Conference Agenda

Climate change and urbanization transform life globally, with direct impacts on each other, yet they are rarely studied together across disciplines. The Synergy Grant urbisphere, funded by the European Research Council (ERC), aims to forecast feedbacks between climate and cities. With new synergies between four disciplines (spatial planning, remote sensing, modelling and ground-based observations), urbisphere incorporates city dynamics and human behaviour into climate forecasts/projections, focusing on within-city dynamics of peoples’ activities and how these can be up-scaled to cities globally. urbisphere is studying inter/intra-city form and function (demographics, mobility, climate adaptation and vulnerability planning typologies), exploring human/socio-economic vulnerability, exposure, risk perception, coping/adaptive measures to climatic stressors and settlement/building typologies.

urbisphere is developing new ways to represent city dynamics for weather/climate models. These models are informed by the urbisphere developed Earth Observation system, using space-borne/airborne sensors and ground based sensors with near real-time data transmission, processing, visualization and central archiving of data from 500+ sensors, including a network of ceilometers, scintillometers, Doppler wind lidars, flux towers combined with street-level and indoor sensors. Combined these measure the 3-dimensional state of the atmosphere and the surface. The sensors are being deployed through an annual cycle, with successful campaigns in Berlin (2021 - 2022) and Paris (2023 - 2024). The sensors are now being deployed in Bristol. These observations are providing both new understanding of urban surface-atmosphere processes and datasets for model evaluation at unprecedented detail. For example, the Berlin campaign helped understanding how an isolated city modifies the atmospheric boundary layer, the relation with human activity cycles and variations above and downwind of the city.

More information on urbisphere is available at: https://urbisphere.eu

The large abundance of materials absorbing short-wave radiation from the Sun and the concentration of people make cities particularly vulnerable to the heat island effect. Although the surface albedo and emissivity of the materials in the urban fabric are key quantitative properties for heat pollution mitigation strategies, these are often lacking citywide. Observing cities from space with high-spatial resolution optical and thermal-infrared sensors can circumvent the in-situ stations’ spatial and temporal coverage limitations.

However, the measurements from space correspond to information relative to a limited number of satellite acquisition geometry and spectral bands, which prevents the accurate computation of needed quantities such as urban albedo maps. In order to extrapolate satellite observations to any upward directions and to the whole spectral domain of interest, a physical model considering the complex 3D structure of urban environments is needed. This contribution describes the SuaBe project, which focuses on designing and implementing a fast, and robust algorithm, that uses the 3D radiative transfer code DART (https://dart.omp.eu/#/) to invert remote sensing images of cities as a 3D distribution of optical properties and temperature, using a geometric urban database. This approach enables us to obtain a 3D model of a city to simulate urban surface albedo and emissivity maps at any date as long as the optical properties of urban elements remain constant. These optical properties can be up-dated with the inversion of recently acquired satellite imagery.

As a case study, we will apply it to Brussels to retrieve surface albedo and emissivity maps at a neighbourhood scale. These results can be considered an asset to be used by urban planners and decision-makers to identify what urban areas should be considered priority candidates for an intervention to mitigate heat pollution, which in turn, shall allow authorities or civil organisations to maximise benefits from limited financial resources. Since the SuaBe’s methodology is based on a robust and rigorous physical model, it can be seamlessly implemented in any other city worldwide, provided that a geometric urban database is available.

Climate change increases stress on urban areas due to the rise in heat waves, which can threaten people’s wellbeing and even lives. Temperature is a crucial parameter in climate monitoring and Earth Observation (EO) systems. Advances in remote sensing technology have expanded opportunities for monitoring surface temperature from space. With numerous satellite thermal missions anticipated in the coming years, there is a pressing need for improved methods to retrieve surface temperatures for cities. While EO satellites are excellent for mapping Land Surface Temperature (LST), the unique properties and geometry of urban surfaces, along with the trade-off between temporal and spatial resolution, pose challenges in retrieving urban surface temperature (UST).

To this end, the EO4UTEMP project explored the use of EO data for monitoring UST from space. EO4UTEMP developed innovative methods and algorithms for producing detailed, accurate, and frequent UST products. A UST retrieval algorithm for high-resolution thermal sensors (e.g., Landsat, ASTER, ECOSTRESS, and the upcoming TRISHNA, LSTM, and SBG) includes emissivity corrections using ancillary information from external sources (e.g. urban surface cover information from Sentinel-2, Landsat) and spectral libraries. The algorithm accounts for the sensor’s viewing angle and considers the fraction of vertical urban facades in the UST retrieval, increasing the accuracy in retrievals. Combined with a thermal imagery downscaling approach, the UST retrieval algorithm allows for the use of low-resolution satellite thermal imagery, therefore increasing the frequency of UST observations. The EO4UTEMP methodology was evaluated using in-situ measured UST from meteorological station measurements in Heraklion, Greece, with a Mean Absolute Error (MAE) of up to 3.6 K for daytime and 1.4 K. The EO4UTEMP methodology is transferable and applicable to cities worldwide and the project showcases new technologies and tools to the EO community and promotes the use of EO data in urban meteorology.

Extreme heat events pose a growing threat to urban populations, with rising temperatures linked to increased mortality. In response, the development of advanced tools becomes imperative for effective mitigation and real-time management of heat-related mortality. This work presents a novel approach leveraging digital twin (DT) concept to estimate mortality associated with extreme heat events, offering both long-term projections and real-time insights for heatwave management. The work is being implemented within the framework of CARMINE project (Climate-Resilient Development Pathways in Metropolitan Regions of Europe).

The DT on heat health risk will serve as a human mortality estimator, employing a Machine Learning model trained on diverse urban indicators to predict heat-related mortality occurrences during summer months and heatwave events. This research establishes digital coupling, facilitating seamless connections between disparate data sources essential for mortality estimation. Key datasets for this utilization include high resolution urban scale modeling coupled with near-real time data incorporating natural (including Nature-based Solutions – NbS) and built environment features, real-time satellite-derived temperatures, weather forecasts, Copernicus C3S, mortality records, socio-economic data and demographics. The latter are among the prime variables to condition population vulnerability and thus the fatality of future heatwaves and to dictate policies to strengthen resilience.

Protocols for accessing datasets and ensuring data security, including user authentication mechanisms, are integral components of the DT.

By integrating advanced modeling techniques with real-time data streams and urban indicators, the proposed DT offers a comprehensive solution for proactive heatwave management. The ability to forecast heat-related mortality enables policymakers and public health authorities to implement targeted interventions, including NbS, asses their performance through the DT, and allocate resources effectively, ultimately enhancing urban resilience to extreme heat events. Furthermore, this initiative will coordinate with the flagship initiative of DestinE to increase its impact and scaling up.

Funded by the European Union (GA 101137851).

For EU policies to be efficiently planned, there is a need for a continental, harmonized, multitemporal and highly detailed indicator on soil sealing that allows the monitoring of the location and the degree of impacts. The European Copernicus Land Monitoring Service has been producing datasets on imperviousness every 3 years since 2006, which are the only high-resolution datasets that enable European wide monitoring. However, after the 2015 reporting year, the input for the production of the imperviousness dataset was switched from mixed inputs to the European Sentinel satellites. While this led to an improvement in the spatial detail from 20 m to 10 m, the change in the input dataset also resulted in a break in the time series as the 2018 update was not comparable to the previous reference years. In addition, the European Copernicus Land Monitoring Service has been producing a new dataset from 2018 onward entitled the CORINE Land Cover (CLC)+ Back Bone which also include a sealed area thematic class. When comparing both datasets with sampled reference data, it appears that the imperviousness dataset substantially underestimates sealed areas at European level. However. The CLC+ dataset only started to be available from 2018 and currently does not include any change layer. To address these issues, we present a harmonized and bias-corrected continental soil sealing combined dataset for Europe for the entire observation period. This new dataset has been validated to be the best current dataset for monitoring imperviousness and soil sealing impacts as a direct input for European policies. Finally, recommendations for future updates and validation of imperviousness degree monitoring geospatial products are given.

