Assessment of the Added-Value of Sentinel-2 for Detecting Built-up Areas

Spatially-optimized urban greening for reduction of population exposure to land surface temperature extremes

The population experiencing high temperatures in cities is rising due to anthropogenic climate change, settlement expansion, and population growth. Yet, efficient tools to evaluate potential intervention strategies to reduce population exposure to Land Surface Temperature (LST) extremes are still lacking. Here, we implement a spatial regression model based on remote sensing data that is able to assess the population exposure to LST extremes in urban environments across 200 cities based on surface properties like vegetation cover and distance to water bodies. We define exposure as the number of days per year where LST exceeds a given threshold multiplied by the total urban population exposed, in person ⋅ day. Our findings reveal that urban vegetation plays a considerable role in decreasing the exposure of the urban population to LST extremes. We show that targeting high-exposure areas reduces vegetation needed for the same decrease in exposure compared to uniform treatment.

Examining the risk factors for overweight and obesity among women in Ghana: A multilevel perspective

Overweight/obesity prevalence is on the increase in epidemic proportions across Low- and Middle-Income countries (LMICs). The public health burden associated with obesity/overweight cannot be underestimated due to its association with chronic health outcomes. This study investigated the individual- and community level risk factors for obesity/overweight among reproductive women. The data used consist of 4393 reproductive women and form part of the 2014 Ghana Demographic and Health Survey (GDHS). Information on these women are clustered within 427 communities. A 2-tier random intercept multilevel logistic model was used to assess the effect of individual- and community level factors on the likelihood of a woman to be obese/overweight. The obesity/overweight prevalence among reproductive women was estimated to be 35.5% (95% CI: 34.04, 36.90%), which significantly differed across clusters. Most at risk were women from middle-income households (aOR = 2.85; 95% CI: 2.28, 3.56), upper-income households (aOR = 5.019, 95% CI: 3.85, 6.55), attaining secondary education (aOR = 1.74; 95% CI: 1.41, 2.16), and higher (aOR = 1.63; 95% CI: 1.14, 2.33), old age (20-29 years (aOR = 4.26; 95% CI: 3.142,5.78); 30-39 years (aOR = 8.59; 95% CI: 6.15, 12.00); 40-49 years (aOR = 12.81; 95% CI: 9.10, 18.16)). Significant differences in the probability of being overweight/obese between different communities were observed (MOR = 1.39). The high prevalence of overweight/obesity requires urgent public health interventions to prevent future public health crises. Efforts to strengthen the healthcare system, encourage lifestyle modification, and public health education are needed to solidify the gains of ensuring a healthy population by 2030 (SDG 3).

Prediction of the concentration of cadmium in agricultural soil in the Czech Republic using legacy data, preferential sampling, Sentinel-2, Landsat-8, and ensemble models

The current study assesses and predicts cadmium (Cd) concentration in agricultural soil using two Cd datasets, namely legacy data (LD) and preferential sampling-legacy data (PS-LD), along with four streams of auxiliary datasets extracted from Sentinel-2 (S2) and Landsat-8 (L8) bands. The study was divided into two contexts: Cd prediction in agricultural soil using LD, ensemble models, 10 and 20 m spatial resolution of S2 and L8 (context 1), and Cd prediction in agricultural soil using PS-LD, ensemble models and 10 and 20 m spatial resolution of S2 and L8 (context 2). In context 1, ensemble 1, L8 with PS-LD was the cumulative optimal approach that predicted Cd in agricultural soil with a higher R² value of 0.76, root mean square error (RMSE) of 0.66, mean absolute error (MAE) of 0.35, and median absolute error (MdAE) of 0.13. However, with R² = 0.78, RMSE = 0.63, MAE = 0.34, and MdAE = 0.15, ensemble 1, S2 of PS-LD was the best prediction approach in predicting Cd concentration in agricultural soil in context 2. Overall, the predictions from both contexts indicated that ensemble 1 of S2 combined with PS-LD was the most appropriate and best model for Cd prediction in agricultural soil. The modeling approaches' uncertainty in both contexts was assessed using ensemble-sequential gaussian simulation (EnSGS), which revealed that the degree of uncertainty propagated in the study area was within 5% in both contexts. The combination of the PS dataset and the LD along with ensemble models and the remote sensing dataset, produced promising results. Nonetheless, the results demonstrated that the 20 m spatial resolution band dataset used in the prediction of Cd in agricultural soil outperformed the 10 m spatial resolution. When PS is combined with LD, an appropriate modeling approach, and a well-correlated remote sensing dataset are used, good results are obtained.

Wildlife habitat mapping using Sentinel-2 imagery of Mehao Wildlife Sanctuary, Arunachal Pradesh, India

Mehao Wildlife Sanctuary, situated in the state of Arunachal Pradesh, is part of an important biodiversity hotspot in the north-eastern part of India in the Himalayas. The current study deals with the identification of important wildlife habitats in the sanctuary. We used a supervised classification technique to delineate these habitats in the sanctuary, which are used by several mammals and bird species encountered during camera trap and sign surveys conducted between November 2017 and May 2020. Satellite images from Sentinel - 2A were used to classify the land use land cover (LULC) of the sanctuary. The LULC information was generated by using a maximum likelihood classifier. We classified a total of thirteen LULC classes, i.e., water, built-up, agriculture, orchard, grassland, bamboo forest, bamboo-mixed forest, riverbed, barren land, snow, wild banana, riverine forest and mixed forest. LULC classification reveals a high percentage of mixed forest, about 69.9%, followed by wild bananas at 7.2%. The commission and omission error rates, however, are high for riverbed and agriculture (0.5) and bamboo forest (0.5), respectively. The accuracy assessment showed an overall classification accuracy of 88.5% with a Kappa coefficient of 0.87. The abundance of mammals was high in the mixed forest, but Ivlev's electivity index shows that species generally avoided this habitat and preferred specialized forest habitats, such as bamboo forest, bamboo-mixed forest, grassland, riverbed and riverine forest. Our LULC map will provide a baseline for potential planning and monitoring changes of wildlife habitats in Mehao WLS.

