Sentinel-2 Multispectral Data Research Articles

Comparison of Machine Learning Methods for Estimating Mangrove Above-Ground Biomass Using Multiple Source Remote Sensing Data in the Red River Delta Biosphere Reserve, Vietnam

This study proposes a hybrid intelligence approach based on an extreme gradient boosting regression and genetic algorithm, namely, the XGBR-GA model, incorporating Sentinel-2, Sentinel-1, and ALOS-2 PALSAR-2 data to estimate the mangrove above-ground biomass (AGB), including small and shrub mangrove patches in the Red River Delta biosphere reserve across the northern coast of Vietnam. We used the novel extreme gradient boosting decision tree (XGBR) technique together with genetic algorithm (GA) optimization for feature selection to construct and verify a mangrove AGB model using data from a field survey of 105 sampling plots conducted in November and December of 2018 and incorporated the dual polarimetric (HH and HV) data of the ALOS-2 PALSAR-2 L-band and the Sentinel-2 multispectral data combined with Sentinel-1 (C-band VV and VH) data. We employed the root-mean-square error (RMSE) and coefficient of determination (R2) to evaluate the performance of the proposed model. The capability of the XGBR-GA model was assessed via a comparison with other machine-learning (ML) techniques, i.e., the CatBoost regression (CBR), gradient boosted regression tree (GBRT), support vector regression (SVR), and random forest regression (RFR) models. The XGBR-GA model yielded a promising result (R2 = 0.683, RMSE = 25.08 Mg·ha−1) and outperformed the four other ML models. The XGBR-GA model retrieved a mangrove AGB ranging from 17 Mg·ha−1 to 142 Mg·ha−1 (with an average of 72.47 Mg·ha−1). Therefore, multisource optical and synthetic aperture radar (SAR) combined with the XGBR-GA model can be used to estimate the mangrove AGB in North Vietnam. The effectiveness of the proposed method needs to be further tested and compared to other mangrove ecosystems in the tropics.

High-resolution digital mapping of soil organic carbon and soil total nitrogen using DEM derivatives, Sentinel-1 and Sentinel-2 data based on machine learning algorithms

Soil organic carbon (SOC) and soil total nitrogen (STN) are important indicators of soil health and play a key role in the global carbon and nitrogen cycles. High-resolution radar Sentinel-1 and multispectral Sentinel-2 images have the potential to investigate soil spatial distribution information over a large area, although Sentinel-1 and Sentinel-2 data have rarely been combined to map either SOC or STN content. In this study, we applied machine learning techniques to map both SOC and STN content in the southern part of Central Europe using digital elevation model (DEM) derivatives, multi-temporal Sentinel-1 and Sentinel-2 data, and evaluated the potential of different remote sensing sensors (Sentinel-1 and Sentinel-2) to predict SOC and STN content. Four machine-learners including random forest (RF), boosted regression trees (BRT), support vector machine (SVM) and Bagged CART were used to construct predictive models of SOC and STN contents based on 179 soil samples and different combinations of environmental covariates. The performance of these models was evaluated based on a 10-fold cross-validation method by three statistical indicators. Overall, the BRT model performed better than RF, SVM and Bagged CART, and these models yielded similar spatial distribution patterns of SOC and STN. Our results showed that multi-source sensor methods provided more accurate predictions of SOC and STN contents than individual sensors. The application of radar Sentinel-1 and multispectral Sentinel-2 images proved useful for predicting SOC and STN. A combination of Sentinel-1/2-derived predictors and DEM derivatives yielded the highest prediction accuracy. The prediction accuracy changed with and without the Sentinel-1/2-derived predictors, with the R2 for estimating both SOC and STN content using the BRT model increasing by 12.8% and 18.8%, respectively. Topographic variables were the main explanatory variables for SOC and STN predictions, where elevation was assigned as the variable with the most importance by the models. The results of this study illustrate the potential of free high-resolution radar Sentinel-1 and multispectral Sentinel-2 data as input when developing SOC and STN prediction models.

