Extreme heat is increasingly recognized as one of the most severe climate-related risks affecting urban populations, with disproportionate impacts on public health, energy systems, and vulnerable communities. As heatwaves intensify under climate change, cities require near-real time, high-resolution and actionable information to support early warning systems, preparedness, and long-term adaptation. Addressing this challenge at urban-local scale demands not only methodological innovation, but also robust digital infrastructures capable of delivering consistent and interoperable climate intelligence across regions.

Destination Earth (DestinE), a strategic initiative of the European Union, represents a transformative step in this direction by providing global, high-resolution climate and weather simulations, through Digital Twins of the Earth System. By coupling advanced numerical models, Earth Observation (EO) data, and high-performance computing, DestinE establishes a common backbone for next-generation climate services. However, translating these powerful datasets into locally relevant, operational products for cities remains a critical challenge.

DE_395-Urban Heat Health Forecasting (UHHF) project addresses this gap by demonstrating how DestinE Extremes Digital-Twin outputs can be transformed into urban-scale user-oriented heat-health indicators through the operational use of Machine Learning (ML). The project applies ML-based downscaling techniques to near-surface air temperature (T2m) and relative humidity (RH) forecasts, enhancing spatial resolution from kilometre-scale to approximately 200 m. These downscaled fields are subsequently used to derive human-biometeorological indicators such as the Universal Thermal Climate Index (UTCI) and Thermal Stress Duration (TSD), supporting health-oriented risk assessment.

The UHHF framework integrates DestinE atmospheric drivers with EO-derived and geospatial predictors describing urban form, land cover, vegetation, and topography, including Local Climate Zones. Quality-controlled crowdsourced observations from citizen weather stations are combined with WMO reference data to constrain and validate the ML models, ensuring robustness under both average and extreme conditions. The approach is being implemented across four climatically and socio-environmentally diverse Functional Urban Areas, e.g. Naples, Chicago, Santiago, and Cape Town, enabling a systematic evaluation of models across continents.

By building directly on DestinE and complementary European programmes led by ECMWF, ESA, and Copernicus, drawing on both their data assets and operational services, UHHF aims to illustrate how these can be leveraged to develop affordable, scalable, and reproducible urban-scale climate information and services. The project highlights the strategic importance of climate data platforms in bridging the gap between global simulations and local decision-making, contributing to the development of interoperable urban climate and health services aligned with European and international resilience frameworks.

How to cite: Girão, I., Paixão, J., Castro, M., Miranda, V., Souza Silva, F., Siemen, S., Di Napoli, C., and Oliveira, A. P.: Urban Heat Health Forecasting with Destination Earth: Leveraging Digital Twins and Machine Learning for Scalable Urban Climate Services, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-19009, https://doi.org/10.5194/egusphere-egu26-19009, 2026.

Urban mobility and air quality are tightly coupled in cities: travel demand, network performance, and the spatial distribution of activities shape transport-related emissions and accessibility, and therefore underpin policy instruments such as low-emission zones, speed regulation, network reconfiguration, and land-use adjustments. Urban transport systems, however, operate within a broader set of constraints that extend beyond traffic and emissions management. Flooding and other water-related disruptions are a recurrent and increasingly relevant challenge for cities, with the potential to severely affect the transport network functionality. These challenges are often addressed through separate analytical tools, reflecting isolated approaches to mobility, environmental quality, and climate resilience topics. This fragmentation limits the ability of decision-support systems to effectively evaluate interventions across interrelated domains, motivating the need for modular and extensible services capable of integrating multiple processes within a single analytical framework.

CityNexus Pro, an Advanced Application Service (AAS) onboarded on Destination Earth, addresses this need through an operational and modular architecture designed to support integrated and cross-cutting scenarios analysis. The service builds on CityNexus, initially developed to support scenario-based assessment of mobility patterns, transport-related emissions, and air quality, and extends this baseline by incorporating an interoperable module for modelling mobility disruptions caused by flooding.

