The study determined the influence of changes in land use and land cover (LULC) on land surface temperature (LST) over a 33-year period based on a medium-sized European city (Poznań, Poland). The LST was estimated from Landsat 5, 8 and Terra (MOD11A2v6) satellites. The local estimation of climate patterns was based on the Local Climate Zones (LCZ) classification utilised with the methodology proposed by the World Urban Database and Access Portal Tools (WUDAPT). Moreover, the Copernicus’ imperviousness density product (IMD) was used. Between 2006 and 2018 the area with IMD of 41–100% increased by 6.95 km², 0–20% decreased by 7.03 km². The contribution of built-up LCZs increased by 7.4% (19.21 km²) between 1988 and 2021 reaching 13% (34 km²) within open mid-rise LCZ. Due to urbanisation and reforestation, low plants LCZ shrunk by 12.7%. For every 10% increase in IMD, LST increases by up to 0.14 °C. Between 1988 and 2021 the LSTm in specific LCZs rose from 1.52 up to 2.97 °C. As per LST models LCZ change from natural to built-up led up to 1.19 °C LST rise. The increase of the LSTm was registered even when the LCZ remained unchanged. The results highlight a clear trend of intensifying urban heat island effects driven by the transformation of natural and semi-natural areas into impervious and built-up surfaces. The spatial distribution of LST patterns strongly correlates with the extent and density of artificial surfaces, as confirmed by both remote sensing data and LCZ classification. Additionally, the study emphasizes the utility of integrating multi-source satellite data with standardised urban classification methods to detect fine-scale thermal responses to urban development. These insights provide valuable input for urban planning and climate adaptation strategies aimed at mitigating future temperature rises in expanding urban areas.

How to cite: Zwolska, A., Półrolniczak, M., and Kolendowicz, L.: Urban growth’s implications on land surface temperature in a medium-sized European city based on LCZ classification, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-273, https://doi.org/10.5194/ems2025-273, 2025.

Water scarcity is one of the most critical impacts of climate change in many parts of the world. Water scarcity results from a combination of limited or uneven precipitation, excessive consumption, and inefficient management practices driven by various economic activities, and this often occurs in metropolitan areas. This study centres on the Brașov Metropolitan Region (BMR), situated in central Romania, a region undergoing a significant increase in average temperatures while maintaining relatively stable annual precipitation levels. Despite the overall consistency in precipitation amounts, climate projections and historical analyses indicate an intensification in the frequency and severity of extreme hydrometeorological events, notably heavy rainfall episodes and prolonged drought periods, which collectively pose growing challenges for sustainable water management in the area. At the same time, the BMR is defined by population increase, changing consumption patterns, urban expansion, and economic growth (including tourism intensification). All contribute to an increasing pressure on water resources, which become insufficient in some periods of the year. Different indicators were used to assess the water scarcity in the area of interest, such as the Falkenmark Indicator, Green-Blue Water Scarcity, and Water Stress Index, in the present climate and under different climate scenarios and socioeconomic perspectives. The study employs data and information from publicly available sources and data collected from local sources during the project implementation and the outcomes of hectometer scale earth systems modelling focusing on the floods that occurred in the past decade, leveraging available meter scale urban data sets available for the BMR. 

The results support the co-development of viable solutions that consider both the climatic and socioeconomic pressures and are firmly based on the long-term participatory approach involving the quadruple helix, such as policymakers, business, citizens (including vulnerable communities), and academia.

The quadruple helix perspective on water scarcity was given in the Living Lab Brașov, where the 27 stakeholders (including vulnerable groups) confirmed it as a critical challenge. Associated risks, drivers, and measures were identified to understand and address BMR's water scarcity. 

The results are obtained in the project Climate-Resilient Development Pathways in Metropolitan Regions of Europe (CARMINE), funded by the Εuropean Union under the Horizon Europe Programme (Grant agreement 101137851). 

How to cite: Cheval, S., Amihaesei, V., Cardos, T., Craciunescu, V., Dinicila, S., Gabrian, S., Falcescu, V., Ioja, C., Marin, M., Micu, D., Nita, M. R., Tudose, N. C., Ungurean, C., and Velea, L.: Vulnerability to water scarcity in metropolitan areas under climate change and development challenges, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-584, https://doi.org/10.5194/ems2025-584, 2025.