A framework for large-scale mapping of human settlement extent from Sentinel-2 images via fully convolutional neural networks

Human settlement extent (HSE) information is a valuable indicator of world-wide urbanization as well as the resulting human pressure on the natural environment. Therefore, mapping HSE is critical for various environmental issues at local, regional, and even global scales. This paper presents a deep-learning-based framework to automatically map HSE from multi-spectral Sentinel-2 data using regionally available geo-products as training labels. A straightforward, simple, yet effective fully convolutional network-based architecture, Sen2HSE, is implemented as an example for semantic segmentation within the framework. The framework is validated against both manually labelled checking points distributed evenly over the test areas, and the OpenStreetMap building layer. The HSE mapping results were extensively compared to several baseline products in order to thoroughly evaluate the effectiveness of the proposed HSE mapping framework. The HSE mapping power is consistently demonstrated over 10 representative areas across the world. We also present one regional-scale and one country-wide HSE mapping example from our framework to show the potential for upscaling. The results of this study contribute to the generalization of the applicability of CNN-based approaches for large-scale urban mapping to cases where no up-to-date and accurate ground truth is available, as well as the subsequent monitor of global urbanization.

An Automatic Processing Chain for Near Real-Time Mapping of Burned Forest Areas Using Sentinel-2 Data

A fully automated processing chain for near real-time mapping of burned forest areas using Sentinel-2 multispectral data is presented. The acronym AUTOBAM (AUTOmatic Burned Areas Mapper) is used to denote it. AUTOBAM is conceived to work daily at a national scale for the Italian territory to support the Italian Civil Protection Department in the management of one of the major natural hazards, which affects the territory. The processing chain includes a Sentinel-2 data procurement component, an image processing algorithm, and the delivery of the map to the end-user. The data procurement component searches every day for the most updated products into different archives. The image processing part represents the core of AUTOBAM and implements an algorithm for burned forest areas mapping that uses, as fundamental parameters, the relativized form of the delta normalized burn ratio and the normalized difference vegetation index. The minimum mapping unit is 1 ha. The algorithm implemented in the image processing block is validated off-line using maps of burned areas produced by the Copernicus Emergency Management Service. The results of the validation shows an overall accuracy (considering the classes of burned and unburned areas) larger than 95% and a kappa coefficient larger than 80%. For what concerns the class of burned areas, the commission error is around 1%−3%, except for one case where it reaches 25%, while the omission error ranges between 6% and 25%.

Mapping the spatial distribution of the yellowwood tree (Podocarpus henkelii) in the Weza-Ngele forest using the newly launched Sentinel-2 multispectral imager data

ABSTRACT The conservation of indigenous tree species is not only significant for the natural heritage, but for conserving numerous species that are heavily dependent on these trees for survival. Remotely sensed data have been proven to be an effective tool for enumeration monitoring of vegetation resources. However, the utility of freely available new generation multispectral sensors with improved spatial and spectral resolutions still needs to be understood in the conservation of natural resources. Therefore, this study sought to map the spatial distribution of Podocarpus henkelii in Weza-Ngele forest using Sentinel-2 Multispectral Instrument. A total of five classes were randomly sampled and discriminated using Random Forest technique. The models created from only spectral bands were compared to those derived from combining vegetation indices and spectral bands. The Index Database was used to compute vegetation indices (VI) with 10 different VI being selected for characterizing Podocarpus land cover types. The overall accuracies of spectral bands, as well as spectral bands combined with vegetation indices, was 67% and 80%, respectively. These results underscore the utility of the new generation of multispectral sensors in successfully discriminating P.henkelii from other land cover, thus providing a cheaper and easier alternative for indigenous forest species mapping.

Urban Impervious Surface Extraction Based on Multi-Features and Random Forest

Impervious surface data has become an indicator of the degree of urbanization and the environmental quality, which inspires the widely use of remote sensing technology in extracting impervious surface. In order to reduce the confusion between impervious surface and other landcover types, this paper proposed an effective urban impervious surface extraction method based on multi-features and Random Forest (RF). First, Sentinel-2 multispectral data and Luojia 1–01 images are employed to extracted multi-features, including spectral features, texture features and temporal features. Then, a feature selection method with null importance is proposed to remove irrelevant features. Finally, Probabilistic Label Relaxation (PLR) is introduced into RF to obtain the classification results and impervious surface. The main urban areas of Zhengzhou and Hangzhou are selected as study areas. The experiment results show that the integration of the multi-features can significantly improve the overall accuracy of classification and the extraction accuracy of impervious surface. And the classification accuracy can be further improved after the feature selection with null importance. Besides, the PLR method can effectively reduce the salt-and-pepper phenomenon of classification results using random forest, which presupposes the optimal number of iterations. The method proposed in this paper can effectively improve the estimation of impervious surface and provide an important reference for the extraction of impervious surface based on pixel level.

