Conference Agenda

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

The European Space Agency (ESA) has established the Third Party Missions (TPM) Programme to enhance the accessibility and utilization of satellite data from non-ESA missions. This initiative allows ESA to distribute and support data from a variety of missions operated by international and commercial partners, including NewSpace companies, providing scientists and researchers with additional resources for a broad range of Earth Observation applications.

In this presentation, an in-depth overview of the TPM Programme will be provided, highlighting its objectives, benefits, and the diverse range of missions included under its umbrella. We will explore how the programme facilitates the integration of complementary datasets, thereby enriching the scientific community's ability to monitor and analyse global environmental and climatic changes, among others.

Aligned with the objectives of URBIS24, this presentation will focus on how TPM data supports urban monitoring and innovative EO-integrated solutions to address urban challenges. By leveraging these datasets, urban policymakers, researchers, and service providers can gain valuable insights into urban planning, climate resilience, infrastructure management, and more, fostering new collaborations and advancements in urban Earth Observation.

SatVu, a start-up company based in London (UK) is developing a constellation of ten satellites (“HotSats”) flying a Medium Wave Infrared camera, with the mission to capture thermal information of any target of the Earth during both night and day. Our MWIR sensor offers a unique perspective of the world, imaging at an unprecedented resolution of 3.5 m, and is a significant improvement over any commercially available space-based thermal sensor.

One area where high resolution thermal data is a game-changing technology is the example is the Urban Heat Island Effect (UHI). The UN expects 68% of people to live in urban areas by 2050, up from 55% today. As global temperatures are also rising, many more people will be vulnerable to heat-related illness in the coming years. This is especially true where rapid urbanisation coincides with high vulnerability to climate change.

Every year, innovative solutions are adopted by city officials. The diversity of climate adaptation plans highlights that a strategy effective in one location may not be easily applicable to another. Each city is unique, influenced not only by its geographical location but also by factors such as demographics, land structure, and other distinctive characteristics. Regardless of that, more granular and frequent measurements of heat distribution in urban areas should become a tool in assessing the cost, effectiveness, and urgency of the local authorities’ response to extreme heat events.

In this presentation, we will showcase some of the images captured by HotSat-1 launched in June 2023. We will present the outcome of our partnership with Office of Planetary Observations who used one of our earliest data products as part of their nature-based solutions service, allowing better planning and management of cities across the world’s urban greening assets.

Challenge

The relevance of thermal remote sensing satellite data has become increasingly recognised for urban environmental monitoring in recent years, especially for tackling the growing Urban Heat Island effect. The problem with current thermal satellite data is that they are either only available in very high to high temporal resolution and low spatial resolution (>1,000m) respectively from geostationary or sun-synchronous satellites, or low temporal resolution and moderate spatial resolution of 30-100m. Such data are therefore only of limited suitability when regular monitoring of small-scale environmental factors is required.

Methodology

constellr develops the HiVE (High-precision Versatile Ecosphere monitoring mission) constellation of state-of-the-art high-resolution visible, near, and thermal infrared satellites, planned for launch by the end of 2024, to monitor land surface temperature (LST). With a 4- to 1-day revisit time (1 sat 2025 to 5 sats from 2028), 30 meters native spatial resolution, and 4-band multispectral TIR capabilities from 8-12µm enabling a temperature accuracy up 1.5 K, HiVE is uniquely equipped to provide accurate and timely data urban areas.

The HiVe´s secondary optical VNIR payload provides 10 spectral bands (similar to Sentinel-2) from 400-1000nm enabling the use of super resolution techniques for thermal sharpening.

Expected results

We will present constellr HiVE mission concept, status and provide insights into our upcoming activities to ensure high data quality from mid of 2025. On top we will present the added value of HiVE data for urban and infrastructure monitoring. We will demonstrate simulated HiVE data based on airborne campaigns as well as constellr LST30 which incorporates multiple available thermal public mission data and applies the constellr proprietary LST retrieval algorithm leading to higher sharpness at a 30m spatial resolution. We apply a time series of LST30 data on Freiburg, Germany during the 2023 heatwave to understand specific localized urban heat resilience challenges.