Current research on future urban climate involves several steps from global climate simulation planning (e.g. CMIP), through downscaling and down to impact modelling. This process is often time-consuming and can introduce physical and technical inconsistencies due to the variety of tools and assumptions involved. With the advent of coupled km-scale multi-decadal modelling, pioneered in the nextGEMS project and operationalized by Destination Earth, the workflow can now be accelerated and simplified by directly performing urban climate analysis on the global simulations.

We present what is, to our knowledge, the first analysis of urban climate on global km-scale climate simulations. We exploit the fully coupled IFS-FESOM and IFS-NEMO simulations produced on the nextGEMS project. These span for several years across horizontal resolutions of 28, 9 and 4.4 km, and include a 30-year historical simulation (1990-2020) at 9 km, as well as a 30-uear future scenario (scenario 2020-2050) following the SSP3-7.0  scenario.

We present a robust automated methodology that, based on surface static information, allows to gather and filter simulation information over all kinds of urban areas and their rural references worldwide. We then show the spatiotemporal features of such urban and rural model representations consistently for hundreds of cities worldwide. We further analyze the sensitivity of the nextGEMS present-day multi-annual simulations to spatial resolution, with a particular focus on the thermal aspects of urban climate and its contrast to the rural counterpart in each season. By exploiting km-scale surface temperature remote sensing products by LSA-SAF, we can confirm that the models are able to capture key spatial and temporal features of the typical surface urban heat island diurnal cycle, and that performance improves with increasing spatial resolution.

Finally, we make use of the available multi-decadal simulations by IFS-FESOM to explore the evolution of urban climates for both past and future scenario and group urban areas according to their expected change. We further investigate the possible amplifiers, such as orography or urban density, in an attempt to explain the different trends for cities worldwide found in the simulations.

How to cite: Pedruzo Bagazgoitia, X., Sützl, B., Dutra, E., McNorton, J., Rüdiger, C., and Tsiringakis, A.: Global urban climate analysis on multi-decadal km-scale climate simulations, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-651, https://doi.org/10.5194/ems2025-651, 2025.

Cities play a fundamental role in climate at local to regional scales through modification of heat and moisture fluxes, as well as affecting local atmospheric chemistry and composition, alongside air-pollution dispersion. Vice versa, regional climate change impacts urban areas and is expected to affect cities and their citizens increasingly in the upcoming decades when the share of the population living in urban areas is growing and is projected to reach about 70 % by 2050. This is especially critical in connection to extreme events, for instance, heat waves with extremely high temperatures exacerbated by the urban heat island effect, in particular during night-time, with significant consequences for human health.

From the perspective of recent regional climate model development with resolution achieving city scales within convection permitting RCMs, parameterization of urban processes plays an important role to understand local/regional climate change. The inclusion of the individual urban processes affecting energy balance and transport (i.e. heat, humidity, momentum fluxes, emissions) via special urban land-surface interaction parameterization of local processes becomes vital to simulate the urban effects properly. This enables improved assessment of climate change impacts in cities and planning adaptation and/or mitigation options, as well as adequate preparation for climate-related risks (e.g. heat waves, smog conditions, etc.).

We introduced this topic to the CORDEX platform, within the framework of flagship pilot studies on challenging issues and gaps in regional climate change knowledge. The main aims and progress of this activity will be presented, especially an analysis of Stage-0 experiments using case studies of heat wave and convection episode within ensemble of nearly 40 simulations for City of Paris with convection permitting RCMs from different groups over the world. Further outlook of long term (10 years – Stage 1 experiment) climate simulation with these models in common strategy to IMPETUS4CHANGE Horizon Europe Project will be presented as well, The development of Global Satellite Cities experiment will be introduced as another part of Stage 1 experiment. Outlooks for further experiments will be explained as well.

How to cite: Halenka, T., Langendijk, G., and Hoffmann, P.: CORDEX Flagship Pilot Study URB-RCC: Urban Environments and Regional Climate Change – Where We Are and Where We Are Going, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-673, https://doi.org/10.5194/ems2025-673, 2025.