Climatology and landscape determinants of AOD, SO2 and NO2 over Indo-Gangetic Plain

Indo-Gangetic Plains (IGP) experiences high loading of particulate and gaseous pollutants all year around and is considered to be the most polluted regions of India. Understanding the effect of landscape determinants on air pollution in IGP regions is crucial to make its environment sustainable. We examined satellite retrievals of OMI NO₂ and SO₂, and MODIS AOD to analyse the long-term trend, spatio-seasonal pattern and dynamics of aerosols, NO₂ and SO₂ over three IGP regions, namely Upper Indo-Gangetic plain (UIGP), Middle Indo-Gangetic plain (MIGP) and Lower Indo-Gangetic plain (LIGP) over the period 2005-2019. IGP experienced an overall increment in AOD (R² = 0.63) and SO₂ (R² = 0.67) values, with LIGP (AOD, R² = 0.8 & SO₂, R² = 0.8) experiencing the largest rate of enhancement. The levels of NO₂ (R² = 0.2) experienced a decrement after 2012 (owing to implementation of vehicle emission policy) except in MIGP, with UIGP (R² = 0.23) exhibiting the largest rate of decrement. Seasonal heterogeneity in the nature of sources was observed over IGP regions. AOD (0.61 ± 0.1) and NO₂ value (3.82 ± 0.98 × 10¹⁵ molecules/cm²) were found highest during post-monsoon in UIGP owing to crop residue burning activity. The value of NO₂ (3.8 ± 1.4 × 10¹⁵ molecules/cm²) in MIGP was found highest during pre-monsoon due to high consumption of coal in power plants for summer cooling demand. The highest SO₂ level (0.09 ± 0.06 DU) was observed during post-monsoon in UIGP, as a large number of brick kilns are fired during this period. Correlations among landscape determinants and pollutants revealed that topography is the dominant variable that affect the spatial pattern of AOD compared to vegetation and land use. Lower elevation tends to have high AOD values compared to higher elevation. Vegetation-AOD relationship showed an inverse association in IGP regions and is influenced by factors such as seasonal meteorology and size of the airborne particles. Vegetation possesses positive relationship with SO₂ and NO₂, implying no pollution abatement effect on SO₂ and NO₂ pollutants. Built-up change has deteriorating effect as well as quenching effect on pollutants. Increase in built terrain have deteriorated the air quality in UIGP whereas it favored in suppressing the aerosol level in LIGP.

Remote Sensing for Short-Term Economic Forecasts

Economic forecasts are an important instrument to judge the nation-wide economic situation. Such forecasts are mainly based on data from statistical offices. However, there is a time lag between the end of the reporting period and the release of the statistical data that arises for instance from the time needed to collect and process the data. To improve the forecasts by reducing the delay, it is of interest to find alternative data sources that provide information on economic activity without significant delays. Among others, satellite images are thought to assist here. This paper addresses the potential of earth observation imagery for short-term economic forecasts. The study is focused on the estimation of investments in the construction sector based on high resolution (HR) (10–20 m) and very high resolution (VHR) (0.3–0.5 m) images as well as on the estimation of investments in agricultural machinery based on orthophotos (0.1 m) simulating VHR satellite imagery. By applying machine learning it is possible to extract the objects of interest to a certain extent. For the detection of construction areas, VHR satellite images are much better suited than HR satellite images. VHR satellite images with a ground resolution of 30–50 cm are able to identify agricultural machinery. These results are promising and provide new and unconventional input for economic forecasting models.

Remote Sensing-Based Analysis of Urban Landscape Change in the City of Bucharest, Romania

The paper investigates the urban landscape changes for the last 50 years in Bucharest, the capital city of Romania. Bucharest shows a complex structural transformation driven by the socialist urban policy, followed by an intensive real-estate market development. Our analysis is based on a diachronic set of high-resolution satellite imagery: declassified CORONA KH-4B from 1968, SPOT-1 from 1989, and multisensor stacked layers from Sentinel-1 SAR together with Sentinel-2MSI from 2018. Three different datasets of land cover/use are extracted for the reference years. Each dataset reveals its own urban structure pattern. The first one illustrates a radiography of the city in the second part of the 20th century, where rural patterns meet the modern ones, while the second one reveals the frame of a city in a full process of transformation with multiple constructions sites, based on the socialist model. The third one presents an image of a cosmopolitan city during an expansion process, with a high degree of landscape heterogeneity. All the datasets are included in a built-up change analysis in order to map and assess the spatial transformations of the city pattern over 5 decades. In order to quantify and map the changes, the Built-up Change Index (BCI) is introduced. The results highlight a particular situation linked to the policy development visions for each decade, with major changes of about 50% for different built-up classes. The GIS analysis illustrates two major landscape transformations: from the old semirural structures with houses surrounded by gardens from 1968, to a compact pattern with large districts of blocks of flats in 1989, and a contemporary city defined by an uncontrolled urban sprawl process in 2018.

Analysis of Built-Up Areas of Small Polish Cities with the Use of Deep Learning and Geographically Weighted Regression

Small cities are an important part of the settlement system, a link between rural areas and large cities. Although they perform important functions, research focuses on large cities and metropolises while marginalizing small cities, the study of which is of great importance to progress in social sciences, geography, and urban planning. The main goal of this paper was to verify the impact of selected socio-economic factors on the share of built-up areas in 665 small Polish cities in 2019. Data from the Database of Topographic Objects (BDOT), Sentinel-2 satellite imagery from 2015 and 2019, and Local Data Bank by Statistics Poland form 2019 were used in the research. A machine learning segmentation procedure was used to obtain the data on the occurrence of built-up areas. Hot Spot (Getis-Ord Gi*) analysis and geographically weighted regression (GWR) was applied to explain spatially varying impact of factors related to population, spatial and economic development, and living standards on the share of built-up areas in the area of small cities. Significant association was found between the population density and the share of built-up areas in the area of the cities studied. The influence of the other socio-economic factors examined, related to the spatial and economic development of the cities and the quality of life of the inhabitants, showed great regional variation. The results also indicated that the share of built-up areas in the area of the cities under study is a result of the conditions under which they were established and developed throughout their existence, and not only of the socio-economic factors affecting them at present.

Linking Urban Sprawl and Surface Urban Heat Island in the Teresina–Timon Conurbation Area in Brazil

Negative consequences of urban growing disparities usually lead to impressive levels of segregation, marginalization, and injustices, particularly in the context of climate change. Understanding the relations between urban expansion and social vulnerability has become extremely necessary for municipality management and sustainable urban development. Although the study of urbanization in Latin America (LA) has been well discussed, little attention has been given to how the population is affected by urban expansion-oriented movement after the 2008 economic crisis. Massive investments in infrastructure displaced the population to peripheral zones without adequate urban planning, which reflected in alteration in land use and land cover (LULC), followed by environmental impacts and public health issues caused by thermal discomfort, notably in semiarid regions. This paper aims to evaluate the effects of urban sprawl on the Teresina–Timon conurbation (TTC) area’s local population, located in Brazil’s northeast. Descriptive metrics (Moran’s I statistic and social vulnerability index) and orbital products derived from remote sensing—LULC and Land surface temperature (LST) maps—were applied. The results indicated that the housing program ‘My House My Life’ (PMCMV) had increased the values of land consumption per capita since 2009 significantly, showing a clear expanding trend. The gradual replacement of green areas by residential settlements resulted in an increased LST. The PMCMV program contributed substantially to a change in land use and land cover, which increased the extent of urbanized areas and changed the local microclimate.

