The time-varying areal extent and duration of surface melt on ice sheets are important parameters for climate and cryosphere research and key indicators of climate change in polar regions. To evaluate snowmelt dynamics and melting/refreezing processes in Greenland and Antarctica, we developed and implemented an algorithm for generating time-series of surface melt extent and melt phases (dry, wet refreezing) based on the analysis of continuous time series of C-band active microwave satellite data. Our results, based on METOP ASCAT scatterometer and Sentinel-1 SAR data, demonstrate the excellent capability of these missions for operational monitoring of snowmelt areas, providing a consistent climate data record on the presence of liquid water in snow and firn areas of Greenland and Antarctica for studying surface melt processes and ice sheet mass loss.

Satellite image time series (SITS), such as those by Sentinel-2 (S2) satellites, provides a large amount of information due to their combined temporal, spatial, and spectral resolutions. The high revisit frequency and spatial resolution of S2 result in: 1) increase in the probability of acquiring cloud-free images and 2) availability of detailed information for analyzing small objects. These characteristics are of interest in precision agriculture, where temporally dense SITS can benefit the understanding of crop behaviors. In the past, information about agricultural practices has been collected over large regions and focused on mixed/aggregated crops due to the poor tradeoff between the spatial and temporal resolutions. Products have been generated at low spatial resolution and daily basis or at high spatial resolution and weekly/monthly basis. They are meaningful for large agricultural fields, whereas they are limited when fields show a small average size. In this context, S2 characteristics allow for both high spatial and temporal resolution products. However, no existing automatic method effectively separates small fields from each other in an unsupervised way and deals with data irregularly sampled in time. Thus, this article presents a method suitable for the analysis of small crop fields in S2 dense SITS that accounts for S2 characteristics. The method fuses spatio-temporal information, analyzes data spatio-temporal evolution, and extracts relevant spatio-temporal information. The effectiveness of the proposed method was corroborated by experiments carried out on S2-SITS acquired over an area located in Barrax, Spain.

This paper presents an unsupervised approach that extracts reliable labeled units from outdated maps to update them using time series (TS) of recent multispectral (MS) images. The method assumes that: 1) the source of the map is unknown and may be different from remote sensing data; 2) no ground truth is available; 3) the map is provided at polygon level, where the polygon label represents the dominant class; and 4) the map legend can be converted into a set of classes discriminable with the TS of images (i.e., no land-use classes that require manual analysis are considered). First, the outdated map is adapted to the spatial and spectral properties of the MS images. Then, the method identifies reliable labeled units in an unsupervised way by a two-step procedure: 1) a clustering analysis performed at polygon level to detect samples correctly associated to their labels and 2) a consistency analysis to discard polygons far from the distribution of the related land-cover class (i.e., having high probability of being mislabeled). Finally, the map is updated by classifying the recent TS of MS image with an ensemble of classifiers trained using only the reference data derived from the map. The experimental results obtained updating the 2012 Corine Land Cover (CLC) and the GlobLand30 in Trentino Alto Adige (Italy) achieved 93.2% and 93.3% overall accuracy (OA) on the validation data set. The method increased the OA up to 18% and 11.5% with respect to the reference methods on the 2012 CLC and the GlobLand30, respectively.

Satellite Image Time Series (SITS), such as the ones acquired by the new Sentinel-2 (S2), combine a large amount of information compared to previous satellite generations since a better trade-off in terms of spatial/spectral/temporal resolutions is guaranteed. The specific characteristic of acquiring images under overlapped orbits, offered by S2, results in: i) availability of irregularly sampled acquisitions and ii) increase of the probability to acquire cloud free images over time. This characteristic becomes relevant in the agricultural analysis, where availability of dense SITS is required to map and analyze fast working crop behaviors. In the literature, several methods exist that extract phenological parameters for agricultural analysis, but none of them is able to deal with irregularly sampled data. Thus, this paper presents an approach for derivation of cropland phenological parameters from irregularly sampled S2-SITS. Experimental results obtained on S2-SITS acquired over Barrax, Spain, confirm the effectiveness of the proposed approach.