Within CityNexus Pro, urban mobility dynamics are represented by coupling data-driven origin–destination estimation with a traffic simulation engine, generating high-resolution spatio-temporal traffic flows. These flows are translated into emission estimates and linked to air quality models to quantitatively assess pollutant concentrations under alternative urban scenarios. Model assumptions, data sources, and parameterisations are explicitly documented to ensure transparency and reproducibility. Flood modelling outputs derived from hydrodynamic simulations based on the SFINCS model are mapped onto road network elements and incorporated into the mobility simulation chain, enabling dynamic modification of traffic conditions through configurable speed-reduction and road-closure thresholds.

The service, which already supports a range of policy-relevant scenarios—including low-emission zones implementation, speed limit changes, partial or full road inaccessibility, land-use reallocations, and shifts in mobility demand—is further complemented by compound scenario analysis in which flood hazards and mobility-related policy interventions are evaluated jointly. Users can configure flood scenarios by adjusting parameters such as precipitation timing and duration, river and sea discharge, and the presence of flood defences. In addition, CityNexus Pro is designed to integrate forecast products from the DestinE Digital Twin for Weather-Induced Extremes, enabling the impact assessment of extreme rainfall and flooding on mobility patterns and accessibility. 

CityNexus Pro is operational in Copenhagen, Seville, Bologna, and Aarhus, and is currently being deployed in Bucharest and Vitoria-Gasteiz. The service demonstrates how modular urban analytics on Destination Earth can be incrementally enhanced to address compound climate risks and support non-siloed, policy-relevant scenario analysis for urban resilience.

How to cite: Feliciotti, A., Lizama, A., Lemma, L., Ruess, A., Marconcini, M., Altenkirch, A., Stark, J., and Fratini, S.: Integrating Flood-Induced Mobility Disruption Modelling into CityNexus as a New Advanced Application Service on Destination Earth, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-19782, https://doi.org/10.5194/egusphere-egu26-19782, 2026.

Policy makers at local, national, and international levels are increasingly being required to make decisions that mitigate the effects of climate change on society and the economy. Earth Observations (EO) are already an important source of data to support such decisions, but this data represents only one aspect of the broader socio-technical systems that decision makers seek to influence. Policy effectiveness depends not only on environmental conditions, but also on household behaviour, technology adoption decisions, economic constraints, and feedbacks across scales. Capturing these dynamics requires modelling approaches that explicitly represent human decision-making alongside EO-derived inputs. This paper will present the results from the development of a scenario-planning digital twin (SPDT) designed to support decision-making processes related to local energy policies. The new SPDT will demonstrate how EO datasets can be integrated with multilevel agent-based models (MABMs) to enable specific scenarios to be used to support policy decisions.

The use case in this work enables policy makers to (i) model residential heating demand, (ii) test policy levers that might best encourage the uptake of low-carbon heating, and (iii) assess the implications for energy use and fuel poverty. Specifically, the MABM simulates hourly residential energy demand for space heating at the household level, accounting for building characteristics, policy levers, occupancy patterns, retail energy prices, and external ambient temperature. The MABM supports baseline demand estimation at fine spatial granularity (individual households), the assessment of new technologies (such as retrofit measures or heating controls/meters) and energy price variations, and counterfactual analysis (e.g., setpoint shifts, tariff changes, warm/cold snaps). Earth observation data is used to inform medium to long-term climate trends for the use case region. The project results presented in this paper have been developed to serve the city of Newcastle upon Tyne in the UK. We discuss results for Newcastle developed so far, and possible new future scenarios that could be developed using this type of methodology.

How to cite: Wagg, D. J., Malleson, N., Beltran, A., Tipuric, M., and Arribas-Bel, D.: Using Earth Observation Informed Agent-Based Models to build a Scenario Planning Digital Twin for Local Energy Policies, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-22325, https://doi.org/10.5194/egusphere-egu26-22325, 2026.