A Disease Index for Efficiently Detecting Wheat Fusarium Head Blight Using Sentinel-2 Multispectral Imagery

Rapid, non-destructive detection of wheat Fusarium head blight (FHB) is an important tool for disease control. Red-edge (RE) is a prominent spectral feature for determining crop conditions with the potential to enhance the accuracy of monitoring FHB regionally. This study explored the potential of RE for FHB monitoring based on Sentinel-2 Multispectral Instrument (MSI) data. The novel red-edge head blight index (REHBI) was developed to detect FHB at a regional scale. Hyperspectral data at the canopy scale was integrated to simulate Sentinel-2 multispectral reflectance using the relative spectral response (RSR) function of the sensor. Then, many differential and ratio combinations of Sentinel-2 bands that were sensitive to FHB severity were selected. REHBI was established based on these basic vegetation indexes (VIs), and the model developed from REHBI performed best in monitoring FHB severity (R 2 = 0.82, RMSE = 10.1). Additionally, the infected canopies with disease index (DI) values between 10 and 50 were classified as slightly diseased canopies. Ordinary least square (OLS) was used to test the performance of REHBI and two conventional VIs, i.e., OSAVI and RDVI, in monitoring slightly diseased canopies; REHBI outperformed these alternatives (R 2 = 0.69, RMSE = 3.6). To approximate real agricultural conditions, Poisson noise was added to the simulated Sentinel-2 multispectral data and generalized performance of VIs was evaluated again; REHBI still had the highest R 2 and lowest RMSE values (0.74 and 12.6, respectively). Finally, to validate REHBI's ability to detect FHB infection in agricultural production, it was applied to monitoring FHB in the wheat planting areas of Changfeng and Dingyuan counties from Sentinel-2 imagery. Generally, REHBI performed better in disease monitoring than OSAVI and RDVI. The overall accuracy was up to 78.6%, and the kappa coefficient was 0.51. Experimental results demonstrate that REHBI can be used to monitor FHB.

Exploring the Potential of C-Band SAR in Contributing to Burn Severity Mapping in Tropical Savanna

The ability to map burn severity and to understand how it varies as a function of time of year and return frequency is an important tool for landscape management and carbon accounting in tropical savannas. Different indices based on optical satellite imagery are typically used for mapping fire scars and for estimating burn severity. However, cloud cover is a major limitation for analyses using optical data over tropical landscapes. To address this pitfall, we explored the suitability of C-band Synthetic Aperture Radar (SAR) data for detecting vegetation response to fire, using experimental fires in northern Australia. Pre- and post-fire results from Sentinel-1 C-band backscatter intensity data were compared to those of optical satellite imagery and were corroborated against structural changes on the ground that we documented through terrestrial laser scanning (TLS). Sentinel-1 C-band backscatter (VH) proved sensitive to the structural changes imparted by fire and was correlated with the Normalised Burn Ratio (NBR) derived from Sentinel-2 optical data. Our results suggest that C-band SAR holds potential to inform the mapping of burn severity in savannas, but further research is required over larger spatial scales and across a broader spectrum of fire regime conditions before automated products can be developed. Combining both Sentinel-1 SAR and Sentinel-2 multi-spectral data will likely yield the best results for mapping burn severity under a range of weather conditions.

