Search

The purpose of this research is to demonstrate the strong potential of Earth-observation (EO) data and techniques in support of migration policies, and to propose actions to fill the existing structural gaps. The work was carried out within the “Smart URBan Solutions for air quality, disasters and city growth” (SMURBS, ERA-PLANET/H2020) project. The novelties introduced by the implemented solutions are based on the exploitation and synergy of data from different EO platforms (satellite, aerial, and in situ). The migration theme is approached from different perspectives. Among these, this study focuses on the design process of an EO-based solution for tailoring and monitoring the SDG 11 indicators in support of those stakeholders involved in migration issues, evaluating the consistency of the obtained results by their compliance with the pursued objective and the current policy framework. Considering the city of Bari (southern Italy) as a case study, significant conclusions were derived with respect to good practices and obstacles during the implementation and application phases. These were considered to deliver an EO-based proposal to address migrants’ inclusion in urban areas, and to unfold the steps needed for replicating the solution in other cities within and outside Europe in a standardized manner.

Local and Regional Authorities require indicators at the intra-urban scale to design adequate policies to foster the achievement of the objectives of Sustainable Development Goal (SDG) 11. Updated high-resolution population density and settlement maps are the basic input products for such indicators and their sub-indicators. When provided at the intra-urban scale, these essential variables can facilitate the extraction of population flows, including both local and regular migrant components. This paper discusses a modification of the dasymetric method implemented in our previous work, aimed at improving the population density estimation. The novelties of our paper include the introduction of building height information and site-specific weight values for population density correction. Based on the proposed improvements, selected indicators/sub-indicators of four SDG 11 targets were updated or newly implemented. The output density map error values are provided in terms of the mean absolute error, root mean square error and mean absolute percentage indicators. The values obtained (i.e., 2.3 and 4.1 people, and 8.6%, respectively) were lower than those of the previous dasymetric method. The findings suggest that the new methodology can provide updated information about population fluxes and processes occurring over the period 2011–2020 in the study site—Bari city in southern Italy.

The present study focuses on the use of Convolutional Neural Networks (CNN or ConvNet) to classify a multi-seasonal dataset of Sentinel-2 images to discriminate four grassland habitats in the “Murgia Alta” protected site. To this end, we compared two approaches differing only by the first layer machinery, which, in one case, is instantiated as a fully-connected layer and, in the other case, results in a ConvNet equipped with kernels covering the whole input (wide-kernel ConvNet). A patchwise approach, tessellating training reference data in square patches, was adopted. Besides assessing the effectiveness of ConvNets with patched multispectral data, we analyzed how the information needed for classification spreads to patterns over convex sets of pixels. Our results show that: (a) with an F1-score of around 97% (5 × 5 patch size), ConvNets provides an excellent tool for patch-based pattern recognition with multispectral input data without requiring special feature extraction; (b) the information spreads over the limit of a single pixel: the performance of the network increases until 5 × 5 patch sizes are used and then ConvNet performance starts decreasing.

Snow cover plays an important role in biotic and abiotic environmental processes, as well as human activities, on both regional and global scales. Due to the difficulty of in situ data collection in vast and inaccessible areas, the use of optical satellite imagery represents a useful support for snow cover mapping. At present, several operational snow cover algorithms and products are available. Even though most of them offer an up-to-daily time scale, they do not provide sufficient spatial resolution for studies requiring high spatial detail. By contrast, the Let-It-Snow (LIS) algorithm can produce high-resolution snow cover maps, based on the use of both the normalized-difference snow index (NDSI) and a digital elevation model. The latter is introduced to define a threshold value on the altitude, below which the presence of snow is excluded. In this study, we revised the LIS algorithm by introducing a new parameter, based on a threshold in the shortwave infrared (SWIR) band, and by modifying the overall algorithm workflow, such that the cloud mask selection can be used as an input. The revised algorithm has been applied to a case study in Gran Paradiso National Park. Unlike previous studies, we also compared the performance of both the original and the modified algorithms in the presence of cloud cover, in order to evaluate their effectiveness in discriminating between snow and clouds. Ground data collected by meteorological stations equipped with both snow gauges and solarimeters were used for validation purposes. The changes introduced in the revised algorithm can improve upon the overall classification accuracy obtained by the original LIS algorithm (i.e., up to 89.17 from 80.88%). The producer’s and user’s accuracy values obtained by the modified algorithm (89.12 and 95.03%, respectively) were larger than those obtained by the original algorithm (76.68 and 93.67%, respectively), thus providing a more accurate snow cover map.

The present study aims to discriminate four semi-arid grassland habitats in a Mediterranean Natura 2000 site, Southern Italy, involving 6210/E1.263, 62A0/E1.55, 6220/E1.434 and X/E1.61-E1.C2-E1.C4 (according to Annex I of the European Habitat Directive/EUropean Nature Information System (EUNIS) taxonomies). For this purpose, an intra-annual time-series of 30 Sentinel-2 images, embedding phenology information, were investigated for 2018. The methodology adopted was based on a two-stage workflow employing a Support Vector Machine classifier. In the first stage only four Sentinel-2 multi-season images were analyzed, to provide an updated land cover map from where the grassland layer was extracted. The layer obtained was then used for masking the input features to the second stage. The latter stage discriminated the four grassland habitats by analyzing several input features configurations. These included multiple spectral indices selected from the time-series and the Digital Terrain Model. The results obtained from the different input configurations selected were compared to evaluate if the phenology information from time-series could improve grassland habitats discrimination. The highest F1 values (95.25% and 80.27%) were achieved for 6210/E1.263 and 6220/E1.434, respectively, whereas the results remained stable (97,33%) for 62A0/E1.55 and quite low (75,97%) for X/E1.61-E1.C2-E1.C4. However, since for all the four habitats analyzed no single configuration resulted effective, a Majority Vote algorithm was applied to achieve a reduction in classification uncertainty.