Soil sealing – also called imperviousness – is defined as a change in the nature of the soil leading to its impermeability. Soil sealing has several impacts on the environment, especially in urban areas and local climate, influencing heat exchange and soil permeability; soil sealing monitoring is crucial for the Mediterranean coastal areas, where soil degradation combined with drought and fires contributes to desertification.

Some artificial features like buildings, paved roads, paved parking lots, and other artifacts can be considered to have a long duration. In general, these land cover types are referred to as permanent soil sealing because the probability of coming back to natural use is low. Other land cover features included in the definition of soil sealing can be considered reversible. For them, the probability of coming back to natural use is higher. The land cover classes that are included in the reversible soil sealing have been defined with the users of the project, and include solar panels, construction site in early stage, mines and quarries, long-term plastic-covered soil in agricultural areas (e.g., non-paved greenhouses).

The project Mediterranean Soil Sealing, promoted by the European Space Agency (ESA) in the frame of the EO Science for Society – Mediterranean Regional Initiative, aims to provide specific products related to soil sealing and its degree over the Mediterranean coastal areas by exploiting EO data with an innovative methodology capable to optimize and scale-up their use with other non-EO data. The project started in March 2021 and the final products are available in 2024. The project team is led by Planetek Italia, and composed by ISPRA and CLS.

The targeted products are high-resolution maps of the degree of soil sealing over the Mediterranean coastal areas (within 20km from the coast) for the 2018-2022, at yearly temporal resolution with a targeted spatial resolution of 10m.

The involvement of stakeholders and end-users is an essential element of the project. Since from the early stage of the proposal, efforts have been made to reach a diversity of users and stakeholders; the presence of ISPRA in the consortium is a plus for the project in this sense.

Users are grouped into classes: municipalities; sub-national agencies or local governmental institution; national institutions and research centers; regional institutions (EEA) and international (UN).

We would like to present TRIPS, a web application developed as an ESA 5G for l'ART Demonstration Project in collaboration with the Turin Municipality, Municipal Police aimed at integrating advanced ML/DL technologies to address key challenges in urban safety. It has three core modules:

Road Markings Quality Assessment: Using state-of-the-art Computer Vision algorithms on Very High-Resolution (VHR) data, TRIPS provides a diagnostic of road markings quality through a robust pipeline. A domain-adapted neural network is used to extract a visible road mask, which is then used to assist in training the markings model. This process helps the model concentrating on the key elements of the road. Two other helpful features are that the models have been trained under supervision through the laborious process of manually labeling many VHR pictures, and a customized shadow detector model has been created to manage the shadows.

Car Risk Accidents Forecasting: TRIPS incorporates a sophisticated predictive model capable of forecasting car accidents across the city for the next 5 days by analyzing traffic patterns, weathers and street characteristics like intersection type or number of pedestrian crossings. This approach empowers authorities to identify high-risk areas and implement targeted interventions to prevent accidents, ultimately enhancing overall road safety.

Drone-Based Accident Surveillance: During the pilot phase, TRIPS integrates a module that harnesses the capabilities of drones deployed by municipal police for accident surveillance. This module facilitates real-time collection of images and data at accident sites, enabling prompt emergency response and comprehensive post-accident analysis.

In terms of accident prevention and emergency response, TRIPS offers a paradigm change in urban safety management. Through cooperation between the Police, the Turin Municipality, and ESA, TRIPS is an example of innovation using EO data and ML technology to address smart mobility in urban areas.

The African Development Bank (2014) reports that 53% of African roads are unpaved, with these roads being vital for the continent's economic and social development but requiring efficient maintenance strategies to remain motorable. This study, supported by the European Space Agency, responds to the challenge of irregular and inaccurate traditional condition surveys by introducing an innovative, cost-effective machine learning (ML) solution aimed at aiding local road authorities to monitor and plan road maintenance more effectively. This research builds on earlier initiatives by TRL, which demonstrated the efficacy of classical ML models in analysing Tanzania's unpaved roads through high-resolution satellite imagery. Despite the potential economic advantages of the proposed ML methods over traditional techniques, stakeholders considered high resolution imagery to be expensive. This trial involves leveraging both medium and low-resolution satellite images to assess road conditions in Madagascar and Malawi to make significant savings on imagery costs. Our approach involves Multimodal ML using classical models trained on values derived from image statistics. Our findings indicate that Multimodal ML achieves commendable accuracy (87%) with high-resolution imagery, which declines by 8% and 7% for medium and low resolutions, respectively. This study underscores the potential of ML technologies to significantly enhance the assessment and maintenance of unpaved roads through optical satellite imagery analysis, presenting a promising path for cost-effective road management strategies.

The PRIMARY project aims to enhance air quality monitoring, especially in urban areas, using data from the PRISMA (PRecursore IperSpettrale della Missione Applicativa) mission. By analyzing PRISMA's hyperspectral data, the project seeks to understand atmospheric aerosols content and composition, crucial for assessing environmental and health impacts, particularly in cities. Spatial resolution of PRISMA data (30 m) and artificial intelligence play a key role in overcoming challenges such as spatial resolution limitations and the complexity of the inverse problem in satellite-based atmospheric studies.
To train neural networks for estimating aerosol characteristics using PRISMA data, a synthetic PRISMA-like dataset was generated with support from the Copernicus Atmosphere Monitoring service (CAMS). The training dataset generation exploited the libRadtran radiative transfer model. Trained AI modules are then applied to PRISMA images to produce atmospheric aerosol products.

Field campaigns were conducted in Rome (autumn 2022) and Milan (winter to summer 2023) to validate the PRIMARY project's outcomes. Moreover, drone measurements are being integrated to support validation activities. Preliminary results are encouraging and seems aligned with ground based measurements.
Data fusion products combining PRIMARY results with air quality data from missions such as Sentinel-5P, Sentinel-3 and GCOM-C are also under consideration.

In many cities the population is exposed to elevated levels of air pollution. Often, the spatial distribution of local air quality throughout urban areas is not well known due to the sparseness of official monitoring networks, or due to the inherent limitations of urban air quality models. Satellite observations and emerging low-cost sensor technology have the potential to provide complementary information. An integrated interpretation, however, is not straightforward. The CitySatAir project (part of ESA’s EO Science for Society program) investigates how satellite data of atmospheric composition can be better exploited for monitoring and mapping urban air quality at scales relevant for human exposure.

Focusing particularly on the nitrogen dioxide product provided by the TROPOMI instrument on the Sentinel-5P platform, we investigate different approaches for combining this data with other information such as from models and air quality monitoring stations. We choose four contrasting study sites across Europe (Madrid, Oslo, Rotterdam, Warsaw) differing in size, pollution levels, dominant emission sources, and cloud cover.

For Oslo and Warsaw, we use the Sentinel-5P NO₂ data in conjunction with the urban dispersion model EPISODE to bias-correct the underlying bottom-up emission dataset. The results indicate that, when the model is run with the satellite-corrected emission dataset and validated against air quality monitoring stations, the model error (RMSE) decreases for all stations by up to 20%. The updated model dataset is then used to assimilate observations from monitoring stations and low-cost sensors. In addition, we exploit the synergy of TROPOMI and EPISODE data by deriving surface NO₂ data and carrying out geostatistical downscaling to provide a satellite-based surface NO₂ dataset at scales relevant for human exposure.

For Madrid, Rotterdam, and Warsaw we developed a versatile urban dispersion model able to calculate both surface concentrations of NO₂ at street level and NO₂ column concentrations matching the TROPOMI observations. Urban emissions are described by proxies taken from open data, where emission factors are updated periodically to best match the observations from either ground or space. Compared to the CAMS regional ensemble, local biases are reduced considerably, especially if in-situ measurements are also assimilated in the simulated concentration fields using optimal interpolation.

The multi-annual reanalysis of hourly urban air pollution concentrations at street level provides a very rich data set, which demands special user-friendly tools for exploration and analysis. The data sets for the different cities are showcased in the Lobelia Explore viewer. Lobelia Explore is based on a serverless architecture: as a result of the user interacting with the viewer, the web application requests air pollution data from the cloud as static files and uses this data to render maps, display charts and aggregate data over user-defined areas, all of this browser-side. This architecture eliminates the need of on-demand data processing and reduces maintenance costs.