Monitoring Glyphosate-Based Herbicide Treatment Using Sentinel-2 Time Series—A Proof-of-Principle

In this paper we aim to show a proof-of-principle approach to detect and monitor weed management using glyphosate-based herbicides in agricultural practices. In a case study in Germany, we demonstrate the application of Sentinel-2 multispectral time-series data. Spectral broadband vegetation indices were analysed to observe vegetation traits and weed damage arising from herbicide-based management. The approach has been validated with stakeholder information about herbicide treatment using commercial products. As a result, broadband NDVI calculated from Sentinel-2 data showed explicit feedback after the glyphosate-based herbicide treatment. Vegetation damage could be detected after just two days following of glyphosate-based herbicide treatment. This trend was observed in three different application scenarios, i.e., during growing stage, before harvest and after harvest. The findings of the study demonstrate the feasibility of satellite based broadband NDVI data for the detection of glyphosate-based herbicide treatment and, e.g., the monitoring of latency to harvesting. The presented results can be used to implement monitoring concepts to provide the necessary transparency about weed treatment in agricultural practices and to support environmental monitoring.

Derivation of Tasseled Cap Transformation Coefficients for Sentinel-2 MSI At-Sensor Reflectance Data

Tasseled cap transformation (TCT) is a commonly used remote-sensing technique and has been successfully used in various remote sensing-related applications. However, the TCT coefficient set is sensor-specific, and therefore, in this article, we developed the TCT coefficients specifically for Sentinel-2 multispectral instrument at-sensor reflectance data. A total of ten synchronous image pairs of Sentinel-2 and Landsat-8, collected from the different parts of the world, were used for this approach. Instead of using the traditional Gram-Schmidt orthogonalization (GSO) method, we derived the coefficients using a principal component-based Procrustes analysis (PCP) method. This was done by rotating principal component axes of Sentinel-2 data to align to Landsat-8 Operational Land Imager tasseled cap axes via the Procrustes analysis. The results show that the TCT coefficients derived from our PCP method can effectively enhance brightness, greenness, and wetness characteristics of the Sentinel-2 imagery. The results have also been compared with those of a previous study that derived the Sentinel-2 TCT data using the GSO method instead. Landsat-8 and moderate resolution imaging spectroradiometer (MODIS)-derived TCT data have been used as references for comparison. The comparison shows that the PCP method outperforms the GSO method, as the PCP's results generally have lower root mean square errors and higher correlation coefficients (R) when compared with the corresponding TC components of Landsat-8 and MODIS data, respectively. The greatest difference between the PCP and GSO methods lies in the wetness component. The PCP method can correctly highlight vegetation and soil moisture, as well as water features in the component.

Examining the prospects of sentinel-2 multispectral data in detecting and mapping maize streak virus severity in smallholder Ofcolaco farms, South Africa

Crop diseases monitoring is critical in understanding the effects of diseases on crop production and associated implications on food security. The aim of this study was to assess the utility of the 10 m resolution Sentinel 2 data set, in detecting and mapping Maize Streak Virus (MSV) disease in Ofcolaco farms in Tzaneen, South Africa. Specifically, the study sought to spectrally discriminate and map maize infected with MSV from other land-cover classes. To achieve this objective two analysis approaches were used: spectral analysis (Test I: spectral bands; Test II: spectral bands + spectral vegetation indices) using random forest algorithm in a supervised classification approach. The indices combined with spectral bands were EVI, SAVI, NDVI, GNDVI, GLI and MSAVI. Results indicated that infected maize was highly separable from health maize and other land cover classes (TDSI > 1.8). The mapping accuracy was high using spectral data (Overall accuracy = 85.29% and Kappa = 0.79) and even higher when spectral bands were combined with derived vegetation indices (Overall accuracy = 89.43% and Kappa = 0.84). The results of the study show that the 10 m resolution multispectral Sentinel 2 data set can be used to detect and map maize infected by MSV. The findings are important in showing the value of combining 10 m spectral data with derived indices from Sentinel 2 in improving monitoring of maize steak virus in resource-constrained nations.