Land Consumption Monitoring with SAR Data and Multispectral Indices

Land consumption is the increase in artificial land cover, which is a major issue for environmental sustainability. In Italy, the Italian Institute for Environmental Protection and Research (ISPRA) and National System for Environmental Protection (SNPA) have the institutional duty to monitor land consumption yearly, through the photointerpretation of high-resolution images. This study intends to develop a methodology in order to produce maps of land consumption, by the use of the semi-automatic classification of multitemporal images, to reduce the effort of photointerpretation in detecting real changes. The developed methodology uses vegetation indices calculated over time series of images and decision rules. Three variants of the methodology were applied to detect the changes that occurred in Italy between the years 2018 and 2019, and the results were validated using ISPRA official data. The results show that the produced maps include large commission errors, but thanks to the developed methodology, the area to be photointerpreted was reduced to 7300 km2 (2.4% of Italian surface). The third variant of the methodology provided the highest detection of changes: 70.4% of the changes larger than 100 m2 (the pixel size) and over 84.0% of changes above 500 m2. Omissions are mainly related to single pixel changes, while larger changes are detected by at least one pixel in most of the cases. In conclusion, the developed methodology can improve the detection of land consumption, focusing photointerpretation work over selected areas detected automatically.

Urban Land Mapping Based on Remote Sensing Time Series in the Google Earth Engine Platform: A Case Study of the Teresina-Timon Conurbation Area in Brazil

Teresina-Timon conurbation (TTC) area is an example of urban agglomeration, situated in the semiarid environment of the northeast region of Brazil, which has shown an accelerated process of urban development over the last four decades (1985–2019). In this study, we developed a semi-automatic urban land mapping framework at the Google Earth Engine (GEE) platform to (a) evaluate spatiotemporal sprawl of the TTC area (1985–2018); and (b) quantify current urban fabric structures of TTC area (2019). The main empirical results demonstrate that the use of the Landsat historical dataset is a suitable option for generating consistent urban land maps across the years in semiarid environments. Teresina and Timon expanded, respectively, from 70.34 km2 and 12.20 km2 in 1985 to 159.02 km2 and 30.68 km2 in 2018, increasing annually at 3.05% and 3.69% averaged rate, showing an underlying tendency of continuous growth, and magnitude similar to Asian cities. The results of the urban fabric (UF) structures mapping demonstrates a high complexity of the urbanized surfaces, characterized by irregular shapes and variability of urban coverage. In 2019, the TTC metropolitan area was covered by urban land use classes as ceramic roofs, other types of roofs, and impervious surface, in the proportions of 28.02%, 11.97%, and 5.67%, respectively.

Machine Learning-Based Processing Proof-of-Concept Pipeline for Semi-Automatic Sentinel-2 Imagery Download, Cloudiness Filtering, Classifications, and Updates of Open Land Use/Land Cover Datasets

Land use and land cover are continuously changing in today’s world. Both domains, therefore, have to rely on updates of external information sources from which the relevant land use/land cover (classification) is extracted. Satellite images are frequent candidates due to their temporal and spatial resolution. On the contrary, the extraction of relevant land use/land cover information is demanding in terms of knowledge base and time. The presented approach offers a proof-of-concept machine-learning pipeline that takes care of the entire complex process in the following manner. The relevant Sentinel-2 images are obtained through the pipeline. Later, cloud masking is performed, including the linear interpolation of merged-feature time frames. Subsequently, four-dimensional arrays are created with all potential training data to become a basis for estimators from the scikit-learn library; the LightGBM estimator is then used. Finally, the classified content is applied to the open land use and open land cover databases. The verification of the provided experiment was conducted against detailed cadastral data, to which Shannon’s entropy was applied since the number of cadaster information classes was naturally consistent. The experiment showed a good overall accuracy (OA) of 85.9%. It yielded a classified land use/land cover map of the study area consisting of 7188 km2 in the southern part of the South Moravian Region in the Czech Republic. The developed proof-of-concept machine-learning pipeline is replicable to any other area of interest so far as the requirements for input data are met.

Generalized Vertical Components of built-up areas from global Digital Elevation Models by multi-scale linear regression modelling

The estimation of the vertical components of built-up areas from free Digital Elevation Model (DEM) global data filtered by multi-scale convolutional, morphological and textural transforms are generalized at the spatial resolution of 250 meters using linear least-squares regression techniques. Six test cases were selected: Hong Kong, London, New York, San Francisco, Sao Paulo, and Toronto. Five global DEM and two DEM composites are evaluated in terms of 60 combinations of linear, morphological and textural filtering and different generalization techniques. Four generalized vertical components estimates of built-up areas are introduced: the Average Gross Building Height (AGBH), the Average Net Building Height (ANBH), the Standard Deviation of Gross Building Height (SGBH), and the Standard Deviation of Net Building Height (SNBH). The study shows that the best estimation of the net GVC of built-up areas given by the ANBH and SNBH, always contains a greater error than their corresponding gross GVC estimation given by the AGBH and SGBH, both in terms of mean and standard deviation. Among the sources evaluated in this study, the best DEM source for estimating the GVC of built-up areas with univariate linear regression techniques is a composite of the 1-arcsec Shuttle Radar Topography Mission (SRTM30) and the Advanced Land Observing Satellite (ALOS) World 3D–30 m (AW3D30) using the union operator (CMP_SRTM30-AW3D30_U). A multivariate linear model was developed using 16 satellite features extracted from the CMP_SRTM30-AW3D30_U enriched by other land cover sources, to estimate the gross GVC. A RMSE of 2.40 m and 3.25 m was obtained for the AGBH and the SGBH, respectively. A similar multivariate linear model was developed to estimate the net GVC. A RMSE of 6.63 m and 4.38 m was obtained for the ANBH and the SNBH, respectively. The main limiting factors on the use of the available global DEMs for estimating the GVC of built-up areas are two. First, the horizontal resolution of these sources (circa 30 and 90 meters) corresponds to a sampling size that is larger than the expected average horizontal size of built-up structures as detected from nadir-angle Earth Observation (EO) data, producing more reliable estimates for gross vertical components than for net vertical component of built-up areas. Second, post-production processing targeting Digital Terrain Model specifications may purposely filter out the information on the vertical component of built-up areas that are contained in the global DEMs. Under the limitations of the study presented here, these results show a potential for using global DEM sources in order to derive statistically generalized parameters describing the vertical characteristics of built-up areas, at the scale of 250x250 meters. However, estimates need to be evaluated in terms of the specific requirements of target applications such as spatial population modelling, urban morphology, climate studies and so on.