Extreme rainfall is expected to increase because of global warming, driven by the increase in atmospheric heat which boosts the atmospheric water content, subsequently altering precipitation patterns. The Clausius‐Clapeyron (CC) equation dictates a 7\% increase in atmospheric capacity to hold water for every 1 °C temperature increase, and although many deviations from CC scaling have been observed, there is a consensus in the literature that extreme precipitation is changing. Urban areas are particularly affected by weather extremes, although the impact of urbanization on intense rainfall remains difficult to quantify. This study investigates changes in extreme precipitation events using daily data from 6028 weather stations worldwide, extracted from the Global Historical Climatological Network (GHCN). While previous studies examined similar trends and found the largest frequency increase for the most intense events, this work also incorporates urbanization factors. The analysis focuses on the 60 most intense precipitation events within the 1962-2021 timeframe, evaluating trends in frequency at each station, and considering stationarity assumptions. Two urbanization indices were used to categorize stations, revealing correlations with changes in extreme event frequency, indicating that the occurrence of extreme precipitations is increasing significantly more in densely populated urban areas. In addition to these observations, the study conducted seasonal analyses, revealing that, for both indices, the frequency versus urbanization index trend is primarily attributed to measurements in the autumn and winter seasons. The observed changes offer a valuable insights into the intricate relationships between heavy rainfall and urban areas, highlighting a correlation between the frequency of extreme precipitation events and urbanization at a global scale. Future research should focus on how specific variables contribute to the observed variations in the characteristics of extremes. These deeper investigations can provide insights into the underlying physical mechanisms driving the variations in the characteristics of extreme precipitation found in this work.

How to cite: Guccione, A., Bassi, P., Desbiolles, F., Borgnino, M., D'Andrea, F., and Pasquero, C.: Global Extreme Precipitation Changes in Relation to Urbanization, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-27, https://doi.org/10.5194/ems2025-27, 2025.

Oxygenated volatile organic compounds (OVOCs) are important precursors and intermediate products of atmospheric photochemical reactions, which can promote the formation of secondary pollutants such as ozone (O₃) and secondary organic aerosol (SOA). The photochemical age parameterization model is widely used to analyze primary and secondary sources of OVOCs. However, a key challenge lies in selecting appropriate tracers, chemicals used to estimate contributions from different emission sources. Accurate tracer selection is crucial for improving source apportionment accuracy, yet it is often constrained by local emission inventories and may not fully capture rapid atmospheric chemical transformations, introducing uncertainty in OVOC apportionment. This study presents a novel approach integrating eight different machine learning methods to identify optimal tracers for OVOCs during extreme summer temperatures (experimental group) and average spring temperatures (control group). Our results demonstrated notable differences in tracer effectiveness between these two groups. In the spring, toluene and carbon monoxide (CO) were identified as the most effective tracers for OVOCs with high and low reactivity, respectively. In the summer, acetylene or CO were better suited for moderate and low reactivity OVOCs. By incorporating machine learning for tracer selection, we significantly improved the accuracy of the photochemical age parameterization model. The machine learning outputs correlated well with the model’s performance, particularly in terms of fitting accuracy of OVOCs. However, extremely high temperatures during summer disrupted the usual patterns of OVOC production and removal, which led to inconsistencies in matching high reactivity OVOCs with their tracers. Future research involves collecting more data on OVOC behavior under high-temperature conditions and applying Fourier transformation techniques. This will help in identifying characteristic patterns and improving the dynamic accuracy of our model.

How to cite: Zou, Y., Guan, X., Flores, R., Yan, X., Liang, X., Fan, L., Deng, T., Deng, X., Ye, D., and Doskey, P.: Optimizing OVOCs Source Apportionment with Machine Learning-Enhanced Photochemical Age-based Parameterization Model, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-65, https://doi.org/10.5194/ems2025-65, 2025.