Lead author: Airbus Dimitri - BOULZE / Special campaigns & partnerships

Co-Author: Dassault Systèmes - Frederic BOS / Senior Client Executive

Airbus and Dassault Systèmes started discussions in 2020 about the possibility to combine Airbus expertise in 3D models production from satellite high resolution imagery; and Dassault Systèmes capabilities in physical simulation to generate “Virtual Twins”, trustworthy 3D replica of any area of interest worldwide, and use them as playground to simulate various physical phenomena. Airbus and Dassault Systèmes namely worked on Virtual Twins over various urban areas to demonstrate use cases around predictive maintenance, monitoring, prevention and crisis management.

The Rationale of Airbus and Dassault Systèmes to push for an ambition on virtual twins, namely over cities, encompasses the following assumptions:

• The number of EO sensors has soared in the last 10 years, with a resulting surge in data volume as well as data type available to EO users. With Pléiades Neo today and soon with CO3D and its native stereo acquisition, Airbus is therefore securing access to a high quality and reliable source of data for 3D content that can feed new usages.
• 3D datasets are the new frontier, and we can expect that they gradually replace 2D datasets in a large panel of uses, both in the commercial and institutional sector. Various GIS software providers (Google Earth, Google Maps, QGis, ArcGis, etc…) are defining new OGC standards allowing to visualise large 3D datasets in accessible, sometimes free tools. 3D is already included in Google Earth and it’s likely that the majority of these tools will follow the same trend, which will trigger a new leap in geospatial analysis. In a matter of years, Copernicus Services may need high resolution 3D coverage the same way they need 2D coverage today
• The advent of cloud computing: AI based solutions and analytics have transformed the way both defence and commercial users are consuming geospatial data, providing faster means to exploit data, automate processing and combine with other datasets to extract relevant insights. These technical bricks in which Airbus and Dassault Systèmes have started investing several years ago are a cornerstone of any strategy around virtual twins as the need for automation, big-data and in-depth analysis is mandatory.

In 2021, in the frame of the “France Relance” plan, Airbus and Dassault Systèmes agreed on a common goal and formed a partnership to generate trustworthy simulations and indicators that can help better anticipate environmental, social, economic or sanitary crises and establish adequate prevention and response plans. The project covered three main objectives:

• See how 3D models can be integrated in Dassault Systèmes’ simulation software environment. The exploration of use cases was spread across a wide spectrum of physical phenomena: fluid dynamics (hydro or aero), acoustic, thermal or electromagnetic propagation. The list of these physical domains is not exhaustive. A matrix of about forty use-cases/verticals/simulation services has been established and to date less than a dozen have been explored. The potential remains very important.
• Test and use different LODs (Level of Details) of 3D models and run simulations over urban areas, where the complexity of the 3D environment is the highest, and the need is the strongest. More than 10 urban areas have been produced already, using Pléiades and Pléiades Neo sensors, to calibrate the relevance and specific added value to different use cases. Several production chains were also used to test various levels of details and editing, and compare how simulations are affected.
• Analyse market size and select use cases with higher score between technical challenge and business potential. The idea being to address real use cases, on-boarding end-users with prototypes as early as possible to confirm added value of the solution, while building and packaging a service offer.

The project is still ongoing, and close to 10 additional 3D models will be produced by the end of the project, making them available for a wide variety of simulations.

End-users have been on-boarded all along the project (primarily cities and institutional actors) making sure to drive the approach and help assessing the right technical trade-offs.

The COSMO-SkyMed (CSK) system is an operational constellation of 5 SAR satellites (3 of first generation + 2 of second generation) with very high performing capabilities: very high resolution, large swaths, unique radiometric accuracy, high geolocation accuracy, better than 12 hours revisit, and several other characteristics.

Among the several COSMO-SkyMed capabilities, one of the most important is the possibility to perform interferometric acquisitions using Spotlight and Stripmap imaging modes. Especially important is the possibility to perform interferometry between Stripmap data acquired by the first and second generation, thus allowing to take advantage of a huge and very long-lasting archive with a projection to the future (2 new second generation satellites will follow in 2025-2026). Currently the system is able to acquire 5 interferometric acquisitions every cycle of 16 days.

During all the years, ASI has implemented (with the support of e-GEOS) a so-called background mission to populate the catalogue with useful acquisitions. For this we have focused on performing Stripmap interferometric acquisitions over several targets, including all the major world cities (having more than 200,000 inhabitants). In this way we have now a huge archive over all the most important urban areas that has monitored the situation for more than 10 years.