Urbanization and health: The effects of the built environment on chronic disease risk factors among women in Tanzania

Sub-Saharan Africa is experiencing rapid urban growth. Cities enable greater access to health services and improved water and sanitation infrastructure, leading to some improvements in health. However, urban settings may also be associated with more sedentary, stressful lifestyles and consumption of less nutritious food. C-reactive protein (CRP) is a measure of chronic inflammation predictive of cardiovascular disease, and high body mass index (BMI), a ratio of weight to height, indicates overweight or obesity and is associated with an increased risk of many chronic diseases. To explore the association between urbanicity and these two markers, we overlaid data from the 2010 Tanzania Demographic and Health Survey (DHS) with a satellite-derived measure of built environment. Linear regression models were constructed for the outcomes of BMI and CRP, by 1) administratively defined urban/rural categorization from the DHS, 2) satellite derived built environment, and 3) built environment stratified by urban/rural. A total of 2,212 women were included; 23% had elevated CRP, 21% were overweight or obese. A third (33%) lived in a highly built up area and 29% lived in an area classified as urban. A strong positive association between both CRP and BMI and built environment was detected; log CRP increased 0.43 in the highest built up areas compared to not built up (p<0.05); log BMI increased 0.02 in the most built up areas compared to not built up (p<0.05). However, comparing urban to rural category was only significant in unadjusted models. Models stratified by urban/rural category highlight that the variation in CRP and BMI by built environment is mainly driven by rural areas; within urban areas there is less variation. Our findings highlight the potential negative effects of urbanicity on chronic disease markers, with potentially more change detected for those transitioning from rural to urban lifestyles. Satellite-derived urbanicity measures are reproducible and provide more nuanced understanding of effects of built environment on health.

Convolutional neural networks for global human settlements mapping from Sentinel-2 satellite imagery

Spatially consistent and up-to-date maps of human settlements are crucial for addressing policies related to urbanization and sustainability, especially in the era of an increasingly urbanized world. The availability of open and free Sentinel-2 data of the Copernicus Earth Observation program offers a new opportunity for wall-to-wall mapping of human settlements at a global scale. This paper presents a deep-learning-based framework for a fully automated extraction of built-up areas at a spatial resolution of 10 m from a global composite of Sentinel-2 imagery. A multi-neuro modeling methodology building on a simple Convolution Neural Networks architecture for pixel-wise image classification of built-up areas is developed. The core features of the proposed model are the image patch of size 5 × 5 pixels adequate for describing built-up areas from Sentinel-2 imagery and the lightweight topology with a total number of 1,448,578 trainable parameters and 4 2D convolutional layers and 2 flattened layers. The deployment of the model on the global Sentinel-2 image composite provides the most detailed and complete map reporting about built-up areas for reference year 2018. The validation of the results with an independent reference dataset of building footprints covering 277 sites across the world establishes the reliability of the built-up layer produced by the proposed framework and the model robustness. The results of this study contribute to cutting-edge research in the field of automated built-up areas mapping from remote sensing data and establish a new reference layer for the analysis of the spatial distribution of human settlements across the rural–urban continuum.

On the Reliable Generation of 3D City Models from Open Data

A 3D model communicates more effectively than a 2D model, hence the applications of 3D city models are rapidly gaining significance in urban studies. However, presently, there is a dearth of free of cost, high-resolution 3D city models available for use. This paper offers potential solutions to this problem by providing a globally replicable methodology to generate low-cost 3D city models from open source 2D building data in conjunction with open satellite-based elevation datasets. Two geographically and morphologically different case studies were used to develop and test this methodology: the Chinese city of Shanghai and the city of Nottingham in the UK. The method is based principally on OpenStreetMap (OSM) and Advanced Land Observing Satellite World 3D digital surface model (AW3D DSM) data and use GMTED 2010 DTM data for undulating terrain. Further enhancement of the resultant 3D model, though not compulsory, uses higher resolution elevation models that are not always open source, but if available can be used (i.e., airborne LiDAR generated DTM). Further we test and develop methods to improve the accuracy of the generated 3D models, employing a small subset of high resolution data that are not open source but can be purchased with a minimal budgets. Given these scenarios of data availability are globally applicable and time-efficient for 3D building generation (where 2D building footprints are available), our proposed methodology has the potential to accelerate the production of 3D city models, and thus to facilitate their dependent applications (e.g., disaster management) wherever commercial 3D city models are unavailable.

Towards Circumpolar Mapping of Arctic Settlements and Infrastructure Based on Sentinel-1 and Sentinel-2

Infrastructure expands rapidly in the Arctic due to industrial development. At the same time, climate change impacts are pronounced in the Arctic. Ground temperatures are, for example, increasing as well as coastal erosion. A consistent account of the current human footprint is needed in order to evaluate the impact on the environments as well as risk for infrastructure. Identification of roads and settlements with satellite data is challenging due to the size of single features and low density of clusters. Spatial resolution and spectral characteristics of satellite data are the main issues regarding their separation. The Copernicus Sentinel-1 and -2 missions recently provided good spatial coverage and at the same time comparably high pixel spacing starting with 10 m for modes available across the entire Arctic. The purpose of this study was to assess the capabilities of both, Sentinel-1 C-band Synthetic Aperture Radar (SAR) and the Sentinel-2 multispectral information for Arctic focused mapping. Settings differ across the Arctic (historic settlements versus industrial, locations on bedrock versus tundra landscapes) and reference data are scarce and inconsistent. The type of features and data scarcity demand specific classification approaches. The machine learning approaches Gradient Boosting Machines (GBM) and deep learning (DL)-based semantic segmentation have been tested. Records for the Alaskan North Slope, Western Greenland, and Svalbard in addition to high-resolution satellite data have been used for validation and calibration. Deep learning is superior to GBM with respect to users accuracy. GBM therefore requires comprehensive postprocessing. SAR provides added value in case of GBM. VV is of benefit for road identification and HH for detection of buildings. Unfortunately, the Sentinel-1 acquisition strategy is varying across the Arctic. The majority is covered in VV+VH only. DL is of benefit for road and building detection but misses large proportions of other human-impacted areas, such as gravel pads which are typical for gas and oil fields. A combination of results from both GBM (Sentinel-1 and -2 combined) and DL (Sentinel-2; Sentinel-1 optional) is therefore suggested for circumpolar mapping.