Air pollution, particular aerosols and their precursors, has a substantial impacts on local weather and climate by increasing cloud condensation nuclei and altering how much solar energy is absorbed or reflected by the atmosphere. To accurately model these impacts, emissions inventories, dispersion models, and receptor models perform best when using high-resolution inputs. Currently, Europe has adopted regulations aimed at improving air quality and encouraging detailed studies of emission sources. While emission records over time indicate an overall decline, the transport sector has grown in recent decades, mostly because an annual increase in vehicle numbers. Although advancements in vehicle technology aim to reduce emissions, concerns remain that the increasing number of vehicles on the road may hinder this progress. Additionally, a critical knowledge gap has been identified in the bottom-up approach used to estimate emissions from transit vehicles and tourism activities.

Our study identifies and evaluates the issue of vehicle congestion on the roads during the summer, primarily driven by transit demands and tourism activities.

The methodology to capture an understanding of traffic-related emissions from the summer vehicle peak was developed. Summer traffic peak was estimated by comparing the summer vehicle numbers with those of other parts of the year. Vehicle numbers were recognized by vehicle counters located on a Slovenian highway junction in the year 2021. Moreover, the study also revealed the emissions from the summer traffic peak, calculated by the COPERT emission model.

We observed that, on an average summer day, there are up to 11,520 additional vehicles on Slovenian roads. Our study found that in the year 2021, on average, there were increases of 85%, 19%, 34%, and 17%, with up to 88%, 33%, 63%, and 32% increases in motorcycles, buses, passenger cars, and light duty vehicles. Meanwhile, it is recognized that the decrease in heavy duty vehicles is, on average, −14%. Those results help to understand contributions to estimation of urban source of emissions, which lead to improve the inputs data for the dispersion and additional atmosphere models. The methodology could also be copied in other places.

How to cite: Dolšak Lavrič, P., Bec, D., Rus, M., Ciglenečki, D., Kukec, A., and Ogrin, M.: Contribution of Tourist and Transit Vehicle Emissions to Air Pollution on Slovenian Roads during Summer, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-98, https://doi.org/10.5194/ems2025-98, 2025.

The air quality in ancient Roman cities is still unclear, but historical sources suggest that there was noticeable air pollution, at least in terms of odour. As a pilot study for a smaller settlement, we simulated the combined pollution from heating, cooking and industrial activities. The Roman vicus modelled is located in the modern town of Eisenberg (Pfalz), in the Pfalz region, near Kaiserslautern. Utilising archaeological data on pottery locations and historical buildings, the simulation was conducted to estimate air pollution levels around the vicus.

The simulation utilised the German regulatory pollution dispersion model AUSTAL, driven by weather data from the Copernicus European reanalysis (CERRA) and the SRTM topographic dataset. The Roman vicus consisted of almost twenty buildings, most of which have been archaeologically excavated and are well documented. The vicus is known to have housed potteries, but in most cases the actual use of the excavated houses is unknown. Therefore, we had to assume the location of the pottery workshops in the eastern part. The industrial sources were modelled after measurements taken during experimental pottery production by LEIZA, Mainz, in a reconstructed kiln. The residential sources were modelled after hourly recordings of firewood usage in Nepal, where traditional rural buildings are remarkably similar to those of the Roman period in Central Europe.

The simulation showed clearly the benefits of considering daily cycles rather than averages in the modelling of the air quality. The results obtained demonstrated that, in general, the pollution levels were found to be low when compared to today's limits. However, it turns out that the levels of pollutants are similar to those found in contemporary villages where houses are mainly heated with wood and briquettes.

How to cite: Drüe, C. and Jonas, K.: An experimental reconstruction of the air quality in the Roman vicus Eisenberg, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-327, https://doi.org/10.5194/ems2025-327, 2025.

The Regions4Climate project, funded under Horizon Europe, supports transformative adaptation by co-developing and testing tailored climate resilience solutions in 12 European regions. One of these is Pärnu, Estonia’s coastal “summer capital,” which—by Nordic standards—is particularly vulnerable to heat due to its unique geographic and climatic setting. The case study focuses on mitigating urban heat-related risks.

Urban heat island (UHI) conditions in Pärnu had not been systematically studied before. To fill this gap, we applied a threefold methodological and approach: (1) deploying a dense real-time weather sensor network, (2) analysing satellite-derived land surface temperatures, and (3) simulating thermal comfort under various climate and land use scenarios using microscale modelling. Together, these methods allow us to observe and understand heat dynamics from regional to street level.