Using these acquisitions, it is possible to generate very precise change detection maps (using multitemporal combinations, with coherence analysis) and to analyze also millimetric vertical ground movements using the PS technique. Such activities allow to monitor closely the urban areas in time, regardless of the cloud cover, taking advantage of the very high resolution of the Stripmap mode (3 m) which is complementing the Sentinel-1 capabilities providing a more detailed analysis over dense urban areas.

Prométhée Earth Intelligence is a French start-up founded in 2020 aiming to democratize the use of satellite imagery to offer high value-added services in environmental or strategic intelligence. It relies on proprietary data from its own satellites, with ProtoMéthée currently in orbit, followed in 2025 by the Japetus demonstrator. By 2027, the Japetus constellation of 20 nanosatellites will be fully operational to provide high-revisit and high-reactivity data acquisition capabilities. The data will be available through the proprietary Earth Observation Platform (EOP), which enhances raw data by merging it with other complementary information sources to build solutions for operational services. This agile platform acts as a unique and aggregative access point which is linked to a cloud-based digital processing system. It is designed to facilitate EO access to a broader user community.

In particular, Prométhée Earth Intelligence offers an operational solution to protect cities from flooding, splitted in three application levels, by correlating physical and human geography :

• Situational Awareness Service to Understand, delivers a flood vulnerability map based on topographic (morphology of the relief) and contextual (land use and climate) information.
• Early Warning System to Prevent and Anticipate, highlights all the critical infrastructures and locates the potential landslide zones, evaluating the most endangered areas in case of flooding.
• Rapid Response service to Act, delivers a flood map emphasises impacted buildings and transport network status. A daily refresh will be computed on it, allowing accurate monitoring.

This new capability solution delivers a decision support capacity helpful for the authorities to handle flood events in urban areas. It is a scalable tool that complements and interfaces with existing information systems, based on the informational power of GEOINT and adaptable to current and future operational needs. This will be detailed through a scientific poster.

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 surface fabric identification and mapping present a significant challenge in the field of Earth Observation. Precise knowledge of surface characteristics is essential for effective urban planning and climate research. However, the presence of artificial materials in urban areas and mixed pixels complicates the accurate analysis of spectral data from multispectral and hyperspectral sensors. In turn, the current hyperspectral libraries, which rely on spectroradiometers, do not offer enough spectral variability from artificial materials for successful Machine Learning model training and accurate material detection. To address these gaps, the urbisphere urban hyperspectral library is currently being developed, utilizing the Spectral Evolution RS-3500 spectroradiometer and HySpex VS-620 Camera.

Today, the urbisphere urban hyperspectral library contains more than 5000 in-situ hyperspectral measurements from various natural and artificial materials collected from several European cities (e.g., Heraklion, Paris, and Berlin) and is planned to be enriched further in the coming years. The library also contains the respective adjusted spectra for several satellite sensors (e.g., Sentinel-2, Landsat-8, Planet SuperDove, EnMap, PRISMA, etc.), enabling satellite image classification without the need for time-consuming on-site data collection.

In this study, the current performance of the urbisphere urban hyperspectral library was tested over the broad urban area of Heraklion city. Specifically, the X-SVM classifier was trained using only the adjusted satellite spectra from the library for the satellites of Planet SuperDove, Sentinel-2, Landsat-8, EnMap, and PRISMA, while the trained models were applied to the respective satellite images acquired between August 3rd and 5th, 2023. The results highlight the current performance of the library for satellite image classification and the unique limitations that originate from the low spatial resolution for the Hyperspectral satellites (EnMap, PRISMA) and, on the other hand, from the low spectral resolution from the multispectral sensors (Sentinel-2, Planet SuperDove).

Urban planning and city governance require innovative solutions to face new urgent requirements and priorities. Leveraging advancements and the integration of Earth Observation (EO) with Artificial Intelligence (AI) methodologies has become critical in urban management.

Using AI models to chain multiple processes in a pipeline, from Super Resolution (SR) to Change Detection (CD) and Building Footprints (BF) extraction, is crucial for urban delineation, providing stakeholders with accurate results for informed decision-making. The project IRIX4US aims to monitor urban dynamics accurately for mobility, sustainability, urban planning, and accessibility in urban areas.