Combining existing thematic vector products and recently acquired satellite images to generate regular updated maps is extremely interesting at operational level. However, employing these maps is not straightforward. They are typically provided at polygon level, where the polygon labels do not necessarily correspond to spectrally homogeneous areas. Moreover, usually there is a semantic gap between the map legend and the set of natural classes discriminable in multispectral images. To overcome these issues, this paper presents a method that first performs a domain understanding to detect the discrepancies between the vector map domain and the multispectral (MS) image domain. Then, it accomplishes a domain modeling which uses a MS image contemporary to the map to extract a set of reliable and informative samples from the map. Finally, the method carries out Domain Adaptation (DA) using a recent MS image to update the map. Experimental results obtained updating a crop thematic map in Czech Republic confirm the effectiveness of the method.

We propose a system for detecting clear-cuts in Sentinel-2 (S-2) images of the Indonesian forest by means of an adaptive and unsupervised multivariate Change Vector Analysis (CVA) method. By leveraging on the unique spatial and spectral characteristics of the S- 2 mission, the proposed method characterizes a relevant portion of the target change as lying in a Gaussian neighborhood of the spectral stacked bi-temporal domain of the change. The processing system analyzes all the available bi-temporal pairs in the time series, enabling us to: (1) partially recovering lost information due to cloud coverage, and (2) providing a representation of the change evolving in time. The system is fully automated and potentially operational ready, so it can be used to provide accurate information about clear-cuts at the country scale in Indonesia.

This paper presents an approach to the update of land-cover maps by classifying Remote Sensing (RS) images in an unsupervised way. The proposed method assumes that: i) an old thematic map is available; ii) no ground truth data are available; iii) the source used to generate the available thematic map is unknown. To classify the most recent RS image available on the considered area, the method automatically extracts from the considered land-cover map a “pseudo” training set. First, a preprocessing phase adapts the map to the properties of the RS data. Then, we perform an automatic “pseudo” training set identification to select the most reliable samples from the existing thematic map. Finally, a consistency check is defined to determine whether the inconsistencies between the updated and the original maps are due to real changes on the ground or classification errors. Experimental results obtained by updating the 2012 Corine Land Cover Map (CLC) in Trentino, Italy, using Sentinel 2 (S2) images confirm the effectiveness of the proposed method.

The overall process commonly referred to as Ocean Acidification (OA) is nowadays gathering increasing attention for its profound impact at scientific and socio-economic level. To date, the majority of the scientific studies into the potential impacts of OA have focused on models and in situ datasets. Satellite remote sensing technology have yet to be fully exploited and could play a significant role by providing synoptic and frequent measurements for investigating OA processes on global scales. Within this context, the purpose of the ESA “Pathfinders-OA” project is to quantitatively and routinely estimate surface ocean pH by means of satellite observations in several ocean regions. Satellite Ocean Colour, Sea Surface Temperature and Sea Surface Salinity data (with an emphasis on the latter) will be exploited. A proper merging of these different datasets will allow to compute at least two independent proxies among the seawater carbonate system parameters and therefore obtain the best educated guess of the surface ocean pH. Preliminary results of the anomaly and variability of the ocean pH maps are presented.

The performances of a novel salinity retrieval strategy by means of Support Vector Regression (SVR) have been studied. The SMOS satellite brightness temperatures measurements and additional auxiliary parameters have been co-located with salinity data collected by Argo buoys, which represented the ground-truth to be matched by the algorithm. Salinity fields estimated by the SVR with a combination of features and at two polarizations are in good agreement with the ground-truth data. A critical additional feature that was studied was the TB/emissivity incidence angle dependency, analyzing the possible performances improvements due to the multi-angular information content. The robustness and versatility of this approach are under further assessment over wider areas and time lags, and in various combinations of SMOS features.

The European Space Agency Soil Moisture and Ocean Salinity mission aims at estimating, over the oceans, sea surface salinity (SSS) with spatial and temporal coverage adequate for large-scale oceanography. Spatiotemporal averaging of the retrieved SSS [level-3 (L3) product] has to be properly performed in order to meet the challenging mission requirements. At high latitudes, the generally low sea surface temperature (SST) characterizing the ocean degrades the brightness temperature sensitivity to SSS, but conversely, an improvement in the L3 retrieved SSS performances should be expected due to an increased pixel sampling. This tradeoff between geophysical effects in cold seawater and the concomitant temporal oversampling has been addressed by analyzing the latitudinal trend of the retrieved salinity performances, in various retrieval configurations and settings, once a conservative and optimal data filtering strategy is applied. Quantitative rate of changes of the SSS retrieval performance with the SST variability is provided, together with the net oversampling contribution to the L3 SSS accuracy. The experiments carried out demonstrate that the high-latitude oversampling does not compensate for the SST-driven latitudinal degradation of the L3 SSS product quality.