Sentinel-2 Data for Land Cover/Use Mapping: A Review

The advancement in satellite remote sensing technology has revolutionised the approaches to monitoring the Earth’s surface. The development of the Copernicus Programme by the European Space Agency (ESA) and the European Union (EU) has contributed to the effective monitoring of the Earth’s surface by producing the Sentinel-2 multispectral products. Sentinel-2 satellites are the second constellation of the ESA Sentinel missions and carry onboard multispectral scanners. The primary objective of the Sentinel-2 mission is to provide high resolution satellite data for land cover/use monitoring, climate change and disaster monitoring, as well as complementing the other satellite missions such as Landsat. Since the launch of Sentinel-2 multispectral instruments in 2015, there have been many studies on land cover/use classification which use Sentinel-2 images. However, no review studies have been dedicated to the application of ESA Sentinel-2 land cover/use monitoring. Therefore, this review focuses on two aspects: (1) assessing the contribution of ESA Sentinel-2 to land cover/use classification, and (2) exploring the performance of Sentinel-2 data in different applications (e.g., forest, urban area and natural hazard monitoring). The present review shows that Sentinel-2 has a positive impact on land cover/use monitoring, specifically in monitoring of crop, forests, urban areas, and water resources. The contemporary high adoption and application of Sentinel-2 can be attributed to the higher spatial resolution (10 m) than other medium spatial resolution images, the high temporal resolution of 5 days and the availability of the red-edge bands with multiple applications. The ability to integrate Sentinel-2 data with other remotely sensed data, as part of data analysis, improves the overall accuracy (OA) when working with Sentinel-2 images. The free access policy drives the increasing use of Sentinel-2 data, especially in developing countries where financial resources for the acquisition of remotely sensed data are limited. The literature also shows that the use of Sentinel-2 data produces high accuracies (>80%) with machine-learning classifiers such as support vector machine (SVM) and Random forest (RF). However, other classifiers such as maximum likelihood analysis are also common. Although Sentinel-2 offers many opportunities for land cover/use classification, there are challenges which include mismatching with Landsat OLI-8 data, a lack of thermal bands, and the differences in spatial resolution among the bands of Sentinel-2. Sentinel-2 data show promise and have the potential to contribute significantly towards land cover/use monitoring.

Comparative Assessment of Machine Learning Methods for Urban Vegetation Mapping Using Multitemporal Sentinel-1 Imagery

Mapping of green vegetation in urban areas using remote sensing techniques can be used as a tool for integrated spatial planning to deal with urban challenges. In this context, multitemporal (MT) synthetic aperture radar (SAR) data have not been equally investigated, as compared to optical satellite data. This research compared various machine learning methods using single-date and MT Sentinel-1 (S1) imagery. The research was focused on vegetation mapping in urban areas across Europe. Urban vegetation was classified using six classifiers—random forests (RF), support vector machine (SVM), extreme gradient boosting (XGB), multi-layer perceptron (MLP), AdaBoost.M1 (AB), and extreme learning machine (ELM). Whereas, SVM showed the best performance in the single-date image analysis, the MLP classifier yielded the highest overall accuracy in the MT classification scenario. Mean overall accuracy (OA) values for all machine learning methods increased from 57% to 77% with speckle filtering. Using MT SAR data, i.e., three and five S1 imagery, an additional increase in the OA of 8.59% and 13.66% occurred, respectively. Additionally, using three and five S1 imagery for classification, the F1 measure for forest and low vegetation land-cover class exceeded 90%. This research allowed us to confirm the possibility of MT C-band SAR imagery for urban vegetation mapping.

Accuracy assessment of Global Human Settlement Layer (GHSL) built-up products over China

Building a density map over large areas could provide essential information of land development intensity and settlement condition. It is crucial for supporting studies and planning of human settlement environment. The Global Human Settlement Layer (GHSL) is a comprehensive data set of mapping human settlement at a global scale, which was produced by the Joint Research Centre (JRC), European Commission. The built-up density is an important layer of GHSL data set. Currently, the validation of the GHSL built-up area products was preliminarily conducted over the United States and European countries. However, as a typical East Asian region, China is quite different from the United States, Europe, and other regions in terms of building forms and urban layouts. Therefore, it is necessary to perform an accuracy assessment of GHSL data set in Asian countries like China. With individual building footprint data of 20 typical cities in China, this paper presents our effort to validate the GHSL built-up area products. The aggregation mean and neighborhood search based algorithms are adopted for matching building footprint data and the GHSL products, through the regression analysis at per-pixel level, the building density map in raster format are generated as validation data. The accuracy index of GHSL built-up area was calculated for the study areas, and the validation methods were explored for GHSL built-up products at large scale. The results show that the built-up layer aggregated by the building footprint have the highest correlation with the coarse resolution GHSL built-up products, but GHSL tends to underestimate the building density of low-density areas and overestimate the areas with high density. This study suggests that GHSL built-up area products in 20 representative Chinese cities of China could provide quantitative information about built-up areas, but the product accuracy still need to be improved in the regions with heterogeneous formations of human settlements like China. There is a big picture of mapping high accuracy built-up density of China with the training data set acquired by the study.

The Use of Geographic Databases for Analyzing Changes in Land Cover—A Case Study of the Region of Warmia and Mazury in Poland

This article analyzes the applicability of spatial data for evaluating and monitoring changes in land use and their impact on the local landscape. The Coordination of Information on the Environment (CORINE) Land Cover database was used to develop a procedure and an indicator for analyzing changes in land cover, and the continuity of different land use types. Changes in land use types were evaluated based on land cover data. The results were analyzed over time to track changes in the evaluated region. The studied area was the Region of Warmia and Mazury in Poland. The preservation of homogeneous land cover plays a particularly important role in areas characterized by high natural value and an abundance of forests and water bodies. The study revealed considerable changes in land cover and landscape fragmentation in the analyzed region.

A Mapping Review on Urban Landscape Factors of Dengue Retrieved from Earth Observation Data, GIS Techniques, and Survey Questionnaires

To date, there is no effective treatment to cure dengue fever, a mosquito-borne disease which has a major impact on human populations in tropical and sub-tropical regions. Although the characteristics of dengue infection are well known, factors associated with landscape are highly scale dependent in time and space, and therefore difficult to monitor. We propose here a mapping review based on 78 articles that study the relationships between landscape factors and urban dengue cases considering household, neighborhood and administrative levels. Landscape factors were retrieved from survey questionnaires, Geographic Information Systems (GIS), and remote sensing (RS) techniques. We structured these into groups composed of land cover, land use, and housing type and characteristics, as well as subgroups referring to construction material, urban typology, and infrastructure level. We mapped the co-occurrence networks associated with these factors, and analyzed their relevance according to a three-valued interpretation (positive, negative, non significant). From a methodological perspective, coupling RS and GIS techniques with field surveys including entomological observations should be systematically considered, as none digital land use or land cover variables appears to be an univocal determinant of dengue occurrences. Remote sensing urban mapping is however of interest to provide a geographical frame to distribute human population and movement in relation to their activities in the city, and as spatialized input variables for epidemiological and entomological models.

The heterogeneity and change in the urban structure of metropolitan areas in the United States, 1990-2010

While the population of the United States has been predominantly urban for nearly 100 years, periodic transformations of the concepts and measures that define urban places and population have taken place, complicating over-time comparisons. We compare and combine data series of officially-designated urban areas, 1990-2010, at the census block-level within Metropolitan Statistical Areas (MSAs) with a satellite-derived consistent series on built-up area from the Global Human Settlement Layer to create urban classes that characterize urban structure and provide estimates of land and population. We find considerable heterogeneity in urban form across MSAs, even among those of similar population size, indicating the inherent difficulties in urban definitions. Over time, we observe slightly declining population densities and increasing land and population in areas captured only by census definitions or low built-up densities, constrained by the geography of place. Nevertheless, deriving urban proxies from satellite-derived built-up areas is promising for future efforts to create spatio-temporally consistent measures for urban land to guide urban demographic change analysis.