Engaging a broad set of relevant users and stakeholders, from public organizations to private industry, provided an opportunity to develop an EO-integrated solution tailored to the needs of urban experts and decision-makers. The solution consisted in a comprehensive AI pipeline:

1. Fine-Tuned SR of Sentinel-2 (S2) images: An AI-driven solution has been conducted to enhance their spatial resolution up to 2.5 meters. The model was trained using data from very high-resolution satellite imagery at a European scale. This process outputs a realistic representation of buildings, ensuring sharp edges and clear differentiation from surrounding objects such as roads.
2. Segmentation and BF extraction: IRIX4US adapts tested segmentation models to the super-resolved S2 imagery in urban landscapes, extracting visible and near-infrared (VNIR) bands and BFs using high-quality labels provided by champion users.
3. CD with AI Models: AI models have been employed for identifying differences in BFs between different images over time. These AI models were trained using temporal change data provided by champion users, allowing for the effective monitoring of urban development patterns in a multi-temporal context.

The results within the IRIX4US provides a dynamic and time-saving advancement for urban planning, proven feasible and scalable applications such as building segmentation, building change detection, illegal settlement identification and construction damage assessment.

This study investigates the efficacy of image restoration techniques of satellite EO images with a focus on super-resolution of Sentinel-2 and PlanetScope products. The ultimate goal is to develop a robust image restoration model capable of producing enhanced multispectral aerial-like imagery. The study is investigating several semi-supervised generative algorithms including SR-GANs, EDSR-GANs, WDSR-GANs, Lambda-PNN and W-Net.

The neural network architectures examined exhibit variations in their learning approaches and the potential utilization of a HR panchromatic component. For instance, the SR-GANs, EDSR-GANs, WDSR-GANs and WNet architectures are trained within a semi-supervised framework, i.e. supervising the training process of the generative models by incorporating multispectral HR target images. The Lambda-PNN network is trained within a fully unsupervised framework, hence no HR target images are adopted during its training phase. On the other hand, Lambda-PNN and WNet include a HR resolution panchromatic channel aiding the image super-resolution task. For our assessment with Lambda-PNN and WNet architectures, we opted for a panchromatic channel from an aerial image captured at a spatial resolution of 75cm either within the same date and in year 2019.

From our preliminary experiments, we have observed that GAN architectures which do not require a high-resolution panchromatic band can reconstruct HR scenes only for synthetic LR image datasets at 3m resolution obtained by downscaling aerial images. Pan-sharpening architectures like Lambda-PNN do not require a multispectral ground truth for training. However, when fed with Sentinel-2 and PlanetScope images, such architecture can produce synthetic images whose spatial structure is preserved (low structural loss) but yields unrealistic results regarding spectral information.

Among the preliminarily investigated architectures, the only architecture yielding consistent and plausible predictions is W-NET, a GAN fed with panchromatic and LR images and trained using HR target images employing a supervised approach. Furthermore, we are dedicating our effort in quantifying the reliability of generated images with respect to the introduction of spatial and spectral artifacts.

A myriad of global/regional datasets have provided valuable insights into environmental dynamics at global scale, including urban environments, however they often fall short of capturing the fine-scale nuances of the state and dynamics at local levels. Most existing datasets lacks the resolution and specificity required to address the diverse monitoring needs of urban stakeholders, particularly in densely populated or rapidly changing urban landscapes.

In response to these limitations, there is a growing recognition of the need for human-in-the-loop approaches, wherein stakeholders actively engage in the process of data collection, analysis, and interpretation to augment existing datasets and tailor monitoring efforts to local contexts. In this presentation, we will present a new agile cloud-based solutions that empower users to independently create and update urban datasets using free and open Copernicus Sentinel and NASA Landsat data, thereby overcoming the challenges associated with existing global datasets and fostering a more dynamic and responsive approach to urban environmental monitoring.

Developed as part of the EU 100Ktrees activity, based on the elaborated needs of municipalities worldwide, you will hear how complex machine learning frameworks and automated satellite data acquisition has been turned into user friendly cloud-based web applications for scalable mapping of urban environments on demand. You will learn how multitemporal satellite data and automated data analysis can turn raw satellite data into scalable information about urban heat islands, green spaces, flood exposure and impervious surfaces. And you will discover how these tools, and others, are vital to address the existing data gap across urban landscapes worldwide and how they can be used to underpin comprehensive and dynamic monitoring regimes.