This paper addresses a specific typology of land-cover classification problems, hereinafter referred to as “targeted land-cover classification,” where the objective is the identification of only one or few specific “targeted” land-cover classes of interest, disregarding all the other potential classes present in the area under analysis. Such a challenging problem, which is common to a variety of operational information services and applications (e.g., agriculture, forestry, spatial planning, ecosystem monitoring, disaster management, habitat mapping, etc.), can be effectively solved by traditional supervised classification techniques provided that an exhaustive ground truth is available for all the land-cover classes present in the region of interest. Such a requirement is seldom satisfied and presents several practical drawbacks and limitations, both in terms of time and economic cost that may render this task difficult to achieve in most real-life cases. However, the possibility to perform an effective targeted classification using only ground-truth samples for the class(es) of interest (hence avoiding the burden and cost associated with the collection of a full and exhaustive ground-truth information) would represent a significant advantage. In this paper, we present a novel technique capable of identifying specific land-cover classes of interest by exploiting the ground truth only available for these targeted classes, while providing accuracies comparable to those of traditional fully supervised methods. The proposed technique jointly exploits both the unlabeled samples of the image under investigation and the training samples only available for the targeted classes. In particular, the expectation-maximization algorithm and Markov random fields are employed to estimate the probability density function of both the class(es) of interest and the unknown class representing the merger of all the unknown land-cover classes characterizing the study area for which no ground-truth information is available. An extensive experimental analysis and cross-comparisons with both fully supervised support vector machines and ensembles of multiple one-class support-vector-data-description classifiers on different data sets confirmed the effectiveness and the reliability of the proposed technique.

A sounding of the capabilities of a novel salinity retrieval strategy by means of Support Vector Regression (SVR) has been performed. SMOS brightness temperatures measurements and additional auxiliary parameters have been co-located with salinity data collected by ARGO buoys, which represented the ground-truth to be matched by the algorithm. Salinity fields estimated by the SVR are in good agreement with the ground-truth, suggesting that the chosen approach can be promising, despite its robustness and versatility are under further assessment over wider areas and time lags, and in various combinations of SMOS features.

In several real-world applications the objective of landcover classification is actually limited to map one or few specific “targeted” land-cover classes over a certain area. In such cases, ground truth is generally available for the only land-cover classes of interest, which limits (or hinders) the possibility of successfully employing standard supervised approaches that require an exhaustive ground truth for all the land-cover classes characterizing the investigated area. In this paper, we present a novel technique capable of addressing this challenging issue by exploiting the only ground truth available for the only land-cover classes of interest. In particular, the proposed method exploits the expectation-maximization (EM) algorithm and an iterative labeling strategy based on Markov random fields (MRF) accounting for spatial correlation. Experimental results confirmed the effectiveness and the reliability of the proposed technique.

A preliminary attempt of deriving a purely satellite-based Temperature-Salinity (T-S) diagram is presented, with the overall aim of assessing to what extent is possible, and in which geographical areas, to identify and trace water masses by satellite. This has been performed by using recent SMOS and Aquarius satellite SSS products in conjunction with spaceborne SST data. A baseline T-S diagram is arranged from climatology data, differentiating 7 ocean zones and mapping them into the T-S domain. Therefore, a comparison with satellite data is carried out, highlighting, for this preliminary test, which are the most challenging zones and where, in turn, they mutually agree in a reasonable way.

A prospective sounding of the capabilities of a novel salinity retrieval by means of Support Vector Regression has been performed. Co-located SMOS measurements and additional auxiliary parameters have been considered, whilst salinity data collected by ARGO buoys represented the ground-truth to be matched by the algorithm. Salinity fields estimated by the SVR are in good agreement with the ground-truth, suggesting that the chosen approach can be promising, despite its robustness and versatility needs to be assessed over wider areas and time lags, and in various combinations of SMOS features.

