Resilience has become an important necessity for cities, particularly in the face of climate change. Mitigation and adaptation actions that enhance the resilience of cities need to be based on a sound understanding and quantification of the drivers of urban transformation and settlement structures, human and urban vulnerability, and of local and global climate change. Copernicus, as the means for the establishment of a European capacity for Earth Observation (EO), is based on continuously evolving Core Services. A major challenge for the EO community is the innovative exploitation of the Copernicus products in dealing with urban sustainability towards increasing urban resilience. Due to the multidimensional nature of urban resilience, to meet this challenge, information from more than one Copernicus Core Services, namely the Land Monitoring Service (CLMS), the Atmosphere Monitoring Service (CAMS), the Climate Change Service (C3S) and the Emergency Management Service (EMS), is needed. Furthermore, to address urban resilience, the urban planning community needs spatially disaggregated environmental information at local (neighbourhood) scale. Such information, for all parameters needed, is not yet directly available from the Copernicus Core Services mentioned above, while several elements - data and products - from contemporary satellite missions consist valuable tools for retrieving urban environmental parameters at local scale. The H2020-Space project CURE (Copernicus for Urban Resilience in Europe) is a joint effort of 10 partners from 9 countries that synergistically exploits the above Copernicus Core Services to develop an umbrella cross-cutting application for urban resilience, consisting of individual cross-cutting applications for climate change adaptation/mitigation, energy and economy, as well as healthy cities and social environments, at several European cities. These cross-cutting applications cope with the required scale and granularity by also integrating or exploiting third-party data, in-situ observations and modelling. CURE uses DIAS (Data and Information Access Services) to develop a system capable of supporting operational applications and downstream services across Europe. The CURE system hosts the developed cross-cutting applications, enabling its incorporation into operational services in the future. CURE is expected to increase the value of Copernicus Core Services for future emerging applications in the domain of urban resilience, exploiting also the improved data quality, coverage and revisit times of the future satellite missions. Thus, CURE will lead to more efficient routine urban planning activities with obvious socioeconomic impact, as well as to more efficient resilience planning activities related to climate change mitigation and adaptation, resulting in improved thermal comfort and air quality, as well as in enhanced energy efficiency. Specific CURE outcomes could be integrated into the operational Copernicus service portfolio. The added value and benefit expected to emerge from CURE is related to transformed urban governance and quality of life, because it is expected to provide improved and integrated information to city administrators, hence effectively supporting strategies for resilience planning at local and city scales, towards the implementation of the Sustainable Development Goals and the New Urban Agenda for Europe.
Large amounts of Earth observation (EO) data have been collected to date, to increase even more rapidly with the upcoming Sentinel data. All this data contains unprecedented information, yet it is hard to retrieve, especially for nonremote sensing specialists. As we live in an urban era, with more than 50% of the world population living in cities, urban studies can especially benefit from the EO data. Information is needed for sustainable development of cities, for the understanding of urban growth patterns or for studying the threats of natural hazards or climate change. Bridging this gap between the technology-driven EO sector and the information needs of environmental science, planning, and policy is the driver behind the TEP-Urban project. Modern information technology functionalities and services are tested and implemented in the Urban Thematic Exploitation Platform (U-TEP). The platform enables interested users to easily exploit and generate thematic information on the status and development of the environment based on EO data and technologies. The beta version of the web platform contains value added basic earth observation data, global thematic data sets, and tools to derive user specific indicators and metrics. The code is open source and the architecture of the platform allows adding of new data sets and tools. These functionalities and concepts support the four basic use scenarios of the U-TEP platform: explore existing thematic content; task individual on-demand analyses; develop, deploy and offer your own content or application; and, learn more about innovative data sets and methods.
H2020-Space project URBANFLUXES (URBan ANthrpogenic heat FLUX from Earth observation Satellites) investigates the potential of Copernicus Sentinels to retrieve anthropogenic heat flux, as a key component of the Urban Energy Budget (UEB). URBANFLUXES advances the current knowledge of the impacts of UEB fluxes on urban heat island and consequently on energy consumption in cities. This will lead to the development of tools and strategies to mitigate these effects, improving thermal comfort and energy efficiency. In URBANFLUXES, the anthropogenic heat flux is estimated as a residual of UEB. Therefore, the rest UEB components, namely, the net all-wave radiation, the net change in heat storage and the turbulent sensible and latent heat fluxes are independently estimated from Earth Observation (EO), whereas the advection term is included in the error of the anthropogenic heat flux estimation from the UEB closure. The project exploits Sentinels observations, which provide improved data quality, coverage and revisit times and increase the value of EO data for scientific work and future emerging applications. These observations can reveal novel scientific insights for the detection and monitoring of the spatial distribution of the urban energy budget fluxes in cities, thereby generating new EO opportunities. URBANFLUXES thus exploits the European capacity for space-borne observations to enable the development of operational services in the field of urban environmental monitoring and energy efficiency in cities.
Classification of hyperspectral data is one of the most challenging problems in the analysis of remote sensing images. The complexity of this process depends on both the properties of data (non-stationary spectral signatures of classes, intrinsic high dimensionality) and the practical constraints in ground-truth data collection (which result in a small ratio between the number of training samples and spectral channels). Among the methods proposed in the literature for classification of hyperspectral images, semisupervised procedures (which integrate in the learning phase both labeled and unlabeled samples) and systems based on Support Vector Machines (SVMs) seem to be particularly promising. In this paper we introduce a novel Progressive Semisupervised SVM technique (PS3VM) designed for the analysis of hyperspectral remote sensing data, which exploits a semisupervised process according to an iterative procedure. The proposed technique improves the one presented in [1,2], exhibiting three main advantages: i) an adaptive selection of the number of iterations of the semi-supervised learning procedure; ii) an effective model-selection strategy; iii) a high stability of the learning procedure. To assess the effectiveness of the proposed approach, an extensive experimental analysis was carried out on an hyperspectral image acquired by the Hyperion sensor over the Okavango Delta (Botswana).