Fast Super-Resolution of 20 m Sentinel-2 Bands Using Convolutional Neural Networks

Images provided by the ESA Sentinel-2 mission are rapidly becoming the main source of information for the entire remote sensing community, thanks to their unprecedented combination of spatial, spectral and temporal resolution, as well as their associated open access policy. Due to a sensor design trade-off, images are acquired (and delivered) at different spatial resolutions (10, 20 and 60 m) according to specific sets of wavelengths, with only the four visible and near infrared bands provided at the highest resolution (10 m). Although this is not a limiting factor in general, many applications seem to emerge in which the resolution enhancement of 20 m bands may be beneficial, motivating the development of specific super-resolution methods. In this work, we propose to leverage Convolutional Neural Networks (CNNs) to provide a fast, upscalable method for the single-sensor fusion of Sentinel-2 (S2) data, whose aim is to provide a 10 m super-resolution of the original 20 m bands. Experimental results demonstrate that the proposed solution can achieve better performance with respect to most of the state-of-the-art methods, including other deep learning based ones with a considerable saving of computational burden.

Monitoring of Urbanization and Analysis of Environmental Impact in Stockholm with Sentinel-2A and SPOT-5 Multispectral Data

There has been substantial urban growth in Stockholm, Sweden, the fastest-growing capital in Europe. The intensifying urbanization poses challenges for environmental management and sustainable development. Using Sentinel-2 and SPOT-5 imagery, this research investigates the evolution of land-cover change in Stockholm County between 2005 and 2015, and evaluates urban growth impact on protected green areas, green infrastructure and urban ecosystem service provision. One scene of 2015 Sentinel-2A multispectral instrument (MSI) and 10 scenes of 2005 SPOT-5 high-resolution instruments (HRI) imagery over Stockholm County are classified into 10 land-cover categories using object-based image analysis and a support vector machine algorithm with spectral, textural and geometric features. Reaching accuracies of approximately 90%, the classifications are then analyzed to determine impact of urban growth in Stockholm between 2005 and 2015, including land-cover change statistics, landscape-level urban ecosystem service provision bundle changes and evaluation of regional and local impact on legislatively protected areas as well as ecologically significant green infrastructure networks. The results indicate that urban areas increased by 15%, while non-urban land cover decreased by 4%. In terms of ecosystem services, changes in proximity of forest and low-density built-up areas were the main cause of lowered provision of temperature regulation, air purification and noise reduction. There was a decadal ecosystem service loss of 4.6 million USD (2015 exchange rate). Urban areas within a 200 m buffer zone around the Swedish environmental protection agency’s nature reserves increased 16%, with examples of urban areas constructed along nature reserve boundaries. Urban expansion overlapped the deciduous ecological corridor network and green wedge/core areas to a small but increasing degree, often in close proximity to weak but important green links in the landscape. Given these findings, increased conservation/restoration focus on the region’s green weak links is recommended.

Multi-Scale Estimation of Land Use Efficiency (SDG 11.3.1) across 25 Years Using Global Open and Free Data

Sustainable Development Goal (SDG) 11 aspires to “Make cities and human settlements inclusive, safe, resilient and sustainable”, and the introduction of an explicit urban goal testifies to the importance of urbanisation. The understanding of the process of urbanisation and the capacity to monitor the SDGs require a wealth of open, reliable, locally yet globally comparable data, and a fully-fledged data revolution. In this framework, the European Commission–Joint Research Centre has developed a suite of (open and free) data and tools named Global Human Settlement Layer (GHSL) which maps the human presence on Earth (built-up areas, population distribution and settlement typologies) between 1975 and 2015. The GHSL supplies information on the progressive expansion of built-up areas on Earth and population dynamics in human settlements, with both sources of information serving as baseline data to quantify land use efficiency (LUE), listed as a Tier II indicator for SDG 11 (11.3.1). In this paper, we present the profile of the LUE across several territorial scales between 1990 and 2015, highlighting diverse development trajectories and the land take efficiency of different human settlements. Our results show that (i) the GHSL framework allows us to estimate LUE for the entire planet at several territorial scales, opening the opportunity of lifting the LUE indicator from its Tier II classification; (ii) the current formulation of the LUE is substantially subject to path dependency; and (iii) it requires additional spatially-explicit metrics for its interpretation. We propose the Achieved Population Density in Expansion Areas and the Marginal Land Consumption per New Inhabitant metrics for this purpose. The study is planetary and multi-temporal in coverage, demonstrating the value of well-designed, open and free, fine-scale geospatial information on human settlements in supporting policy and monitoring progress made towards meeting the SDGs.

Discriminating Urban Forest Types from Sentinel-2A Image Data through Linear Spectral Mixture Analysis: A Case Study of Xuzhou, East China

Urban forests are an important component of the urban ecosystem. Urban forest types are a key piece of information required for monitoring the condition of an urban ecosystem. In this study, we propose an urban forest type discrimination method based on linear spectral mixture analysis (LSMA) and a support vector machine (SVM) in the case study of Xuzhou, east China. From 10-m Sentinel-2A imagery data, three different vegetation endmembers, namely broadleaved forest, coniferous forest, and low vegetation, and their abundances were extracted through LSMA. Using a combination of image spectra, topography, texture, and vegetation abundances, four SVM classification models were performed and compared to investigate the impact of these features on classification accuracy. With a particular interest in the role that vegetation abundances play in classification, we also compared SVM and other classifiers, i.e., random forest (RF), artificial neural network (ANN), and quick unbiased efficient statistical tree (QUEST). Results indicate that (1) the LSMA method can derive accurate vegetation abundances from Sentinel-2A image data, and the root-mean-square error (RMSE) was 0.019; (2) the classification accuracies of the four SVM models were improved after adding topographic features, textural features, and vegetation abundances one after the other; (3) the SVM produced higher classification accuracies than the other three classifiers when identical classification features were used; and (4) vegetation endmember abundances improved classification accuracy regardless of which classifier was used. It is concluded that Sentinel-2A image data has a strong capability to discriminate urban forest types in spectrally heterogeneous urban areas, and that vegetation abundances derived from LSMA can enhance such discrimination.

Evaluation of the Potential of Convolutional Neural Networks and Random Forests for Multi-Class Segmentation of Sentinel-2 Imagery

Motivated by the increasing availability of open and free Earth observation data through the Copernicus Sentinel missions, this study investigates the capacity of advanced computational models to automatically generate thematic layers, which in turn contribute to and facilitate the creation of land cover products. In concrete terms, we assess the practical and computational aspects of multi-class Sentinel-2 image segmentation based on a convolutional neural network and random forest approaches. The annotated learning set derives from data that is made available as result of the implementation of European Union’s INSPIRE Directive. Since this network of data sets remains incomplete in regard to some geographic areas, another objective of this work was to provide consistent and reproducible ways for machine-driven mapping of these gaps and a potential update of the existing ones. Finally, the performance analysis identifies the most important hyper-parameters, and provides hints on the models’ deployment and their transferability.