This work describes preliminary attempts aimed at creating a dataset of daily averages of aerosol optical depth (AOD) on an intraurban scale (300m) using MODIS MAIAC AOD, SEN3 SYN, and AOD from ERA5 reanalysis models. Our preliminary efforts were aimed at understanding the quality of available AOD products by comparing them with daily average measurements provided by the AERONET network for the Italian peninsula during the reference period 2019-2023. MODIS MAIAC AOD proves to be state-of-the-art in satellite AOD reconstruction, while SEN3 SYN correlates less and shows a significant bias when compared with AERONET.

Our efforts are oriented in two directions: a) evaluating whether SEN3 SYN is mature enough to deliver unbiased AOD products on an intraurban scale on a daily, weekly, and monthly basis, possibly using other sources of information such as DEM, latlon, and LST; b) performing data imputation of missing observations using AOD from reanalysis models such as ERA5.

Regarding AOD correction on an urban/intraurban scale, we are evaluating pixel-based approaches such as linear/nonlinear/GAM regression algorithms fueled by the combined use of SEN3 SYN, MODIS MAIAC, ERA5 AOD, and auxiliary data such as MODIS land surface temperature and climatic data.

Our findings demonstrate that there is room for further improvement of AOD products by imputing missing AOD values and by further calibrating AOD using regression models fed with available AOD estimates and auxiliary data.

This work is part of a collaborative project funded by ASI and called APEMAIA (Assessment of PM Exposure at the intra-urban scale in preparation for the MAIA mission). The project is designed to investigate the potential of MAIA by developing a multi-modular system for extracting PM concentrations at the intra-urban scale using Artificial Intelligence techniques.

The environMENTAL EU project aims to investigate the impact of major global challenges on mental health and brain health across the lifespan, including climate change, urbanization, and psychosocial stress. The project also seeks to develop prevention techniques and early interventions in this context.

Earth observation data is used to provide a comprehensive set of spatial information layers that may influence mental health and behavior. Our environmental datasets focus on urbanicity, greenness, water bodies, and elevation information, which will be adjusted to the geographic regions of the studied cohorts and linked to geographical positions and their corresponding data. We examine the relationship between environmental factors and mental health, utilizing global datasets such as the TanDEM-X Digital Elevation Model (DEM), the World Settlement Footprint (WSF) 3D data, night time lights data, local sun incidence angel corrected sun energy data, multi-spectral data, atmospheric data (NO2, SO2, CO, O3, and CO2 concentrations), cloud cover, air temperature, precipitation, and air pollution data.

This work presents first results from combined analysis of UK Biobank cohort data and spatial urban neighborhood metrics on mental well-being indicators such as the neuroticsm score. The neighborhood metrics are calculated for suitable geodata within different diameters ranging from 300 m to 7500 m to include spatial context information in point analysis. From geodata, the corresponding values are extracted at the patient coordinates of the cohorts and a cohort population density normalized analysis of defined bins above UK Biobank cohort data value thresholds is performed. First results indicate correlation of green indices, night time light data and building volume metrics with mental health scores within the UK Biobank cohort data. We hypothesized that environmental factors could also serve as proxies for the social environment and significantly influence mental health, particularly when coupled with the presence of urban green and blue spaces.

Overall, our research provides first insights into the link between geo-environmental factors and mental health outcomes, providing valuable information for policymakers, urban planners, and public health professionals aiming to create healthier and more sustainable living environments.

Urban areas, home to the majority of the global population, significantly contribute to environmental degradation due to substantial energy consumption and greenhouse gas emissions. In the European Union, buildings account for 40% of energy use and 36% of CO2 emissions. With 35% of buildings over 50 years old and 75% considered energy-inefficient, urban retrofitting is crucial for enhancing sustainability. Compounding these challenges, current Energy Performance Certificate (EPC) databases suffer from data gaps, lack of standardization, and restricted access, hindering effective action towards the European Green Deal’s goals for a low-carbon future and net-zero emissions by 2050.

In this framework, the ESA BEE.AI (Building Energy-efficiency Estimation with Artificial Intelligence) project introduces an innovative approach to improve urban building energy performance assessments using advanced deep learning and Earth Observation (EO) data. In particular, the intended solution integrates crowd-sourced street-level optical and thermal imagery, satellite-based very high-resolution top-view visible and near-infrared imagery, high-resolution land surface temperature metrics, and urban morphology metrics. Together with existing EPCs, BEE.AI aims at generating detailed maps categorizing building energy efficiency from "A" (most efficient) to "G" (least efficient), pinpointing retrofitting opportunities. Here, besides a baseline solution implementing an end-to-end deep-learning architecture, BEE.AI also envisages an advanced system which additionally extracts and integrates features explicitly providing insights into building characteristics (i.e., building age, construction material, presence of PV panels) and thermal properties.

Pilot studies across Denmark, Austria, and Italy, engaging stakeholders from the business sector such as real estate developers, local governments, and energy companies, will showcase BEE.AI’s capabilities. These collaborations are vital for tailoring the solutions to regional architectural styles and climate conditions and ultimately setting a new benchmark for sustainable building practices, supporting a transition to a low-carbon future.

The European Green Deal sets ambitious targets emphasizing the urgent need for the ecological transition in Europe, with a specific focus on enhancing renewable energy usage. A pivotal aspect of this initiative is increasing the renewable energy share to 32% by 2030, facilitated by amending the Renewable Energy Directive to promote decentralized sources like rooftop solar installations. Numerous European cities and municipalities are advancing this goal by incentivizing solar power and streamlining approval processes.

In this framework, the DLR Solar-DE project plays a crucial role by providing detailed spatial data essential for urban planners and policymakers to scale up rooftop solar resources effectively. This project has conducted a comprehensive mapping of solar installations across the 20 million buildings in Germany using high-resolution digital orthophotos (20cm spatial resolution), surface and terrain models (1m spatial resolution), and building perimeter vector data from the Federal Agency for Cartography and Geodesy, integrated through advanced machine learning and artificial intelligence (AI) techniques. Additionally, a specialized model assesses potential roof installation sites for photovoltaic (PV) panels by calculating the possible electrical output based on peak sunshine hours, roof inclination, and orientation as well as shading effects from neighboring trees or buildings. This initiative marks the first comprehensive national survey of Germany's solar capacity and identifies significant expansion opportunities, thereby providing essential data at both the building and administrative levels to support localized and national energy policies.

The insights from Solar-DE are instrumental in facilitating targeted investments and strategies for renewable energy development, thereby contributing to the broader goals of energy transition and greenhouse gas reduction. This project not only enhances our understanding of current solar energy infrastructures but also aids in planning future expansions to meet environmental targets.

Urban decarbonisation is one of the most urgent challenges in the fight against climate change, and space technologies are emerging as critical tools to accelerate this transition. With their invaluable contributions, it is possible to better understand and manage the urban environment and promote the adoption of sustainable energy strategies.

Recent developments in digitalisation and green technologies are revolutionising the way cities can reduce emissions and optimise resource use. For example, the integration of satellite data with space-based monitoring systems allows real-time mapping of urban energy efficiency, identifying issues such as heat islands and storm runoff times. This data is essential for designing targeted interventions to reduce emissions and improve the integration of renewable energy sources.

In addition, digitalisation and the use of artificial intelligence in cities are emerging as key trends in achieving sustainability goals. Combining these technologies with advanced geospatial data not only improves energy efficiency, but also strengthens urban resilience and promotes smarter and more sustainable resource management.

In this context, the Decarbonisation Twin Support (DTS) system integrates Earth Observation (EO) data with geospatial and environmental data to create dynamic digital twins of urban environments. These digital twins are designed to monitor and optimise carbon emissions and the efficiency of renewable energy integration in urban environments. By simulating real-world conditions and analysing historical and real-time data, the DTS system provides valuable insights that can guide urban planners, architects and policy makers in reducing carbon footprints.

This approach promises to transform cities into centres of sustainability, where energy is optimally managed and emissions are significantly reduced.