Grassland ecosystems can provide a variety of services for humans, such as carbon storage, food production, crop pollination and pest regulation. However, grasslands are today one of the most endangered ecosystems due to land use change, agricultural intensification, land abandonment as well as climate change. The present study explores the performance of a knowledge-driven GEOgraphic-Object—based Image Analysis (GEOBIA) learning scheme to classify Very High Resolution (VHR) images for natural grassland ecosystem mapping. The classification was applied to a Natura 2000 protected area in Southern Italy. The Food and Agricultural Organization Land Cover Classification System (FAO-LCCS) hierarchical scheme was instantiated in the learning phase of the algorithm. Four multi-temporal WorldView-2 (WV-2) images were classified by combining plant phenology and agricultural practices rules with prior-image spectral knowledge. Drawing on this knowledge, spectral bands and entropy features from one single date (Post Peak of Biomass) were firstly used for multiple-scale image segmentation into Small Objects (SO) and Large Objects (LO). Thereafter, SO were labelled by considering spectral and context-sensitive features from the whole multi-seasonal data set available together with ancillary data. Lastly, the labelled SO were overlaid to LO segments and, in turn, the latter were labelled by adopting FAO-LCCS criteria about the SOs presence dominance in each LO. Ground reference samples were used only for validating the SO and LO output maps. The knowledge driven GEOBIA classifier for SO classification obtained an OA value of 97.35% with an error of 0.04. For LO classification the value was 75.09% with an error of 0.70. At SO scale, grasslands ecosystem was classified with 92.6%, 99.9% and 96.1% of User’s, Producer’s Accuracy and F1-score, respectively. The findings reported indicate that the knowledge-driven approach not only can be applied for (semi)natural grasslands ecosystem mapping in vast and not accessible areas but can also reduce the costs of ground truth data acquisition. The approach used may provide different level of details (small and large objects in the scene) but also indicates how to design and validate local conservation policies.

This study focused on implementation of the Sustainable Development Goal (SDG) 11 indicators, at local scale, useful in monitoring urban social resilience. For this purpose, the study focused on updating the distribution map of the migrant population regularly residing in Bari and a neighboring town in Southern Italy. The area is exposed to increasing migration fluxes. The method implemented was based on the integration of Sentinel-2 imagery and updated census information dated 1 January 2019. The study explored a vector-based variant of the dasymetric mapping approach previously used by the Joint Research Center (JRC) within the Data for Integration initiative (D4I). The dasymetric variant implemented can disaggregate data from census areas into a uniform spatial grid by preserving the information complexity of each output grid cell and ensure lower computational costs. The spatial distribution map of regular migrant population obtained, along with other updated ancillary data, were used to quantify, at local level, SDG 11 indicators. In particular, the map of regular migrant population living in inadequate housing (SDG 11.1.1) and the ratio of land consumption rate to regular migrant population growth rate (SDG 11.3.1) were implemented as specific categories of SDG 11 in 2018. At the local level, the regular migrant population density map and the SDG 11 indicator values were provided for each 100 × 100 m cell of an output grid. Obtained for 2018, the spatial distribution map revealed in Bari a high increase of regular migrant population in the same two zones of the city already evidenced in 2011. These zones are located in central parts of the city characterized by urban decay and abandoned buildings. In all remaining city zones, only a slight generalized increase was evidenced. Thus, these findings stress the need for adequate policies to reduce the ongoing process of residential urban segregation. The total of disaggregated values of migrant population evidenced an increase of 44.5% in regular migrant population. The indicators obtained could support urban planners and decision makers not only in the increasing migration pressure management, but also in the local level monitoring of Agenda 2030 progress related to SDG 11.

This paper discusses the application of the Cross-Correlation Analysis (CCA) technique to multi-spatial resolution Earth Observation (EO) data for detecting and quantifying changes in forest ecosystems in two different protected areas, located in Southern Italy and Southern India. The input data for CCA investigation were elaborated from the forest layer extracted from an existing Land Cover/Land Use (LC/LU) map (time T1) and a more recent (T2, with T2 > T1) single date image. The latter consist of a High Resolution (HR) Landsat 8 OLI image and a Very High Resolution (VHR) Worldview-2 image, which were analysed separately. For the Italian site, the forest layer (1:5000) was first compared to the HR Landsat 8 OLI image and then to the VHR Worldview-2 image. For the Indian site, the forest layer (1:50,000) was compared to the Landsat 8 OLI image then the changes were interpreted using Worldview-2. The changes detected through CCA, at HR only, were compared against those detected by applying a traditional NDVI image differencing technique of two Landsat scenes at T1 and T2. The accuracy assessment, concerning the change maps of the multi-spatial resolution outputs, was based on stratified random sampling. The CCA technique allowed an increase in the value of the overall accuracy: from 52% to 68% for the Italian site and from 63% to 82% for the Indian site. In addition, a significant reduction of the error affecting the stratified changed area estimation for both sites was obtained. For the Italian site, the error reduction became significant at VHR (±2 ha) in respect to HR (±32 ha) even though both techniques had comparable overall accuracy (82%) and stratified changed area estimation. The findings obtained support the conclusions that CCA technique can be a useful tool to detect and quantify changes in forest areas due to both legal and illegal interventions, including relatively inaccessible sites (e.g., tropical forest) with costs remaining rather low. The data obtained through CCA intervention could not only support the commitments undertaken by the European Habitats Directive (92/43/EEC) and the Convention of Biological Diversity (CBD) but also satisfy UN Sustainable Development Goals (SDG).