Since June 2023, SEI Tallinn and partners have operated 50 sensors measuring temperature and relative humidity every 10 minutes across a 10×15 km area. Sensor density is highest around the city centre with its diverse microclimatic conditions—residential areas, parks, commercial districts, and beaches—and decreases towards rural surroundings. Locations were selected following the Local Climate Zone framework, considering critical social infrastructures. Results reveal strong daytime UHI heterogeneity, with cooler temperatures in parks and coastal areas and warmer conditions in (often close-by) built-up zones. At night, a more spatially extensive UHI develops, peaking around the city centre. Real-time data are publicly accessible via a dedicated visualization tool.

To complement these measurements, 15 clear-sky warm days between 2013 and 2024 were processed using Landsat 8 data to generate 100 m resolution land surface temperature maps for midday conditions. These maps identify heat hotspots as well as the cooling influence of green and blue infrastructure, guiding hotspot selection for microscale modelling.

Four representative sites—plus a planned new train station area—were selected for ENVI-met simulations at 1 m resolution. Using the Physiological Equivalent Temperature index, we assessed current and future thermal comfort conditions and detected resilience opportunity areas in the city. Simulations quantify heat exposure and mitigation potential of increased vegetation, shade, and urban form changes under climate change.

By integrating data across scales, our approach offers specific, place-based recommendations for heat-resilient urban planning in Pärnu. It underscores the value of existing green and blue spaces, supports their expansion, advocates for heat-conscious building standards, and promotes strategies to reduce daytime heat uptake—particularly in central areas—to protect vulnerable groups and strengthen the climate resilience of Estonia’s “summer capital.”

How to cite: Hoy, A., Glodeanu, A., Garcia, I., and Cheng-Wei Yu, A.: Towards a Heat-Resilient Pärnu: Integrating Sensor Networks, Satellite Data and Microscale Modelling, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-367, https://doi.org/10.5194/ems2025-367, 2025.

Urban climate analyses have a wide range of different targets, including average values of different meteorological variables, percentiles and number of exceedances of certain threshold values. At least 30 years of data are required for this type of analysis. For large scale analysis model results of several ten kilometres resolution are either available for 30 years and more, or they may be calculated with a coarse resolution model in some foreseeable time. However, the urban effects may not present in these type of data. In any case, the coarse resolution data do not provide any inner-urban differences. These can only be found in model results of a resolution of well below 1 km. When aiming at differences in street canyons or next to buildings, the resolution should be very high and not exceed several meters. The high-resolution models that may be used to produce these type of data in a dynamic simulation are very resources consuming and the waiting time is enormous. A dynamic simulation of 30 years is much too time consuming. Therefore, only a few selected meteorological situations are dynamically calculated. These must be selected correctly in order to support the objective of the urban climate analysis. Average temperatures can then be derived by selecting several meteorological situations and using a statistical-dynamical downscaling approach. If, for example, extremes in meteorological variables are to be determined in the urban area (e.g. temperature or wind speed or humidity or radiation) the relevant meteorological situation can be determined from statistics of coarse resolution data. This is, however, not easy with a target such as the extreme intensity of the urban heat island, which depends on temperature, wind speed, humidity and radiation together. Here the combination of the variables that determines the extreme intensity must be taken into account.

For different temperature related variables and for determining the situation that leads to an extreme intensity of the urban heat island, the presentation will show ways for a targeted selection of the meteorological situations that are to be simulated with high-resolution models.  

How to cite: Schlünzen, K. H.: Targeted data selection for different urban climate analyses, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-604, https://doi.org/10.5194/ems2025-604, 2025.