Access to energy is identified as one of the basic needs towards a decent life with better chances (SDG 7). Whereas in Europe, main initiatives concentrate on implementing the European Green Deal and related national policies, in other parts of the world providing access to energy is a still ongoing task and often handled in a more pragmatic way.

The need of access to consistent and reliable energy as guarantee for economic development remains a challenge in many fast growing and rapidly densifying urban agglomerations (Africa, SE-Asia). Cities are less managed when it comes to a well-designed energy infrastructure, understanding the dissemination grid is crucial. Private initiatives and investors provide access to electricity, thus the urban fringe is often intermingled with off-grid energy units, such as mini-grids, preferably run by diesel generators. Few houses run Photovoltaic (PV) on their rooftops. Air quality is critical, space is limited and open suburban regions convert to densely populated places within few years. This is the common setting where International Financial Institutions (IFIs) engage in supporting the transition towards sustainable solutions in combination with fulfilling SDG 7, serving the ranging needs within urban agglomerations and in the rural areas.

EO can act as overarching element by providing a better understanding of the urban dynamics, and thus in tailoring the financial support accordingly. Focus is drawn to find best fitting, affordable and sustainable solutions, may this be solar rooftop solutions, hydropower, wind energy, or even biogas. This first stage does not necessarily consider commercial VHR1 satellite image data.

Within the Global Development Assistance Project on Clean Energy (GDA-CE), multi-scale approaches are sketched linked to sites if ranging extent. For Armenia, as one example, a coarse solar potential analysis was prepared on national level, benefiting from HR Sentinel-2 imagery (timeline) and most recent terrain data, going beyond the commonly used global solar atlas. A more detailed solar rooftop analysis is performed considering VHR stereo data for the capital Yerevan, emphasising on common challenges when working with spaceborne data. The latter proofs sufficient for the first stage of dimensioning potential investments. When characterising the urban structures regarding their suitability for roof-top installations itself, generic understanding of building orientation, types & sizes, distribution, and specific roof-top characteristics (obstacles, age, sub-rooftop level) is of interest. More detailed aerial flight planning is considered as far too costly and gets rather replaced by local drone flights once investment planning reaches engineering level (static).

When working with IFIs such as the World Bank, besides providing the technical solution itself, the combination of information layers of higher and lower granularity is considered valuable, as long as transferability is given. input parameters are often not optimal, project timelines are prearranged and thus creative and pragmatic solutions adapting to national specifics are necessary. This presentation provides a wrap-up on how multiple scales are reasonable within different planning stages and perspectives, showcased in multiple locations (cities and rural areas). It supports the engagements of the IFIs, being aware of limitations of regional scale vs. VHR data analyses. Benefits of receiving a most recent situational picture, linked to timeline and understanding the contextual options often surpasses this and build the base for a detailed trade-off analysis.

Smart Cities prioritise environmental impact reduction and the green economy to create and maintain healthier, more sustainable places to live and work. Almost three quarters of European citizens now live in cities and this figure is expected to reach 80% by 2050. When it comes to energy, cities are focused on a secure and sustainable supply of clean energy, as the risks of climate change and the need to reduce our carbon footprint grow ever more real. Becoming energy efficient, it means also engaging technologies to reduce emissions in the transport sector and improve infrastructure to support a green transition. The presentation will provide an overview of operational solutions -environmentally and economically sustainable-which have been developed for the needs of the cities.

As urban centres grow, the global energy landscape is undergoing a dramatic shift toward decentralization, digitization, and decarbonization to meet the 2015 Paris Agreement's stringent goals of capping the rise in global temperatures to below 2°C. This shift is even more critical in cities, where energy demand is higher.

In this ongoing urban-centric transformation, wind energy is emerging as a key player due to its efficiency and the falling costs driven by technological advances. In particular, the installation of wind turbines (WT) is proving vital for creating decentralized power systems within and around cities. This approach not only helps mitigate transmission congestion but also bolsters energy security by generating power closer to its consumption points.

However, the variable nature of wind power poses significant challenges in urban settings, where energy supply consistency is crucial. The fluctuating output of turbines can lead to periods of both surplus and insufficient energy, highlighting the need for accurate and sophisticated energy modelling. This modelling is critical to optimize urban energy grids and requires up-to-date and precise data on infrastructure locations, which is frequently lacking.

To bridge this gap, the ESA EO4Energy project employs advanced deep neural networks and leverages Sentinel-1/2 satellite imagery to map onshore WTs and identify active coal power plants (CPP). Specifically, targeting CPPs is crucial not only because they are major emitters of CO2 but also because they offer potential as heat storage solutions that could stabilize the urban grid during low wind periods by storing excess energy.

The initial results from 100 test sites are extremely promising, demonstrating the project’s effectiveness in accurately identifying WTs and CPPs. This success paves the way for applying these technologies globally to improve urban energy planning and infrastructure, ensuring cities are more sustainable and better prepared to meet future energy demands.

This study aims at investigating the suitability of very-high resolution satellite imagery, e.g., Pleiades, WorldView-2 for classifying the dominant urban tree species in both public and private areas and estimating the tree height. Tree species differentiation is challenging in cities, as trees can be lined up or grouped in patch, with a wide range of plant species, high spectral similarity of vegetation types, and due to the complexity of the urban environment (buildings, shadows, open courtyards).

In the present study, we have implemented the so-called “object-based classification of urban tree species from very high-resolution satellite imagery” methodology we published in Sicard et al. (2023), that is an object-based classification using Random Forest classifier with different textural features extracted from tree canopy and grassland (lawn/turf) to identify and map dominant types of vegetation. Four spectral bands (blue, green, yellow, red) and four texture features (i.e., energy, entropy, inverse difference moment, Haralick correlation) were the most efficient attributes. Tree height estimation was performed using Pleaides tri-stereoscopic imageries and the photogrammetric tool MicMac of the French National Geographic Institut and the ForestTools package.

We applied the methodologies in two cities Aix-en-Provence (France, 50km²) and Florence (Italy, 80km²) where about 420,000 and 555,000 canopies were successfully classified in 22 and 20 dominant species with an overall accuracy of 84% and 83%, respectively. We found that about 85% of trees in both cities are in private lands. The highest classification accuracy was obtained for Pinus spp. and Platanus acerifolia in Aix-en-Provence, and for Celtis australis and Cupressus sempervirens in Florence. For the tree height, we obtained an absolute accuracy of 1.8m.

As cities expand, the pressure on natural ecosystems intensifies. Urban and peri-urban areas try to overcome with conflicting demands, which results in fragmented green infrastructure, and severed links between rural and urban zones. The European Union Biodiversity Strategy for 2030 recognizes this urgency and calls for action. The ambitious goal of "Greening urban and peri-urban areas" aims to reverse these trends. Similarly, the UN Sustainable Development Goals indicate the need for inclusive and accessible green urban areas (SDG 11.3).

The concept of Green and Blue Infrastructure (GBI) represents a strategic network of natural and semi-natural areas, thoughtfully integrated into urban and peri-urban landscapes. GBI weaves together green spaces, water bodies, and wildlife corridors to create a dynamic fabric that sustains life and mitigates environmental challenges.

By combining the implementation of GBI together with prioritising accessible green spaces, cities and regions can combat the dual crises of biodiversity loss and climate change. To support policymakers in the identification of these priority areas, a methodology was developed by the authors to map urban green infrastructure in the European Functional Urban Areas. This methodology used several High Resolution Layers (HRLs) and the Urban Atlas from the Copernicus Land Monitoring Service (CLMS) as well as complementary data from the Open Street Map (OSM), improving the thematic and spatial resolution provided by Urban Atlas. As a result, two datasets were produced corresponding to 2012 and 2018 which allows monitoring changes between the defined 8 GBI classes. It also allows quantifying the amount of GBI created within this period. Results are presented in transparent and easy to understand dashboards that allows users to analyse and download GBI data in Europe. The work is carried out in collaboration of the European Environment Agency and DG REGIO of the European Commission.