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.

The characterization of structural changes in urban areas, and specifically the current trend towards verticalization, is a crucial step toward understanding urbanization phenomena at the global level. The use of spaceborne remote sensing data for this task has grown over the last decade, focusing on SAR and multispectral data, often jointly used. In particular, very high resolution (VHR) data, increasingly available in large volumes, calls for efficient and accurate 2D/3D change detection techniques, able to go beyond existing methods, focused either on detecting buildings footprint changes over time or on extracting changes in the number of floors/height of the same buildings. In this work, we present a complete framework applicable to VHR SAR temporal sequences able to characterize 2D & 3D changes at the same time. The methodology involves the extraction of altered buildings in the initial phase and subsequently performs a building segmentation, with specific emphasis on discerning changes in building height. The identification of changed urban core areas is performed using an unsupervised temporal clustering applied to the original sequence of SAR amplitude and coherence images. Subsequently, building segmentation in the initial and ending image of the sequence is performed thanks to a deep learning U-Net architecture, allowing a quantitative characterization of the 2D changes. Finally, the building height extraction is accomplished through the utilization of a novel ResNet deep learning architecture. The proposed framework has been tested using a time series of three years of COSMO-SkyMed data, from January 2019 to November 2021, over the city of Milan, Italy. Experimental results in the "Gae Aulenti" and "City Life" areas show that 2D and 3D changes are correctly detected and the use of the proposed machine and deep learning framework significantly increases the ability to achieve a better characterization of structural changes in urban areas.

While the significance of built-up volume and density for future sustainability and resilience of the built environment is widely recognized, the interplay between 3D built-up patterns, economic development, and local planning policies remains relatively unexplored. To address this gap, we integrate novel global data from the World Settlement Footprint 3D (WSF® 3D) - encompassing building area, height, and volume -, with socioeconomic statistics and information on planning policies across all countries and over 12,000 urban clusters worldwide. Our analysis begins with enhancing the original WSF3D dataset to provide a more accurate representation of high-rise buildings exceeding 50 meters. This enhancement involves integrating data from the Emporis database, a leading source of tall buildings information globally. Subsequently, we merge the enhanced WSF3D data (WSF3Dv2) with socioeconomic statistics sourced from the World Development Indicators (WDI) database and data on zoning regulations and land-use policies provided by the World Bank. For the city-level analyses, we additionally utilize the Urban Center database provided by the Joint Research Center (JRC) of the European Commission. Through our study, we offer a comprehensive and spatially detailed understanding of the global 3D building stock, unveiling intricate relationships between 3D settlement morphology, economic development, and local planning regulations. This empirical evidence strengthens the understanding of the global megatrend of urbanization and provides crucial insights to enhance the effectiveness of land use and spatial development policies aimed at promoting (urban) sustainability and resilience.

Accurate building height estimation is essential for sustainable urban planning, monitoring, and environmental impact analysis. However, conducting large-scale building height estimation at a fine spatial resolution is challenging, especially using open-access satellite data. Existing large-scale solutions provide height at coarse spatial resolution (500 m - 90 m), a better resolution can provide more comprehensive understanding of urban development.

We propose an advanced deep learning model, T-SwinUNet, specifically designed for large-scale building height estimation at a fine spatial resolution of 10 m. The model harnesses salient features from the spatial, spectral, and temporal dimensions of the Sentinel-1 SAR and Sentinel-2 MSI time-series data.

In T-SwinUNet, we integrated the semantic feature learning capabilities of the CNN encoder with the local/global feature comprehension capabilities of Swin transformers. With added temporal attention, the model learns the correlation between constant features (mostly geometry) and variable features (e.g. shadow) of building objects over time. This not only aids in differentiating building from non-building objects but also condition model to learn salient building height features. We equipped T-SwinUNet with uncertainty prediction, which helps in assessing model’s robustness and transferability to new areas. Knowing uncertainty in predictions helps stakeholders to make informed and careful decisions.