ESA provides operational routines to calculate the SMOS Level-2 product soil moisture from the radiometer Tb. But, the radiative transfer from measured Tb into soil moisture is influenced by several conditions such as soil surface roughness and vegetation opacity, which are parameterized in a general way. These cannot be easily measured at the scale of SMOS observation. The absolute values of these parameters for different land surfaces are uncertain, and the degree of this uncertainty is unknown as well. In addition, recent studies found that SMOS overestimates Tb. In this paper, we present a method to enhance the accuracy of the SMOS soil moisture product by parameter estimation using a data assimilation technique (Sampling Importance Resampling Particle Filter SIR-PF) with in-situ soil moisture observations. Therefore, we performed a synthetic study to analyze the ability of the system to track the temporal evolution of parameters such as vegetation opacity and soil surface roughness. To generate a soil moisture and soil temperature reference the hydrological model HYDRUS-1D was used. Based on this, the L-band Microwave Emission of the Biosphere (L-MEB) forward model was run and perturbed according to the measurement accuracy of MIRAS to simulate the SMOS Tb observations. L-MEB was integrated into a data assimilation framework using the SIR-PF, which is able to concurrently update L- MEB states and parameters. In addition, we investigate the ability of the proposed approach to account for the SMOS observation bias by introducing a bias factor in L-MEB. The overall advantage of the proposed sequential approach is its ability to be integrated into the operational near real time processing of the Level-2 product. The objectives of this study are: (i) to retrieve radiative transfer parameters and their temporal changes and (ii) to account for a bias in SMOS measurements.

In several application domains (e.g., crop conversion subsidies, forestry, natural hazard mapping, and spatial planning), the ultimate operational objective of change-detection analysis is actually limited to the identification of only one (or few) specific land-cover transition(s) of interest (i.e., a "targeted" change detection problem), disregarding all the other potential changes occurring in the area under analysis at the same time. Supervised change-detection techniques generally represent the most accurate methodological solution for mapping land-cover changes while identifying the associated land-cover transitions between two different dates. However, the application of these techniques depends on the availability of exhaustive ground-truth information for all the land-cover classes present in the area of interest at the times under investigation. Such a requirement is seldom satisfied since gathering a reliable ground truth for all the classes characterizing the considered scenes at the two dates under analysis presents several practical drawbacks and limitations (both in terms of time and economic cost) that may render this task almost impossible in most real-life cases. Nevertheless, to solve these specific types of problems, it would be highly beneficial for an operator to rely on a robust automatic technique that may allow an effective detection of the "targeted" land-cover transitions by taking into account only ground-truth information for the few classes of interest at each date (thus, avoiding the burden and cost associated to the collection of a full and exhaustive ground-truth data set at both times). In this paper, we address this challenging issue and propose a novel technique (formulated in terms of a compound decision problem) capable of identifying specific "targeted" land-cover transitions by exploiting the ground truth available only for the classes of interest at the two dates, while providing accuracies comparable to those of traditional fully supervised change-detection methods. The proposed technique relies on a partially supervised approach that jointly exploits the expectation-maximization algorithm and an iterative labeling strategy based on Markov random fields accounting for spatial and temporal correlation between the two images. Moreover, the proposed method is applicable to images acquired by different sensors (or to different sets of features) at the two investigated times. Experimental results on different multitemporal and multisensor data sets confirmed the effectiveness and the reliability of the proposed technique.

The ESA DUE project ¿DIVERSITY aimed at supporting the implementation of the UN Convention on Biological Diversity by establishing dedicated information services based on repeatable approaches and earth observation data from space. The experiences gained in the project can support the objective of developing a Global Biodiversity Observation System with respect to data and products specifications and priorities.

The DesertWatch ESA DUE project, recently successfully completed, aimed at developing an integrated information system tailored on the specific user needs, built on the technological transfer of the most significant results of the related research projects. The resulting DesertWatch Information System, a user-friendly integrated Software remote sensing tool for monitoring desertification, have being installed and is now used in Italy, Turkey and Portugal.

The European Space Agency (ESA) is carrying out a number of initiatives aimed at exploring and demonstrating the capabilities of EO technology to support the implementation of key environmental conventions (e.g., UNFCCC, UNCCD, UNCBD, Ramsar Convention). This paper provides an overview of the main projects that the European Space Agency is carrying out within the context of this important topic as well as the

This paper provides an overview of the project of the European Space Agency Building Environment for carried out in collaboration with UNESCO in support of the World heritage Convention. The project aims at demonstrate the capabilities of Earth Observation (EO) technology to provide reliable, synoptic and continuous information to Natural Park managers, Non-Governmental Organizations (NGOs) and local authorities to monitor and manage world heritage natural sites. This pilot project focuses on five different Parks in Central Africa, which correspond with the Gorilla habitat.