Compound dry and hot conditions have the potential to result in adverse socio-economic and ecological impacts in urban areas; they are usually associated with larger repercussions and risks than individual extremes. The thermal properties of vegetated urban parks enable them to function as climate modifiers, thereby increasing the adaptive capacity of cities. In this work, a climatology of compound drought and heat wave events (CDHW) is firstly derived for selected megacities worldwide (cities with population over 10 million residents). To achieve this, reanalysis data (ERA5-Land) and extreme indices (Excess Heat Factor for heatwaves and the Standardized Precipitation Evaporation Index for droughts) are used. Thermal patterns inside cities during CDHW events are derived using remotely-sensed Land Surface Temperatures (LST) (from Landsat 8/9 and MODIS Aqua/Terra satellites) and the co-occurrence between air temperature and LST anomalies is assessed. Then, the thermal regime of large-scale parks within megacities is evaluated under both typical conditions and during the identified CDHW extremes. Remotely sensed data underscore the role of urban green in mitigating the increasing heat and drought hazards confronting cities, driven by local and global climate change.

Urban green spaces are an important component in enhancing urban livability. Therefore, there is a need for sustainable management of these spaces, which can be acquired by using Earth Observation (EO) technology, to maintain an ecological balance, while mitigating the impact of urban heat islands. By harnessing high-resolution EO data, the S4UG project aimed to provide city managers and planners with advanced tools for informed decision-making in urban growth modeling and ecological assessments, particularly focusing on green and blue infrastructures, urban planning, and urban ecology. In this sense, stakeholders from twelve European cities were involved in defining the needs that arise in green infrastructure mapping in terms of resolution, frequency, and accuracy of the data. While Sentinel-2 imagery is suitable for monitoring urban spaces, due to covering vast areas frequently, their spatial resolution is not always enough to detect smaller green areas, specific to urban environments.

To overcome the limitations of Sentinel-2's image resolution, our research conducted during the S4UG project, focused on using super-resolution (SR) techniques for detailed vegetation extent mapping in urban environments. This application involved using images from Sentinel-2 satellites, which have a resolution of 10 meters, and from SPOT 7 satellites with a 1.5-meter resolution. The SR techniques were used to create synthetic imagery with a finer resolution of 2.5 meters. This improved resolution offered more accurate mapping and monitoring capabilities, highlighting its usefulness through services that provided detailed up-to-date land use/land cover maps and vegetation health monitoring, correlation between vegetation health with environmental factors over time and analyzes of green spaces accessibility for inhabitants. These capabilities proved valuable for stakeholders involved in the project, who require detailed spatial data to make informed decisions, showing that the exploitation of SR techniques at application level has the potential to enhance the added value of the provided solutions.

Urban planning is traditionally centred on human perspective, overlooking the needs of animals and plants that in turn help fostering liveability in cities. To address this bias, the concept of green urbanism emerges as a key driver for sustainable urban development. Nevertheless, the description of these habitats is usually not holistic, lacking the common accent to describe inter-specie interaction.

In response, we propose a novel methodology for characterising urban habitats showcased in an application to three distinct urban case studies: the Functional Urban Areas (FUA) of Vienna (Austria), Munich (Germany), and Genoa (Italy). Our approach transcends anthropocentrism by adopting an agnostic perspective—one that embraces the diverse living entities within co-habitative landscapes.

The classification is composed of four 10-meter rasters for each city, each with a separate set of variables focusing on different aspects of urban metabolisms, such as urban morphology at local and landscape scale, anthropic imprint, and biophysical conditions. The workflow scrapes from open data with global validity, resampling at a 10-meter resolution with a 100-meter moving window algorithm. After preprocessing, the pipeline ends with a combination of MiniBatch and Elkan KMeans algorithms.

The resulting rasters bring insights into distinct urban habitat classes and can provide meaningful observations alone or combined for both urban planners and natural scientists. The classification goal is to integrate with models for optimization and multi-criteria decision making. The role is not being an omniscient knowledge base, but a multi-disciplinary common understanding of urban habitats. The tool enables two methodologies: selecting a site for architectural design or ecological research, given a threshold of targets for liveability and conservation, and comparing different sites from different regions. The tool is developed with scalability in mind, and the next step will be to expand to all European FUA.

Cities are facing too many challenges. Urban vegetation, in particular trees, are essential as they provide services in terms of air pollution mitigation, freshness, biodiversity, and citizens’ well-being. The main aim of the European project AIRFRESH “Air pollution removal by urban forests for a better human well-being” is to quantify the environmental benefits provided by urban trees at city-scale in two front-runner cities: Florence (Italy) and Aix-en-Provence (France). To avoid a large underestimation of the quantification of benefits, a consistent inventory of vegetation within private and public areas is needed. Based on an object-based classification from very-high resolution satellite imagery (WorldView-2), we have detected and classified about 550,000 and 414,000 trees, and grassland, in the two study areas. Then, we applied the AIRTREE multi-layer canopy model and WRF-Chem model for the year 2019. We have also considered species-specific parameters, such as tree morphology (height, diameter at breast height, and crown leaf area), leaf habit (deciduous/evergreen) and eco-physiological responses to environmental factors. Finally, we have mapped the annual removal capacity of each urban tree for the most harmful air pollutants in cities, i.e., tropospheric ozone (O₃), nitrogen dioxide (NO₂), and particulate matter (PM_2.5, PM₁₀) in addition to carbon dioxide (CO₂). Deciduous broadleaves have high capacity to uptake O₃ and NO₂ (Platanus x acerifolia: 1.25 and 0.40 g m^-2 per year). Compared to deciduous broadleaves, evergreen conifers, such as Cupressus spp., showed higher performance in PM removal (11.5 and 2.5 g m^-2 per year for PM₁₀ and PM_2.5). We identified tree species with the highest CO₂ uptake capacity with values up to 2.5 kg m^-2 per year for Cedrus atlantica.

Urban areas necessitate effective management strategies to mitigate natural risks and protect communities. By harnessing Sentinel-1 radar images, the European Ground Motion Service (EGMS), an integral component of the Copernicus program, provides comprehensive insights into ongoing ground deformation processes. The EGMS is a deferred-time, multi-purpose mapping, and – to a certain extent – monitoring tool for active ground motion in urban areas. The presentation will showcase some EGMS use cases to convince existing and new users about the added value of the product in enabling the identification of areas prone to instability and the improvement of decision-making processes.

We designed a multi-scale methodology to assess present-day and future land subsidence risk in urban areas of Italy, from the national to the local scale, with a focus on direct impacts on metropolitan landscapes (development of ground depressions, earth fissures, structural damage, increased flood risk). Ground deformation observations from multi-temporal satellite Interferometric Synthetic Aperture Radar (InSAR), hydrogeological, topographic and land use datasets are embedded into an innovative risk assessment workflow, and processed with advanced geostatistics to identify the main subsidence hotspots and drivers.

Future subsidence risk linking with the exploitation of groundwater resources is assessed by accounting for various climate change scenarios (RCP4.5/8.5, medium/high emissions), and the projected demographic and urban development in 2050 and 2100. Advanced numerical models coupling 3D transient groundwater flow and geomechanics also enable the quantification of the effects of groundwater usage to land deformation, and the estimation of uncertainties at the local scale. A bespoke socio-economic impact analysis based on the exposure, vulnerability and resilience of the affected areas, also allows the estimation of market and non-market direct/indirect losses at the national, regional and local scales.

The results for the 15 metropolitan cities of Italy, the whole Emilia Romagna region and the city of Bologna will showcase the potential of the developed methodology and its benefits to inform water resource management and decision making, towards sustainable groundwater use and urban development. This work is funded by the European Union – Next Generation EU, component M4C2: From Research to Business, investment 1.1: Fund for the National Research Programme 2021-2027 and Research Projects of Significant National Interest (PRIN), in the framework of the PRIN 2022 National Recovery and Resilience Plan (PNRR) Call, project SubRISK+ (grant id. P20222NW3E), 2023-2025.