Seasons and their transitions play a critical role in shaping ecosystems and human activities, yet their traditional classifications—meteorological and astronomical—fail to capture the complexities of biosphere-atmosphere interactions. Conventional definitions often overlook the interplay between climate variables, biosphere processes (including human activities), and the actual anticipation of seasons, particularly in the context of global climate change, which has disrupted traditional seasonal patterns. As the climate becomes increasingly variable, the need to redefine how we observe and interpret seasonal change becomes more urgent—not only for ecological and scientific understanding but also for societal adaptation. Urban environments are increasingly recognized as dynamic interfaces where climatic variability, human activity, and biosphere responses converge—often in ways that diverge from traditional seasonal classifications. This study explores seasonal transitions through continuous micrometeorological measurements in three contrasting European cities: Novi Sad (Serbia), Thessaloniki (Greece), and Cardiff (UK), using data from the FAIRNESS micrometeorological platform (FMP2.0). Utilizing the normalized daily temperature range—a biologically grounded seasonality index previously validated in agricultural zones (Lalić et al., 2022; Lalić and Firanj Sremac, 2025)—we identify and characterize the onset, duration, and transition phases of seasons within urban microclimates. Our results reveal distinct spatial and temporal patterns, with clear seasonal offsets and variable transition durations across the cities, reflecting both geographic and anthropogenic influences. These findings not only challenge conventional meteorological and astronomical definitions but also highlight the urban-specific reshaping of seasonal cycles under climate change. The methodology provides scalable and perceptually aligned metrics for urban seasonality, with implications for urban planning, public health, market behaviour, and policy design. As climate variability intensifies, rethinking seasonality through the lens of city-based micrometeorological data becomes crucial for adaptive decision-making across diverse sectors.

Acknowledgements: This research is supported by the Ministry of Science, Technological Development and Innovation of the Republic of Serbia (Grants No. ‪451-03-137/2025-03/ 200125 & 451-03-136/2025-03/ 200125) and COST Action CA20108 FAIR Network of micrometeorological measurements (FAIRNESS).

How to cite: Lalic, B., Firanj Sremac, A., Savić, S., Sharmin, T., Lannon, S., Psistaki, K., and Paschalidou, A.: Framing Seasonal Changes at the Urban Microscale using FMP2.0 data, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-460, https://doi.org/10.5194/ems2025-460, 2025.

Cities contain a significant proportion of the global population. As they are subjected to unique vulnerabilities to climate-related phenomena, such as the Urban heat Island effect, it is crucial for ensuring the durable safety of city residents to understand urban microclimate. However, global and regional climate models operate at scales too coarse to capture the intricacies of these microclimates. Accurately modeling them requires resolving fine-scale details, including the shape and arrangement of buildings. Unfortunately, such high-resolution simulations come with a substantial computational cost, which limits their applicability, making real-time prediction and design optimization problems mainly inaccessible. Therefore, there is a need for computationally efficient models of urban microclimate.

The DANTE project aims to address this challenge by applying Model Order Reduction (MOR) techniques to lower the computational costs associated with high-resolution urban-scale simulations. MOR involves replacing full-order models - here, detailed Computational Fluid Dynamics (CFD) simulations - with reduced-order models of lower complexity. These models can be derived either by projection of the full-order model onto lower-dimensional manifolds, or through machine learning methodologies.

Regardless of the approach, these models must undergo a rigorous validation process before any application is possible to ensure that they accurately reproduce relevant physical properties. Furthermore, evaluating their performance and quantifying their uncertainties is essential to determine the reliability of their output for real world applications. This validation process requires urban-scale ground truth data, which is not directly available. Instead, lower-resolution data must be downscaled to urban scale. As a result, downscaling is a critical part of developing reliable urban microclimate models.

Traditional statistical downscaling methods rely on large datasets to establish mappings from low-resolution to high-resolution data, but in this context, data is scarce. One solution to this problem is Physics-Informed Neural Networks (PINN), which incorporate physical constraints into the learning process, thereby alleviating data requirements. By enforcing, through a choice of loss function, a set of physical partial differential equations, PINNs are able to more efficiently extract relevant information from the data. They can be used for prediction, but also as continuous function approximators for downscaling data. In this work, we propose a downscaling framework that leverages PINNs to assimilate both regional model data and weather station measurements, generating urban-scale data suitable for evaluating reduced-order models.

How to cite: Malhomme, N., Biondi, F., Tavazzi, P., Rooholamin, N., Spasov, G., and Stabile, G.: Downscaling using physics informed neural networks for model evaluation at urban scale, EMS Annual Meeting 2025, Ljubljana, Slovenia, 7–12 Sep 2025, EMS2025-43, https://doi.org/10.5194/ems2025-43, 2025.