In 2001, the European Space Agency (ESA) launched the Treaty Enforcement Services using Earth Observation (TESEO) initiative. The objective was to explore through a series of parallel studies, the capabilities of Earth Observation (EO) technology to support the implementation of key international environmental treaties. One of these development contracts targeted wetlands applications in support of the Ramsar International Convention on Wetlands.

In this paper, a novel automatic approach to the unsupervised identification of changes in multitemporal remote-sensing images is proposed. This approach, unlike classical ones, is based on the formulation of the unsupervised change-detection problem in terms of the Bayesian decision theory. In this context, an adaptive semiparametric technique for the unsupervised estimation of the statistical terms associated with the gray levels of changed and unchanged pixels in a difference image is presented. Such a technique exploits the effectivenesses of two theoretically well-founded estimation procedures: the reduced Parzen estimate (RPE) procedure and the expectation-maximization (EM) algorithm. Then, thanks to the resulting estimates and to a Markov random field (MRF) approach used to model the spatial-contextual information contained in the multitemporal images considered, a change detection map is generated. The adaptive semiparametric nature of the proposed technique allows its application to different kinds of remote-sensing images. Experimental results, obtained on two sets of multitemporal remote-sensing images acquired by two different sensors, confirm the validity of the proposed approach.

An unsupervised retraining technique for a maximum likelihood (ML) classifier is presented. The proposed technique allows the classifier's parameters, obtained by supervised learning on a specific image, to be updated in a totally unsupervised way on the basis of the distribution of a new image to be classified. This enables the classifier to provide a high accuracy for the new image even when the corresponding training set is not available.

One of the main problems related to unsupervised change detection methods based on the "difference image" lies in the lack of efficient automatic techniques for discriminating between changed and unchanged pixels in the difference image. Such discrimination is usually performed by using empirical strategies or manual trial-and-error procedures, which affect both the accuracy and the reliability of the change-detection process. To overcome such drawbacks, in this paper, the authors propose two automatic techniques (based on the Bayes theory) for the analysis of the difference image. One allows an automatic selection of the decision threshold that minimizes the overall change detection error probability under the assumption that pixels in the difference image are independent of one another. The other analyzes the difference image by considering the spatial-contextual information included in the neighborhood of each pixel. In particular, an approach based on Markov Random Fields (MRFs) that exploits interpixel class dependency contexts is presented. Both proposed techniques require the knowledge of the statistical distributions of the changed and unchanged pixels in the difference image. To perform an unsupervised estimation of the statistical terms that characterize these distributions, they propose an iterative method based on the Expectation-Maximization (EM) algorithm. Experimental results confirm the effectiveness of both proposed techniques.

An approach to the automatic analysis of the difference image for change detection in multitemporal remote sensing images is proposed. This approach is based on a technique that exploits the expectation-maximization (EM) algorithm for the estimation of the density functions associated with both the changed and unchanged pixels in the difference image. Then, on the basis of such estimates, an automatic method for the unsupervised analysis of the difference image is described. The method makes use of Markov random fields (MRFs) for modeling the spatial-contextual information included in the neighborhood of each pixel. Experimental results confirm the effectiveness of the proposed approach.

A supervised technique for training radial basis function (RBF) neural network classifiers is proposed. Such a technique, unlike traditional ones, considers the class memberships of training samples to select the centers and widths of the kernel functions associated with the hidden neurons of an RBF network. The result is twofold: a significant reduction in the overall classification error made by the classifier and a more stable behavior of the classification error versus variations in both the number of hidden units and the initial parameters of the training process.

A data fusion approach to the classification of multisource and multitemporal remote-sensing images is proposed. The method is based on the application of the Bayes rule for minimum error to the "compound" classification of pairs of multisource images acquired at two different dates. In particular, the fusion of multisource data is obtained by using multilayer perceptron neural networks for a nonparametric estimation of posterior class probabilities. The temporal correlation between images is taken into account by the prior joint probabilities of classes at the two dates. As a novel contribution of this paper, such joint probabilities are automatically estimated by applying a specific formulation of the expectation-maximization (EM) algorithm to the data to be classified. Experiments carried out on a multisource and multitemporal data set confirmed the effectiveness of the proposed approach.