South-East Asian secondary cities are challenged by increasing floods and droughts occurrence, while decision makers are limited in capacities and data availability to foster sustainable development. Demand assessment in Laos, Cambodian and Indonesia, led to the development of a Water risk mapping methodology that visualizes Climate change impacts and evaluates blue-green adaptation measures. We first use the CORDEX dataset to assess the regional trends and the impact of climate change on precipitation and temperature, by considering Representative Concentration Pathways (RCPs), specifically the RCP 4.5 and RCP 8.5 as future climate scenarios for the period 2020-2050. This analysis is applied on three small watersheds: Prek Te in Cambodia, Boyong in Indonesia, and Nam Xam in Laos. Thereafter, we assess the impact of climate change of streamflow, by simulating the future runoff behavior using the GR2M hydrological models for the medium and extreme RCPs and for the same timeframe, over the Boyong watershed. The utilization of future climatic predictions supports hazard assessment, together with an improved Digital Elevation Model (FABDEM+) and inundation mapping (Sentinel-1) to identify flood prone area, while drought indicators and precipitation trend analysis point out regions susceptible to extreme events. Moreover, the location of buildings and agriculture land through open-source datasets in combination with associated values aid the identification of exposed areas. Finally, information on critical infrastructure, coupled with UAV images help to evaluate degrees of adaptation to define the urban resilience to climate change induced vulnerability. Within the process appropriate weights are applied and different future alternatives are displayed. This study provides information in data-scarce regions, on the impact of climate change over the hydrological cycle, and repercussions on water availability or extreme events occurrence downstream. Therefore, valuable support is provided to urban planning and Water-Sensitive-Urban-Design to evaluate suitable adaptation options and mitigation strategies on the urban level.

The growing trend of urbanization worldwide necessitates a comprehensive understanding of geological phenomena that pose a threat to these environments. Urbanization not only transforms landscapes but also introduces complex geotechnical challenges, heightening the risk of ground instability-related hazards. The utilization of satellite Interferometric Synthetic Aperture Radar (InSAR) facilitate the identification of ground movements on a millimetric scale, providing a critical foundation for evaluating risks such as landslides, which pose a prevalent threat in hilly or steep terrain regions, sinkholes that cause unexpected damage, and subsidence resulting to structural damage.

Addressing these concerns, our study introduces an innovative, data-driven multi-risk model tailored for urban assets, integrating multi-frequency multi-temporal satellite InSAR data, multi-hazard mapping, and the physical attributes of the built environment. This work offers a dynamic, semi-quantitative framework for assessing multiple georisks, thereby facilitating mitigation measures. The model ensures the assessment of diverse geohazards over large geographic scales and high-resolution mapping units, delivering scalable and easily comprehensible results. It computes single- and multi-risk scores through the appraisal of hazard probabilities, potential damages, and building displacement rates, thereby assisting in the prioritization of urban assets for targeted intervention, with the goal of enhancing urban resilience and diminishing future economic losses.

A case study conducted in Rome, Italy, proves the model's efficacy. Assessing multi-risk for approximately 90,000 buildings, it was determined that 60% are exposed to ground instability hazards. Specifically, 33%, 22%, and 5% of these buildings mainly face sinkholes, landslides, and subsidence risk, respectively. Notably, our analysis reveals a positive correlation between historical mitigation expenses and the multi-risk scores of nearby buildings, highlighting the model's value in urban planning and risk management.

This research accentuates the potential of Earth Observation data, such as InSAR, in the domain of multi-hazard risk assessment, providing insights for informed decision-making in predictive maintenance and hazard mitigation.

Flash floods caused by extreme rainfall events pose threats of extensive damage to the urban infrastructure. Conventional methods for flood inundation modeling can be computationally expensive and time-consuming. To speed up the calculations, we develop deep learning-based flood emulators for fast, real-time estimation of rainfall-induced flood depths in urban areas.

Our deep learning models follow a modular methodology. The head of the models consists of a terrain feature encoder and a rainfall distribution encoder. These encoders are connected to a joint decoder through a fusion model. From the fused latent encodings, the decoder learns to predict the pixel-wise maximum flood water depths in the study area during the given rainfall scenario. In this work, several types of deep learning architectures such as convolutional neural networks, recurrent neural networks, and neural operators were considered for the encoder and decoder modules. Different fusion strategies were also investigated for the fusion module. Using the elevation data, additional terrain features that could influence flooding were extracted and their impact on the performance of our emulators was studied.

Compared to previous works in deep learning-based flood prediction, our proposed methodology has been trained on a wide range of urban domains and rainfall scenarios. The reference dataset for supervised learning was built using open-source elevation data with spatial resolution of 1 m of more than 300 cities in the state of North Rhine Westphalia, Germany. Using several rainfall scenarios over the study areas, the corresponding flood water depth labels were computed using the flood inundation modeling tool, FiP [https://doi.org/10.2312/pgv.20221063]. We proved the generalizability of our flood emulators by evaluating their performance on previously unseen domains, in terms of hydrological error metrics. A speed-up in inference of 10,000-fold was achieved using our deep learning-based flood emulators compared to the conventional FiP tool.

This study presents a novel methodology to enhance the sustainability of urban infrastructure, such as urban buildings, cultural heritage, bridges, roads, and railways. using the Persistent Scatterer Interferometric Synthetic Aperture Radar (PS-InSAR) data from Sentinel-1 satellites during 2018–2022 in Ravenna, Italy. The research emphasizes sustainability, which represents the integrated nature of human activities and therefore the need for coordinated planning among different sectors, groups, and jurisdictions. Since the 17 Sustainable Development Goals (SDGs) were established in 2015, scientists have attempted to utilize them for sustainability assessments. Ravenna in Italy, chosen as the case study, renowned for its historical significance and cultural heritage, confronts ongoing challenges in maintaining infrastructure integrity amidst factors such as subsidence and ground instability. By considering and scaling different parameters such as safety, economy, environment, education, health, transportation, recreation, population density, and public utility alongside geological understanding, the research outlines a methodology for assessing urban sustainability and resilience, with a specific focus on subsidence risk. Initial steps involve analyzing time-series deformation patterns to highlight areas experiencing subsidence processes in Ravenna. The observed average line-of-sight (LOS) velocity is about -5 mm/year, with ground deformation near 50 mm. Deformation rates were combined with hazard and potential damage data to obtain a comprehensive risk assessment. Susceptibility of subsidence throughout the study area was employed as the hazard layer, while potential damage estimates were derived from buildings’ vulnerability and real-estate market values retrieved from census parcels and from the Osservatorio Mercato Immobiliare (OMI) database, respectively.

Integrating subsidence risk and weighted factors through geospatial analysis and modeling, this approach ranks municipalities based on their sustainability. It empowers informed decision-making, promoting the sustainability and resilience of the city's infrastructure.

Keywords: Urban Infrastructure Sustainability, PS-InSAR, Subsidence, Ground Instability, Geospatial Analysis, Modeling and Monitoring

Urbanization is a complex phenomenon characterized by rapid changes, especially in developing countries. Despite the availability of various raster layers outlining settlements globally and large-scale building footprint databases (e.g., from Google and Microsoft), these resources suffer from infrequent updates, which quickly renders them obsolete in fast-growing regions, especially in Africa and Asia. This inadequacy is particularly acute where timely data is essential for responsive urban planning and disaster management.

To overcome this drawback, DLR’s novel “World Settlement Footprint (WSF) tracker” monitors for the first time the global settlement extent at 10m resolution every six months from July 2016 to present. Scheduled to be released open and free in 2024 and systematically updated twice per year onwards, the WSF tracker marks a significant step forward in the field of urban geography, offering profound implications for sustainable development across the globe.

The layer is underpinned by a sophisticated methodology enhanced from that used to generate the WSF2019. In particular, the implemented approach integrates temporal statistics for different indices derived from both Sentinel-1 and Sentinel-2 and employs a Random Forest algorithm for classification, all processed on the Google Earth Engine platform.

The robustness and high accuracy of the WSF tracker is being validated through comprehensive qualitative and quantitative assessments, confirming its effectiveness as a reliable source for effectively managing urban development and mitigating environmental impacts. Additionally, the layer is expected to serve as a foundation for related datasets, namely the WSF Imperviousness (estimating the percent of impervious surface area), and the WSF Population (estimating resident population density). Both of these will similarly benefit from updates every six months, thus further enhancing their relevance and utility in several applications.