A Hierarchical Classification Framework of Satellite Multispectral/Hyperspectral Images for Mapping Coastal Wetlands

Mapping different land cover types with satellite remote sensing data is significant for restoring and protecting natural resources and ecological services in coastal wetlands. In this paper, we propose a hierarchical classification framework (HCF) that implements two levels of classification scheme to identify different land cover types of coastal wetlands. The first level utilizes the designed decision tree to roughly group land covers into four rough classes and the second level combines multiple features (i.e., spectral feature, texture feature and geometric feature) of each class to distinguish different subtypes of land covers in each rough class. Two groups of classification experiments on Landsat and Sentinel multispectral data and China Gaofen (GF)-5 hyperspectral data are carried out in order to testify the classification behaviors of two famous coastal wetlands of China, that is, Yellow River Estuary and Yancheng coastal wetland. Experimental results on Landsat data show that the proposed HCF performs better than support vector machine and random forest in classifying land covers of coastal wetlands. Moreover, HCF is suitable for both multispectral data and hyperspectral data and the GF-5 data is superior to Landsat-8 and Sentinel-2 multispectral data in obtaining fine classification results of coastal wetlands.

Accurate modelling of canopy traits from seasonal Sentinel-2 imagery based on the vertical distribution of leaf traits

Leaf traits at canopy level (hereinafter canopy traits) are conventionally expressed as a product of total canopy leaf area index (LAI) and leaf trait content based on samples collected from the exposed upper canopy. This traditional expression is centered on the theory that absorption of incident photosynthetically active radiation (PAR) follow a bell-shaped function skewed to the upper canopy. However, the validity of this theory has remained untested for a suite of canopy traits in a temperate forest ecosystem across multiple seasons using multispectral imagery. In this study, we examined the effect of canopy traits expression in modelling canopy traits using Sentinel-2 multispectral data across the growing season in Bavaria Forest National Park (BFNP), Germany. To achieve this, we measured leaf mass per area (LMA), chlorophyll (Cab), nitrogen (N) and carbon content and LAI from the exposed upper and shaded lower canopy respectively over three seasons (spring, summer and autumn). Subsequently, we estimated canopy traits using two expressions, i.e. the traditional expression-based on the product of LAI and leaf traits content of samples collected from the sunlit upper canopy (hereinafter top-of-canopy expression) and the weighted expression - established on the proportion between the shaded lower and sunlit upper canopy LAI and their respective leaf traits content. Using a Random Forest machine-learning algorithm, we separately modelled canopy traits estimated from the two expressions using Sentinel-2 spectral bands and vegetation indices. Our results showed that dry matter related canopy traits (LMA, N and carbon) estimated based on the weighted canopy expression yield stronger correlations and higher prediction accuracy (NRMSECV < 0.19) compared to the top-of-canopy traits expression across all seasons. In contrast, canopy chlorophyll estimated from the top-of-canopy expression demonstrated strong fidelity with Sentinel-2 bands and vegetation indices (RMSE < 0.48 µg/cm2) compared to weighted canopy chlorophyll (RMSE > 0.48 µg/cm2) across all seasons. We also developed a generalized model that explained 52.57–67.82% variation in canopy traits across the three seasons. Using the most accurate Random Forest model for each season, we demonstrated the capability of Sentinel-2 data to map seasonal dynamics of canopy traits across the park. Results presented in this study revealed that canopy trait expression can have a profound effect on modelling the accuracy of canopy traits using satellite imagery throughout the growing seasons. These findings have implications on model accuracy when monitoring the dynamics of ecosystem functions, processes and services.

Using Remote Sensing Based Metrics to Quantify the Hydrological Response in a City

We propose a remote-sensing based metric approach to evaluate the hydrological response of highly urbanized areas and apply it to the city of Brussels. The model is set-up using 2 m resolution hyperspectral data. Next, it is upscaled to the city level, using multi-spectral Sentinel-2 data with 20 m resolution. We identify the total impervious area, the vegetation cover and the leaf area index as important metrics to derive a timeseries of spatially distributed net rainfall, runoff and infiltration from rainfall data. For the estimation of the actual evapotranspiration we use the potential evapotranspiration and the available water storage based on the interception, the depression storage and the infiltration. Additionally, we route the runoff to the outlet of selected sub-catchments. An important metric for the routing is the timing to the outlet which is approximated using the total impervious area and the hydrological distance to the outlet. We compare our approach to WetSpa model simulations and reach R 2 values of 98% for net rainfall, 95% for surface runoff, 99% for infiltration and 97% for cumulative evapotranspiration. The routing in the Watermaelbeek catchment is evaluated with discharge observations and reaches NSE values of 0.89 at a 2 m resolution and 0.88 at a 20 m resolution using an hourly timestep. At the timestep of 10 min and a 20 m resolution the NSE is reduced to 0.76. For the Roodebeek catchment we reach an NSE of 0.73 at a spatial resolution of 20 m and an hourly timestep. The results presented in this paper are optimistic for using spatial and temporal metrics retrieved from remote sensing data to quantify the water balance of urban catchments.