Urbanization in India: Population and Urban Classification Grids for 2011

India is the world’s most populous country, yet also one of the least urban. It has long been known that India’s official estimates of urban percentages conflict with estimates derived from alternative conceptions of urbanization. To date, however, the detailed spatial and settlement boundary data needed to analyze and reconcile these differences have not been available. This paper presents gridded estimates of population at a resolution of 1 km along with two spatial renderings of urban areas—one based on the official tabulations of population and settlement types (i.e., statutory towns, outgrowths, and census towns) and the other on remotely-sensed measures of built-up land derived from the Global Human Settlement Layer. We also cross-classified the census data and the remotely-sensed data to construct a hybrid representation of the continuum of urban settlement. In their spatial detail, these materials go well beyond what has previously been available in the public domain, and thereby provide an empirical basis for comparison among competing conceptual models of urbanization.

Principles and Applications of the Global Human Settlement Layer as Baseline for the Land Use Efficiency Indicator—SDG 11.3.1

The Global Human Settlement Layer (GHSL) produces new global spatial information, evidence-based analytics describing the human presence on the planet that is based mainly on two quantitative factors: (i) the spatial distribution (density) of built-up structures and (ii) the spatial distribution (density) of resident people. Both of the factors are observed in the long-term temporal domain and per unit area, in order to support the analysis of the trends and indicators for monitoring the implementation of the 2030 Development Agenda and the related thematic agreements. The GHSL uses various input data, including global, multi-temporal archives of high-resolution satellite imagery, census data, and volunteered geographic information. In this paper, we present a global estimate for the Land Use Efficiency (LUE) indicator—SDG 11.3.1, for circa 10,000 urban centers, calculating the ratio of land consumption rate to population growth rate between 1990 and 2015. In addition, we analyze the characteristics of the GHSL information to demonstrate how the original frameworks of data (gridded GHSL data) and tools (GHSL tools suite), developed from Earth Observation and integrated with census information, could support Sustainable Development Goals monitoring. In particular, we demonstrate the potential of gridded, open and free, local yet globally consistent, multi-temporal data in filling the data gap for Sustainable Development Goal 11. The results of our research demonstrate that there is potential to raise SDG 11.3.1 from a Tier II classification (manifesting unavailability of data) to a Tier I, as GHSL provides a global baseline for the essential variables called by the SDG 11.3.1 metadata.

Comparative Evaluation of the Spectral and Spatial Consistency of Sentinel-2 and Landsat-8 OLI Data for Igneada Longos Forest

This study aims to test the spectral and spatial consistency of Sentinel-2 and Landsat-8 OLI data for the potential of monitoring longos forests for four seasons in Igneada, Turkey. Vegetation indices, including Normalized Difference Vegetation Index (NDVI), Enhanced Vegetation Index (EVI) and Normalized Difference Water Index (NDWI), were generated for the study area in addition to the five corresponding bands of Sentinel-2 and Landsat-8 OLI Images. Although the spectral consistency of the data was interpreted by cross-calibration analysis using the Pearson correlation coefficient, spatial consistency was evaluated by descriptive statistical analysis of investigated variables. In general, the highest correlation values were achieved for the images that were acquired in the spring season for almost all investigated variables. In the spring season, among the investigated variables, the Red band (B4), NDVI and EVI have the largest correlation coefficients of 0.94, 0.92 and 0.91, respectively. Regarding the spatial consistency, the mean and standard deviation values of all variables were consistent for all seasons except for the mean value of the NDVI for the fall season. As a result, if there is no atmospheric effect or data retrieval/acquisition error, either Landsat-8 or Sentinel-2 can be used as a combination or to provide the continuity data in longos monitoring applications. This study contributes to longos forest monitoring science in terms of remote sensing data analysis.

Understanding urbanization: A study of census and satellite-derived urban classes in the United States, 1990-2010

Most of future population growth will take place in the world’s cities and towns. Yet, there is no well-established, consistent way to measure either urban land or people. Even census-based urban concepts and measures undergo frequent revision, impeding rigorous comparisons over time and place. This study presents a new spatial approach to derive consistent urban proxies for the US. It compares census-designated urban blocks with proxies for land-based classifications of built-up areas derived from time-series of the Global Human Settlement Layer (GHSL) for 1990–2010. This comparison provides a new way to understand urban structure and its changes: Most land that is more than 50% built-up, and people living on such land, are officially classified as urban. However, 30% of the census-designated urban population and land is located in less built-up areas that can be characterized as mainly suburban and peri-urban in nature. Such insights are important starting points for a new urban research program: creating globally and temporally consistent proxies to guide modelling of urban change.

An Improved Boosting Learning Saliency Method for Built-Up Areas Extraction in Sentinel-2 Images

Built-up areas extraction from satellite images is an important aspect of urban planning and land use; however, this remains a challenging task when using optical satellite images. Existing methods may be limited because of the complex background. In this paper, an improved boosting learning saliency method for built-up area extraction from Sentinel-2 images is proposed. First, the optimal band combination for extracting such areas from Sentinel-2 data is determined; then, a coarse saliency map is generated, based on multiple cues and the geodesic weighted Bayesian (GWB) model, that provides training samples for a strong model; a refined saliency map is subsequently obtained using the strong model. Furthermore, cuboid cellular automata (CCA) is used to integrate multiscale saliency maps for improving the refined saliency map. Then, coarse and refined saliency maps are synthesized to create a final saliency map. Finally, the fractional-order Darwinian particle swarm optimization algorithm (FODPSO) is employed to extract the built-up areas from the final saliency result. Cities in five different types of ecosystems in China (desert, coastal, riverside, valley, and plain) are used to evaluate the proposed method. Analyses of results and comparative analyses with other methods suggest that the proposed method is robust, with good accuracy.

Combined Use of Optical and Synthetic Aperture Radar Data for REDD+ Applications in Malawi

Recent developments in satellite data availability allow tropical forest monitoring to expand in two ways: (1) dense time series foster the development of new methods for mapping and monitoring dry tropical forests and (2) the combination of optical data and synthetic aperture radar (SAR) data reduces the problems resulting from frequent cloud cover and yields additional information. This paper covers both issues by analyzing the possibilities of using optical (Sentinel-2) and SAR (Sentinel-1) time series data for forest and land cover mapping for REDD+ (Reducing Emissions from Deforestation and Forest Degradation) applications in Malawi. The challenge is to combine these different data sources in order to make optimal use of their complementary information content. We compare the results of using different input data sets as well as of two methods for data combination. Results show that time-series of optical data lead to better results than mono-temporal optical data (+8% overall accuracy for forest mapping). Combination of optical and SAR data leads to further improvements: +5% in overall accuracy for land cover and +1.5% for forest mapping. With respect to the tested combination methods, the data-based combination performs slightly better (+1% overall accuracy) than the result-based Bayesian combination.