The model is evaluated on data from the Netherlands, Switzerland, Estonia, and Germany. The extensive evaluation and comparison with state-of-the-art DL models show that our proposed T-SwinUNet model surpasses SOTA by achieving an RMSE of 1.89 m at 10 m spatial resolution. We conducted a detailed ablation study to understand the impact of time-series data, each modality, multi-task learning and others. Further assessment at 100 m resolution shows that our predicted building heights (0.29 m RMSE, 0.75 $R^{2}$) also outperformed the global building height product GHSL-Built-H R2023A product (0.56 m RMSE and 0.37 $R^{2}$).

Accurate determination of building heights is crucial for urban 3D development analysis and disaster risk assessment. State-of-the-art (SOTA) techniques typically treat height retrieval from buildings as a regression problem. For instance, [1, 2] propose supervised Multimodal Deep Learning (DL) frameworks to estimate building heights using Sentinel-1 (Sen-1) and Sentinel-2 (Sen-2) data.

In this work, we employ an Attention-based U-Net model for building height estimation, relying solely on radar information provided by Very High-Resolution (VHR) COSMO-SkyMed (CSK) data. We utilize a CSK Level-1D Stripmap Himage acquisition mode with a spatial resolution of 2.5 meters in Ascending orbit direction, covering the entire metropolitan area of Milan city for the model training. Ground Truth (GT) labels are derived from the Normalized Digital Surface Model (nDSM) and refined by using a binary footprint mask from OpenStreetMap (OSM) data to exclude non-built-up (BU) areas.

Our proposed model exhibits robust performances in terms of Root Mean Square Error (RMSE) on external test sites in the cities of Pavia, Sant’Angelo Lodigiano, and Lodi, with final error values of 0.781, 0.731, and 1.487 meters, respectively, outperforming previous studies [1, 2]. To further validate the model, the average error outside the buildings was also evaluated. The results reveal a general underestimation of building height as their actual height increases, indicating an avenue for future research.

Notably, our method capitalizes on CSK radar data, offering a swift solution for mapping 3D BU area features owing to its VHR, weather-independent capabilities, and rapid emergency response.

REFERENCES

[1] Yadav, R., https://arxiv.org/abs/2307.01378

[2] Bowen, C. et al., https://www.sciencedirect.com/science/article/pii/S1569843223002236

CARS is a CNES open-source 3D reconstruction software part of the Constellation Optique 3D (CO3D) mission. CARS stands out from other MultiView-Stereo methods due to its highly parallelizable design, capable of addressing large volumes of data for processing on an HPC cluster or personal machine.

Designed as a modular set of applications, CARS allows user to plug in new public or confidential contributions, such as new applications or pipelines. Using this plug-in concept, we recently addressed the need for LOD2 semantized meshes on urban areas. The new CARS plug-in makes the most out of intermediate CARS products such as uncertainty and classification layers to create LOD2 meshes.

Surface temperatures are central to the surface energy balance, and particularly in cities link to human thermal comfort and energy consumption. Since, cities have a strong vertical component, estimating the surface temperature for the complete three dimensional (3D) urban surface is important. While satellite remote sensing holds a strong potential in observing city-wide and global urban surface temperatures, these need to be complemented with in-situ infrared observations and modeling to achieve the assessment of the complete 3D surface temperature.

In this study, a sub-building scale three-dimensional (3D) energy balance model is evaluated using a novel ground-based thermal camera observatory in Berlin. Four thermal cameras (OptrisPI160) were mounted on an 80 m tall building, overlooking a mix of low-rise residential, parks, trees from all cardinal directions. 3D urban surface temperature was modeled using an extension of the energy balance model TUF-3D model (Krayenhoff and Voogt, 2007) including a vegetation component (VTUF-3D, Nice et al., 2018).) Earth Observation products (land cover, building and vegetation heights) were used to parametrize the 3D urban form of the study domains, while forcing data were available from meteorological measurements on the same building. A total area of 0.2 km² was simulated with a 5 m spatial resolution for 3 – 6 August 2022. The camera brightness temperatures observations were corrected for emissivity to conclude to surface temperature. Detailed emissivity maps were derived using land cover and reference spectral library information.

The diurnal pattern of modelled surface temperature was found similar to the observed one for different surface types (MAE ranging between 3-10 C depending on the area and time of day, with error increasing during daytime). VTUF-3D simulated surface temperatures for more areas in Berlin will be used to assess the complete temperature from satellite thermal observations, such as Sentinel-3.