Analysis of cloud condition on Sentinel-2 MSI and Landsat-8 OLI images of a public supply lake in Belém-Pará-Brazil

The eutrophication process leads to reduced water quality and economic losses worldwide. Furthermore, it is possible to apply remote sensing techniques for monitoring of aquatic environments. In this paper, we analysed the combined use of Sentinel-2 Multispectral Instrument and Landsat-8 Operational Land Imager data to monitor a eutrophic aquatic environment under adverse cloudy conditions, from July 2016 to July 2018. Data pre-selection was performed, and then the images were acquired for further investigation. After that, we created a key to the interpretation of cloud conditions for the study area and grouped each of 125 scenes in a Principal Component Analysis (PCA). The PCA grouped months with similarities in cloud conditions, highlighting their patterns in terms of the rainy and dry seasons for the study area. Another interesting result was that, even under the inherent adverse cloud regime of the Amazon, the combined use of both free satellite imagery data could be useful for further analyses, such as measuring of chlorophyll a, coloured dissolved organic matters, total suspended solids and turbidity. However, we highlight that, firstly, studies must be made to validate the data in situ, so that monitoring programs can be built through remote sensing applications.

Calculating potential evapotranspiration and single crop coefficient based on energy balance equation using Landsat 8 and Sentinel-2

Evapotranspiration is considered to be an important component of allocating water to agricultural sector; therefore, the more accurate this parameter is, the more optimized the water use can be. This study was conducted in order to evaluate the Landsat 8 and Sentinel-2 data (A and B), both separately and combined, in potential evapotranspiration (ETp) and single crop coefficient (Kc) estimations. Field measurements such as crop height, leaf area index (LAI), land surface temperature (LST), air temperature above canopy (AT), and spectral data were exploited in the evaluating process throughout the entirety of 2017–18 growing season under winter wheat and barley cultivations in the Agricultural Research Farms of the University of Tehran. The novel method of Multi-Sensor Data Fusion using the Priestly-Taylor equation was taken into practice for satellite-based ETp (MSDF-ET) calculation from the combination of MODIS thermal and Landsat 8 and Sentinel-2 multispectral data. Thermal images were downscaled by the means of the TsHARP algorithm. Thus, prior to ETp calculation, the thermal sharpening algorithm calculated using different spectral indices (SI) was assessed. The SI included NDVI, SAVI, SR, NDWI, NDWIg, and LSWI. The subsequent results were representative of the LSWI qualification under both Landsat 8 and Sentinel-2 conditions against thermal and spectral measurements. Also the satellite-based ETp strongly correlated with the ETp derived from the field data illuminating the promising accuracy of the MSDF-ET method in both Landsat 8 and Sentinel-2 data. In the end, the time series of Kc obtained from the combination of satellites were fairly indicative of the real-world variations under different vegetation cover and crop growth stages. Overall, using Landsat 8 and Sentinel-2 products in integration with each other could significantly result in more reliable decisions in agricultural water resources management.

Use of Logistic Regression in Land-Cover Classification with Moderate-Resolution Multispectral Data