Delineation of Built-Up Areas from Very High-Resolution Satellite Imagery Using Multi-Scale Textures and Spatial Dependence

Very high spatial resolution (VHR) satellite images possess several advantages in terms of describing the details of ground targets. Extracting built-up areas from VHR images has received increasing attention in practical applications, such as land use planning, urbanization monitoring, geographic information database update. In this study, a novel method is proposed for built-up area detection and delineation on VHR satellite images, using multi-resolution space-frequency analysis, spatial dependence modelling and cross-scale feature fusion. First, the image is decomposed by multi-resolution wavelet transformation, and then the high-frequency information at different levels is employed to represent the multi-scale texture and structural characteristics of built-up areas. Subsequently, the local Getis-Ord statistic is introduced to model the spatial patterns of built-up area textures and structures by measuring the spatial dependence among frequency responses at different spatial positions. Finally, the saliency map of built-up areas is produced using a cross-scale feature fusion algorithm, followed by adaptive threshold segmentation to obtain the detection results. The experiments on ZY-3 and Quickbird datasets demonstrate the effectiveness and superiority of the proposed method through comparisons with existing algorithms.

Extraction of High-Precision Urban Impervious Surfaces from Sentinel-2 Multispectral Imagery via Modified Linear Spectral Mixture Analysis

This study explores the performance of Sentinel-2A Multispectral Instrument (MSI) imagery for extracting urban impervious surface using a modified linear spectral mixture analysis (MLSMA) method. Sentinel-2A MSI provided 10 m red, green, blue, and near-infrared spectral bands, and 20 m shortwave infrared spectral bands, which were used to extract impervious surfaces. We aimed to extract urban impervious surfaces at a spatial resolution of 10 m in the main urban area of Guangzhou, China. In MLSMA, a built-up image was first extracted from the normalized difference built-up index (NDBI) using the Otsu’s method; the high-albedo, low-albedo, vegetation, and soil fractions were then estimated using conventional linear spectral mixture analysis (LSMA). The LSMA results were post-processed to extract high-precision impervious surface, vegetation, and soil fractions by integrating the built-up image and the normalized difference vegetation index (NDVI). The performance of MLSMA was evaluated using Landsat 8 Operational Land Imager (OLI) imagery. Experimental results revealed that MLSMA can extract the high-precision impervious surface fraction at 10 m with Sentinel-2A imagery. The 10 m impervious surface map of Sentinel-2A is capable of recovering more detail than the 30 m map of Landsat 8. In the Sentinel-2A impervious surface map, continuous roads and the boundaries of buildings in urban environments were clearly identified.

Remote Sensing Derived Built-Up Area and Population Density to Quantify Global Exposure to Five Natural Hazards over Time

Exposure is reported to be the biggest determinant of disaster risk, it is continuously growing and by monitoring and understanding its variations over time it is possible to address disaster risk reduction, also at the global level. This work uses Earth observation image archives to derive information on human settlements that are used to quantify exposure to five natural hazards. This paper first summarizes the procedure used within the global human settlement layer (GHSL) project to extract global built-up area from 40 year deep Landsat image archive and the procedure to derive global population density by disaggregating population census data over built-up area. Then it combines the global built-up area and the global population density data with five global hazard maps to produce global layers of built-up area and population exposure to each single hazard for the epochs 1975, 1990, 2000, and 2015 to assess changes in exposure to each hazard over 40 years. Results show that more than 35% of the global population in 2015 was potentially exposed to earthquakes (with a return period of 475 years); one billion people are potentially exposed to floods (with a return period of 100 years). In light of the expansion of settlements over time and the changing nature of meteorological and climatological hazards, a repeated acquisition of human settlement information through remote sensing and other data sources is required to update exposure and risk maps, and to better understand disaster risk and define appropriate disaster risk reduction strategies as well as risk management practices. Regular updates and refined spatial information on human settlements are foreseen in the near future with the Copernicus Sentinel Earth observation constellation that will measure the evolving nature of exposure to hazards. These improvements will contribute to more detailed and data-driven understanding of disaster risk as advocated by the Sendai Framework for Disaster Risk Reduction.

Comparison of Random Forest, k-Nearest Neighbor, and Support Vector Machine Classifiers for Land Cover Classification Using Sentinel-2 Imagery

In previous classification studies, three non-parametric classifiers, Random Forest (RF), k-Nearest Neighbor (kNN), and Support Vector Machine (SVM), were reported as the foremost classifiers at producing high accuracies. However, only a few studies have compared the performances of these classifiers with different training sample sizes for the same remote sensing images, particularly the Sentinel-2 Multispectral Imager (MSI). In this study, we examined and compared the performances of the RF, kNN, and SVM classifiers for land use/cover classification using Sentinel-2 image data. An area of 30 × 30 km² within the Red River Delta of Vietnam with six land use/cover types was classified using 14 different training sample sizes, including balanced and imbalanced, from 50 to over 1250 pixels/class. All classification results showed a high overall accuracy (OA) ranging from 90% to 95%. Among the three classifiers and 14 sub-datasets, SVM produced the highest OA with the least sensitivity to the training sample sizes, followed consecutively by RF and kNN. In relation to the sample size, all three classifiers showed a similar and high OA (over 93.85%) when the training sample size was large enough, i.e., greater than 750 pixels/class or representing an area of approximately 0.25% of the total study area. The high accuracy was achieved with both imbalanced and balanced datasets.

Synergetic Use of Sentinel-1 and Sentinel-2 Data for Soil Moisture Mapping at 100 m Resolution

The recent deployment of ESA’s Sentinel operational satellites has established a new paradigm for remote sensing applications. In this context, Sentinel-1 radar images have made it possible to retrieve surface soil moisture with a high spatial and temporal resolution. This paper presents two methodologies for the retrieval of soil moisture from remotely-sensed SAR images, with a spatial resolution of 100 m. These algorithms are based on the interpretation of Sentinel-1 data recorded in the VV polarization, which is combined with Sentinel-2 optical data for the analysis of vegetation effects over a site in Urgell (Catalunya, Spain). The first algorithm has already been applied to observations in West Africa by Zribi et al., 2008, using low spatial resolution ERS scatterometer data, and is based on change detection approach. In the present study, this approach is applied to Sentinel-1 data and optimizes the inversion process by taking advantage of the high repeat frequency of the Sentinel observations. The second algorithm relies on a new method, based on the difference between backscattered Sentinel-1 radar signals observed on two consecutive days, expressed as a function of NDVI optical index. Both methods are applied to almost 1.5 years of satellite data (July 2015–November 2016), and are validated using field data acquired at a study site. This leads to an RMS error in volumetric moisture of approximately 0.087 m³/m³ and 0.059 m³/m³ for the first and second methods, respectively. No site calibrations are needed with these techniques, and they can be applied to any vegetation-covered area for which time series of SAR data have been recorded.