The Global Human Settlement Layer (GHSL) provides global, spatially detailed, multi-temporal, regularly updated, and multi-thematic information on the distribution and characteristics of human settlements worldwide. The evolution of GHSL followed a double path. On the one hand it has sustained scientific evolution delivering continuously benchmark setting products and before other proucts; on the other it has established know-how and partnership for transforming data into information and knowledge for policy support and capacity building.

The GHSL enables multi-thematic human settlement analytics at global scale looking back with historical time series from 1975 to 2020 based on multi-sensor data from Landsat and Sentinel-2. The operational product, the Copernicus GHSL (or Exposure Mapping component) of the Copernicus Emergency management Service) allows monitoring of human settlements worldwide. It ensures continuous updates of the built-up surface fraction layer for 2022, 2024, 2026 based on Sentinel-2 data, and it is quality controlled and validated. This allows updating population grids, the settlement classification by Degree of Urbanisation and indicators such as land consumption. The projection products cover short range (i.e. 2025 and 2030), but also longer time series at decadal interval until 2100 by downscaling Shared Socioeconomic Pathway scenarios at 1 km².

Regarding the transformation of data into policy support and capacity building, GHSL teamed up with UN and international stakeholders to develop the Degree of Urbanisation, which was endorsed by the UN Statistical Commission to delineate cities, urban and rural areas for international comparison (e.g. for SDG reporting). This led to a substantial capacity building effort for national statistical offices and the generation of downstream products like the urban centre database. In parallel to the capacity building, and the uptake of the baseline data into scientific literature by many users worldwide, the GHSL has established policy support activities to ensure data support transformative policies and reporting.

Earth observation data gained from the Sentinel-1 and Sentinel-2 satellites play a pivotal role in understanding the changing patterns and dynamics of urban landscapes and environments. Multi-user requirements on European and Global scales demand observing diverse variables like soil sealing, building densities, building usage, and typology. Impervious surfaces, such as roads, buildings, and pavements, significantly impact urban ecosystems but provide indispensable information about the location, size, and dynamic of human settlements relevant for emergency services.
We address these requirements with a versatile and Copernicus-production-proven framework using state-of-the-art deep-learning-based image analysis techniques to leverage the full potential of Sentinel-1 and Sentinel-2 time series data, combining highly efficient and noise-reducing time-series parameterization methodologies with a modified deep convolutional neural network called U-Net. With this setup, we simultaneously address categorical (e.g., land cover) and continuous variables (e.g., degree of soil sealing or building densities). The respective methodologies have been implemented in a flexible yet fault-tolerant processing environment that allows for multi-cloud application scenarios and roll out to large-scale processing. The methodology is currently applied at the European scale to update the CLMS Pan-European High-Resolution Layer on the Non-Vegetated Land Cover Component and for the global-scale production of the newest Global Human Settlement Layer update. Therefore, OSM data and Microsoft Building footprints are rasterized and combined with the Sentinel-2-based time-series data to train the model in predicting building and sealing degree densities. We will give an overview of our framework and present the latest results from both (CLMS and GHSL) productions, discuss and highlight the impact of principle design decisions, and highlight the main differences compared to previous product versions.

Sustainable urbanisation is a challenge and an opportunity at the same time globally. Nowadays, there is an impressive EO capacity available to deliver quality, spatial-temporarily rich, harmonized and fit-for-purpose data capable to provide insight into essential facts on the status and long-term development of the built environment on global level. Nevertheless, a tedious process to create, handle and explore huge global data on built up areas, to define analytical units and to generate standard indicators often complicate or even prevent full adoption of this EO potential for operational activities.

Presented cooperation exploits the existing technologies developed in various ESA projects (Urban TEP, EDC) together with a new generation of global urban datasets available (World Settlement Footprint suite), to address above obstacles and streamline the production of high-quality urban information on SDG indicator 11.3.1 across all world regions in an easy interactive way. Both administrative and functional urban area analytical units are supported by the App with a goal to demonstrate the tangible support of national and local city authorities in developing countries to embrace EO technology in their work, to effectively monitor and analyse their urbanisation processes and to report on the SDG indicator 11.3.1 on sustainable urbanization.

Granted by ESA Earthnet funding the cooperation aims to support collaboration with UN Habitat on Sustainable Development (SDG) Goal 11 and the New Urban Agenda support.

Cities are generally warmer than their surroundings. This phenomenon is known as the Urban Heat Island (UHI) and is one of the clearest examples of human-induced climate modification. UHIs increase the cooling energy demand, aggravate the feeling of thermal discomfort, and influence air quality. As such, they impact the health and welfare of the urban population and increase the carbon footprint of cities. The relative warmth of the urban atmosphere, surface, and substrate leads to four distinct UHI types that are governed by a different mix of physical processes. These four types are the canopy layer, boundary layer, surface, and subsurface UHI. Surface UHIs (SUHI) result from modifications of the surface energy balance at urban facets, canyons, and neighborhoods. They exhibit complex spatial and temporal patterns that are strongly related to land cover and are usually estimated from remotely-sensed Land Surface Temperature (LST) data. In the context of ESA’ Climate Change Initiative LST project (LST_cci) we investigate how the LST of cities has changed over the last ~20 years (2002-2019) using nighttime data from Aqua MODIS. We focus on nighttime conditions when the agreement between the LST and the near-surface air temperature over cities is strongest. Our results reveal a consistent warming trend across all cities, that is on average (± SD) equal to 0.06 ± 0.02 K/year. Cities located in continental climates exhibit the most pronounced warming, of about 0.08 K/year, while those in tropical climates the least (~0.04 K /year). Our results also suggest that the cities in the Northern Hemisphere warm faster than cities in the Southern and that the cities with the strongest increase in nighttime LST are all concentrated in Middle East, where we estimated trends as high as 0.15 K/year (Doha, Qatar).

There is a significant disparity in access to electricity between the Global North and South. For example, in low-income countries, fewer than 50% of people have access to electricity. Moreover, many regions still face challenges in maintaining stable electricity access. In urban areas, spatial inequalities are pronounced; poorer neighbourhoods often lack or have only informal connections to the electrical grid (or off-grid access), leading to a noticeable absence of streetlights. The Sustainable Development Goals, especially SDG 7, stress the importance of universal access to reliable electricity. In poorer neighbourhoods where Artificial Light At Night (ALAN) is available, it is typically unshielded, resulting in inadequate lighting for nighttime outdoor activities and significant light pollution. To effectively contribute to the societal debate on the need for sustainable ALAN and to minimize unnecessary light pollution, access to high-resolution nighttime remote sensing data is crucial. However, our current understanding of ALAN largely depends on datasets from a limited number of remote sensing missions, which typically have sensors with low spatial and spectral resolution. Alternative, high-resolution sources such as images from the International Space Station (ISS) and new data sources like SDGSat-1 are not yet widely used. These novel and alternative sources provide improved spectral and spatial resolution. Our study provides insights into the potential for global monitoring of ALAN using high-resolution nighttime light remote sensing imagery. We also identify user requirements for upcoming satellite-based sensors in the context of a European Space Agency-funded research project, NightWatch

Urban areas are central to a range of sustainability challenges, ranging from land take and the loss of natural habitat to the exposure to climate change impacts. As a result, a large number of models have been presented that project future urban land change under different scenario conditions. The sustainability of future developments depends strongly on the characteristics of urban land, including for example the density, the building material, and the presence of slums. Yet, most of urban change models include only one type of urban land, corresponding with areas recognized as built-up land in satellite imagery. This severely limits their relevance for understanding urban development in general and for sustainability assessments specifically. Here, we present an urban growth model that includes multiple classes along the rural-urban gradient and that is applied to model urban development in five countries in Southeast Asia. In this model, change is driven by future population developments, but these can lead to both expansion and densification, depending on the scenario. In addition, we characterize the different types of urban land in terms of their building materials and demonstrate the relevance of this characterization for assessing future risk for river flooding. Interestingly, the expansion scenario leads to a lower expected annual damage in Lao PDR and Cambodia, while the densification scenario leads to a lower expected annual damage in Myanmar, Thailand, and Viet Nam. Finally we point at the opportunities that recent developments in remote sensing provide for better characterization of urban areas, and thus also for more relevant urban models.

