial resolution. However, it is not as crucial for the SS inversion, images with the original spatial resolution (RMSE<30cm = 6.28 mg/L) were resampled to 10 m resolution (RMSE10m = 5.85 mg/L) and 30 m resolution (RMSE30m = 4.08 mg/L) while using P4M for SS inversion, and the accuracy increased. Our results demonstrated and highlighted various options for future monitoring of Chla and SS, while exploiting the synergy between UAVs and satellites to achieve more precise observations at greater spatial and temporal scales, which will benefit aquatic environment management and protection.

Estimating the concentration of total suspended solids in inland and coastal waters from Sentinel-2 MSI: A semi-analytical approach

Inland and coastal waters provide key ecosystem services and are closely linked to human well-being. In this study, we propose a semi-analytical method, which can be applied to Sentinel-2 MultiSpectral Instrument (MSI) images to retrieve high spatial-resolution total suspended solids (TSS) concentration in a broad spectrum of aquatic ecosystems ranging from clear to extremely turbid waters. The presented approach has four main steps. First, the remote sensing reflectance (Rrs) at a band lacking in MSI (620 nm) is estimated through an empirical relationship from Rrs at 665 nm. Second, waters are classified into four types (clear, moderately turbid, highly turbid, and extremely turbid). Third, semi-analytical algorithms are used to estimate the particulate backscattering coefficient (bbp) at a reference band depending on the water types. Last, TSS is estimated from bbp at the reference band. Validation and comparison of the proposed method with three existing methods are performed using a simulated dataset (N = 1000), an in situ dataset collected from global inland and coastal waters (N = 1265) and satellite matchups (N = 40). Results indicate that the proposed method can improve TSS estimation and provide accurate retrievals of TSS from all three datasets, with a median absolute percentage error (MAPE) of 14.88 %, 31.50 % and 41.69 % respectively. We also present comparisons of TSS mapping between the Sentinel-3 Ocean and Land Colour Instrument (OLCI) and MSI in Lake Kasumigaura, Japan and the Tagus Estuary, Portugal. Results clearly demonstrate the advantages of using MSI for TSS monitoring in small water bodies such as rivers, river mouths and other nearshore waters. MSI can provide more detailed and realistic TSS estimates than OLCI in these water bodies. The proposed TSS estimation method was applied to MSI images to produce TSS time-series in Lake Kasumigaura, which showed good agreements with in situ and OLCI-derived TSS time-series.