The current study highlights the use of binary logistic regression for land-use land-cover (LULC) classification. The moderate-resolution Sentinel-2 multispectral data was used for LULC map generation for the post-monsoon season. The main focus of this study is to present a simple and precise approach for image classification using binary logistic regression (BLR) technique. The study was carried out in cropland, fallow land, forest and water body dominated subtropical region of India located in the eastern coastal region. The cropland and fallow lands are mostly dependent on the monsoon and reciprocal land covers. A large number of training and testing data points were collected viewing the image in a standard false-color composite. ArcGIS, Microsoft Office Excel and R software were used for classification. In addition to BLR, the training and testing data points were also used to perform the classification with ‘random forest’ classifier in R. We observed higher classification accuracy for spectrally pure classes and pixels and lower for closely associated mix-pixels. Lower user’s and producer’s accuracies (< 90%) were observed for fallow land, water body and grassland class during training and model building and for fallow land and forest during accuracy assessment, whereas the accuracies were more than 90% for the rest of classes during both training and testing. Misclassifications were mostly observed between forest, fallow land, grassland and water body during training, which were forest and fallow land in testing, due to their lower spectral difference with reference to classified classes. However, the overall accuracy and kappa value during training and testing were more than 94% and 0.98, respectively. Similar accuracies and misclassification were also obtained with the results of random forest model, validating the adopted methodology. Regardless of the seasonal variations in cropland and fallow land, the field observations (52 locations) also corroborated the estimated classification accuracy. The easy implementation and comparatively higher classification accuracy with the binary logistic technique are believed to increase its intense use in land-cover classification.

ASSESSING VEGETATION STRUCTURAL CHANGES IN OASIS AGRO-ECOSYSTEMS USING SENTINEL-2 IMAGE TIME SERIES: CASE STUDY FOR DRÂA-TAFILALET REGION MOROCCO

Abstract. Nowadays, Moroccan oasis agro-ecosystems are under intense effect of natural and anthropogenic factors. Therefore, this essay proposes to use Leaf Area Index (LAI) to assess the consequences of the oases long-term biodegradation. The index was used as a widely-applied parameter of vegetation structure and an important indicator of plant growth and health. Therefore, a new optical multispectral Sentinel-2 data were used to build a long term LAI time series for the area of the Erfoud and Rissani oases, Errachidia province in Drâa-Tafilalet region in Morocco. Nine images of LAI spatial distribution over the study area were obtained by means of SNAP Biophysical Processor over the period since July 2015 till May 2018. Time series analysis of the resultedmaps has revealed a stable trend towards the average LAI decreasing and vegetation structure simplification as a consequence.

Towards automated mapping and monitoring of potentially dangerous glacial lakes in Bhutan Himalaya using Sentinel-1 Synthetic Aperture Radar data

ABSTRACTThe majority of glacial lakes around the world are located in remote and hardly accessible regions. The use of remote sensing data is therefore of high importance to identify and assess their potential hazards. However, the persistence of cloud cover, particularly in high mountain areas such as the Himalayas, limits the temporal resolution of optical satellite data with which we can monitor potentially dangerous glacial lakes (PDGLs). The ability of Synthetic Aperture Radar (SAR) satellites to collect data, irrespective of weather and at day or night, facilitates monitoring of PDGLs by without compromising temporal resolution. In this study, we present a semi-automated approach, based on a radar signal intensity threshold between water and non-water feature classes followed by post-processing including elevations, slopes, vegetation and size thresholds, to delineate glacial lakes in Sentinel-1 SAR images in Bhutan Himalaya. We show the capability of our method to be used for delineating and monitoring glacial lakes in Bhutan Himalaya by comparing our results to 10 m resolution Sentinel-2 multispectral data, field survey data, meteorological data, and a time series of monthly images from January to December 2016 of two lakes. Sentinel-1 SAR data can, moreover, be used for detecting lake surface area changes and open water area variations, at temporal resolution of six days, providing substantial advantages over optical satellite data to continuously monitor PDGLs.

Recent glacier variations on Mount Melimoyu (44°50'S-72°51'W), Chilean Patagonia, using Sentinel-2 data

This work analyzed the application of Sentinel-2 multispectral imagery and GLIMS data for mapping glacier retreat and to estimate glacier area changes of Mount Melimoyu, located in northern Patagonia, Chile for the period between 1970 and 2017. The results showed a decrease of about 35.61% in the area for the period analyzed and there is a continuing retreating trend in the region. The decreasing trend in mean annual precipitation may explain the recent glacier changes, which indicates a large sensibility for meteorological variability of glaciers, which is influenced by geomorphometry and glacier area, in the region. Using Sentinel 2 imagery, we provided inventory of rock glaciers in the study area. Glacier outlines obtained through manual delineation showed comparable results with the glacier outlines using Sentinel-2 MSI data in the study area, which shows greater accuracy in glacier mapping using Sentinel-2 data.