In the context of GDA-APP (Global Development Assistance - Analytics and Processing Platform) project, a segmentation model has been developed in order to identify urban areas using Sentinel-2 composite image (NRGB). The objective is to create a fully-automatic module to delineate urban area for instance for change detection, informal settlements detection, damage infrastructure assessment, etc…

The modeling pipeline follows several training steps. The first step is corresponding to a pre-training for segmentation using BigEarthNet dataset ~500.000 patches of Sentinel-2 as input and its respective ESA Worldcover building layer as reference: in this way the model will learn how to interpret Sentinel-2 imagery with the objective of detecting urban area. The second step is to improve detection to building scale by using pairs of image of Sentinel-2 composite and Microsoft building layer corresponding mask with ~30.000 patches. The third step improves delimitation capabilities by using a similar dataset but by enhancing spatial resolution from 10m to 3m using a super resolution model. All model versions are made in order to be responsive to any type of urban landscape and performing the segmentation at a global scale; indeed selected images are located over various areas distributed worldwide to make it as much general as possible. Moreover the complexity of the task requires several training steps to go deeper in precision, in terms of spatial resolution and so in building delimitation. The overall architecture corresponds to a UNet composed of 34 layers with ResNet blocks, and optimized with the use of loss function such as focal loss, architecture and functions well known in machine learning for segmentation application. Current model is trained with 10m pairs of images (cf step 2), its performance is estimated through accuracy metric, giving an overall score of more than 95% however the real interest is find in the accuracy of buildings detection, which is approximately to 65%. By following each steps described above, pre-training and final learning with 3m spatial resolution imagery are promising for improve results.

Monitoring Sustainable Development Goal (SDG) indicator 11.3.1 on land use efficiency is crucial for sustainable urban development. This indicator, which assesses the ratio of land consumption rate to population growth rate (LCRPGR), helps urban planners and policymakers optimize land use and curb unsustainable urban sprawl. Efficient land use supports several interlinked SDGs by promoting denser urban living, reducing cities' ecological footprints, enhancing livability, and preserving natural resources. Thus, monitoring this indicator is vital for ensuring sustainable growth and improving quality of life in urban environments.

Earth observation (EO) time series offer a powerful tool for monitoring urban land use efficiency, providing key insights into the dynamics of urban expansion and development. This presentation will first introduce a state-of-the-art method for urban mapping at global scale, leveraging open EO data such as Sentinel-1 Synthetic Aperture Radar (SAR) and Sentinel-2 MultiSpectral Imager (MSI) data and deep learning. Then it will showcase the SDG11.3.1 LCRPGR results in 500 cities during 1985 to 2020 using existing built-up datasets derived from Sentinel-1/2 and the extensive archive of Landsat long time series. The findings demonstrate that while population datasets from various sources minimally affect LCRPGR calculations, different built-up datasets lead to significant variances. Moreover, challenges arise when employing improved built-up products derived from Sentinel-2 data together with the built-up products derived from Landsat data, impacting the LCRPGR calculations. Consequently, this has led to many cities showing a negative LCRPGR during 2015-2020, inaccurately suggesting a decline in density. These results highlight the urgent need to enhance the accuracy and consistency of built-up data, given its significant role in determining the values of SDG 11.3.1 Land Use Efficiency.

The Sustainable Development Goals (SDGs) are a universal agenda to address the world’s most pressing challenges. Robust monitoring mechanisms and timely, accurate and comprehensive data are essential in guiding policies and decisions for successful implementation of the SDGs. Yet current ways of monitoring progress towards the SDGs such as through household surveys cannot address the SDG data gaps and needs. Along with EO data, citizen science offers a solution to complement traditional data sources.

The complementarity of citizen science and EO approaches for SDG monitoring has also been acknowledged in the literature. For example, the authors of this contribution carried out a systematic review of all SDG indicators and citizen science initiatives, demonstrating that citizen science data are already contributing and could contribute to the monitoring of 33 per cent of the SDG indicators. As part of this review, they also identified overlap between contributions from citizen science and EO for SDG monitoring. One specific citizen science tool integrating citizen science and EO approaches that could complement and enhance SDG monitoring is Picture Pile. Picture Pile is a web-based and mobile application for ingesting imagery from satellites, orthophotos, unmanned aerial vehicles or geotagged photographs that can then be rapidly classified by volunteers. Picture Pile has the potential to contribute to the monitoring of fifteen SDG indicators covering areas, such as deforestation, post disaster damage assessment and identification of slums, among others, which can provide reference data for the training and validation of products derived from remote sensing.

This talk presents the potential offered by Picture Pile and other citizen science tools and initiatives focusing on urban applications to complement and enhance official statistics to monitor several SDGs and targets including SDG 11 Sustainable Cities and Communities. Recommendations will also be provided for how to enable partnerships and collaborations across data communities and ecosystems in order to mainstream citizen science and EO data for SDG monitoring and reporting of urban issues.

The rapid urbanization combined with insufficient low-cost housing supply in the Global South results in the proliferation of informal settlements. Our study addresses the pressing need for accurate information by User and Data-centric Artificial Intelligence (AI)-based methods for mapping informal areas. In collaboration with local communities and several (inter)national stakeholders, we co-designed an AI-workflow based on free-cost Earth Observation (EO) and geospatial data to map informal areas in eight cities across the globe. Together with our Early Adopter and Stakeholders, we identified local data questions and validation needs. For example, in Buenos Aires, the main question is to identify unmapped settlements (compared to the national registry). Presently, we are evaluating the performance of the Multi-Branch Convolutional Neural Network (MB-CNN) model across our pilot cities. The model takes Multispectral and SAR data in combination with additional geospatial features (e.g., building density) as input and delivers the segmentation map. This is done in preparation for increasing the reference data quality via our user portal. The initial model results (for informal areas) show for the city of Nairobi an F1 score of 0.79 and for Medellin an F1 score of 0.75. Mumbai, Salvador and Buenos Aires also performed relatively well, with F1 scores of 0.70, 0.61 and 0.57. In contrast, the model performs below 0.5 in Jakarta, Lagos and Mexico City (more complex cities in terms of morphology and reference data). The results indicate that the fusion of datasets provides higher accuracy than using only S-2. This can be attributed to the additional contextual information, which aids in more accurate identification and mapping. Cities with large and densely built-up settlements (e.g., Medellin, Mumbai, Nairobi) significantly improved when building morphology was added. Next, we will be improving reference data by crowdsourcing via our portal.

Informal settlements are the primary residential areas for the urban majority. Despite their significance, a lack of accurate data and often outdated records pose significant challenges for public entities in meeting residents' needs. Consequently, our understanding of the spatial distribution, evolving patterns, and growth over time of these settlements remains limited. However, emerging remote technologies offer new opportunities for mapping and collecting high-quality data. This presentation focuses on the utilization of urban data and AI/ML-based mapping technologies to gain deeper insights into the complex realities of informal settlements. In this context, we will present UNITAC's current research and introduce our work on the Building & Establishment Automated Mapper (BEAM), specialized software for AI/ML-based detection of building footprints in informal settlements

The BEAM tool, developed by UNITAC in partnership with eThekwini Municipality in South Africa, leverages AI to map rooftops in high-resolution aerial photography. It meets a crucial need identified by the municipality for automated mapping processes, crucial in a city where a quarter of residents reside in informal settlements, and census data updates occur only every 10 years. This results in a lack of accurate data about its population, particularly in informal settlements, complicating infrastructure planning and human settlement upgrades. Additionally, the BEAM tool is being upscaled for use with satellite imagery (currently it works on high-resolution aerial photography) in eight Central American cities. Consequently, the tool underscores its innovative support for city governments in the global South, leveraging machine learning to assist these governments in addressing key sustainable development goal targets and indicators, as well as tackling the urgent challenges of urbanization.