Urban Data Space to Support Green Deal Priority Actions

Data spaces are a new data sharing paradigm through a distributed ecosystem, allowing data owners to maintain control over their data use, unlocking the data potential against Findability Accessibility Interoperability and Reusability (FAIR) principles. For urban areas, data spaces provide geospatial, environmental and climate data to everyone. Various international and interdisciplinary projects and initiatives are developing data spaces, allowing policy-makers, researchers, citizens and the private sector to access high-quality, interoperable data in order to generate actionable knowledge, support the green transition of cities as well as enable a more effective decision-making process. 

The Urban Data Space for Green Deal - USAGE - EU project aims to offer innovative governance mechanisms, consolidated frameworks, best practices, AI-based tools and data analytics to share, access and use city-level data from satellite and airborne platforms, Internet of Things (IoT) sensors, authoritative and crowdsource sources. 

Within USAGE, a series of geospatial, thematic and other datasets have been newly acquired or generated over four pilot areas and will be shared through a standard-based web ecosystem to test and evaluate solutions (i) to better understand issues and trends on how our planet and its climate are changing; (ii) to support decision making intended to mitigate the effects of changes and environmental issues on life; and (iii) to address the role that humans play in these changes, e.g., with behaviour adaptation and mitigation actions.

Urban areas are the focus of USAGE since most of human activities are concentrated there, being the main source of some of the issues considered as green deal priorities (e.g. energy use, pollution, climate changes effects); solutions in USAGE are developed by an interdisciplinary team analysing geospatial data and by meeting multiple and diverse local requirements.

In this work we will present the relevant datasets collected in our pilot areas, reporting processing methodologies and applications of analysis-ready and decision-ready geospatial data. In particular we will report experiences related to:

- detection of urban heat islands (UHI) and production of UHI maps, utilizing open data like high-resolution satellite imagery, meteorological ground sensor data, surface properties and a hybrid model based on machine learning and geostatistics;

- generation of semantic 3D city models for photovoltaic solar potential estimation and energy efficiency purposes;

- generation of high-resolution thematic maps (surface materials, ecological indexes, etc.) from hyperspectral airborne imagery using a multi-level machine learning approach and supported by training data provided by the municipalities;

- realization of canopy thematic layers combining 3D point clouds and hyperspectal images to monitor health and growth of trees over time, to estimate biomass and to map species distribution;

- initiation of multi-temporal (night/days, summer/winter) thermal analyses based on high-resolution aerial thermal images, deriving proper land surface temperatures (LST) by correcting raw sensor data with thematic maps of surface materials. 

The presentation will highlight the importance of shared urban data spaces to enable visualization, sharing, fusion and processing of environmental and Earth Observation data from heterogeneous sources, ultimately facilitating more effective decision-making processes, besides advances in scientific research.