The AI4Clouds project develops a deep-learning-based enhanced short-term (up to 12 h) cloud fields for the Destination Earth (DestinE) Weather-Induced Extremes Digital Twin (Extremes DT). By fusing high-resolution Extremes DT simulations with EUMETSAT satellite observations (SEVIRI / FCI), the system learns to correct systematic model biases and provide enhanced cloud-related fields, such as cloud cover, optical depth, and top height fields, which are key variables for renewable-energy and weather applications.

AI4Clouds follows a multi-stage training strategy: it first pre-trains on ERA5 reanalysis data collocated with satellite datasets to capture large-scale dynamics, then fine-tunes on Extremes DT forecasts, also collocated with satellite datasets. It employs stretched-grid Graph Neural Network–Transformer architectures implemented within ECMWF’s Anemoi framework. Probabilistic forecasts are produced via an ensemble approach that quantifies aleatory and epistemic uncertainty. All data retrieval, preprocessing, training, and serving workflows are deployed on the DestinE Data Lake using its HDA, ISLET, and Stack services, ensuring reproducibility and operational integration through MLOps pipelines.

Validation relies on the open-source AQUA framework, extended with cloud-forecast and deep-learning diagnostics (e.g., RMSE, bias, CRPS, spectral metrics). An industrial partner from the solar-energy sector provides user-driven evaluation across several Iberian sites.

By integrating Earth-observation data, high-resolution numerical forecasts, and deep learning within DestinE’s infrastructure—a cloud-native environment—AI4Clouds demonstrates a scalable path toward building actionable applications for weather-sensitive sectors.

How to cite: Iglesias-Suarez, F., García, M., Heredia, I., Perez, A., Portilla, S., Sáinz-Pardo, J., and San-Martin Segura, D.: AI4Clouds: Enhancing Short-Term Cloud Fields in DestinE for the Solar-Energy Sector, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-10081, https://doi.org/10.5194/egusphere-egu26-10081, 2026.

Spring-time frost events pose a significant risk for the agricultural sector. Vineyards, apricots and other crops might be damaged by freezing temperatures after vegetation season onset. Frost events occur commonly during cold outbreaks in April or May after prolonged periods of relatively high air temperatures in late-winter or early-spring. The damage can be significantly reduced by suitable measures, provided a reliable forecast is available. As frost intensity is often highly spatially variable, its forecast can benefit from hectometric-scale numerical atmospheric modelling. We present results related to frost events detection and impact modelling within the Destination Earth On-Demand Extremes (DEODE) project. The detection scheme uses the ECMWF ensemble forecasts of 2-m air temperature and cloud cover to identify regions of potential high-impact frost events. The Global Digital Twin 2-m air temperature sums since the start of the year are used to delimitate areas where vegetation is not active yet. These areas are masked from the risk assessment. Finally, the frost damage risk is expressed in 0–5 scale and may serve as guidance for hectometric-scale simulation domains. After a hectometric simulation is completed, the output is ingested into a downstream frost impact model. The impact model estimates current development phase of several crops and corresponding temperature thresholds for frost damage. These thresholds are compared with hectometric-scale forecasted temperatures to obtain the magnitude of excess of critical temperature for each crop. The impact model has been evaluated during several pilot frost events in the Czech Republic and Spain.

How to cite: Matějka, M., Hájková, L., Možný, M., Musilová, A., and Vlach, V.: Frost event detection and impact modelling within the Destination Earth On-Demand Extremes framework    , EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-13552, https://doi.org/10.5194/egusphere-egu26-13552, 2026.

The  GET-it project (Geohazards Early Digital Twin Component) is devoted to build a Digital Twin for geohazards in the framework of the ESA Early Digital Twin Component (DTC) programme. The Geohazard Digital Twin is transitioning from a demonstration prototype to a shareable, pre-operational Earth Observation (EO)-based service platform. This transition has been initiated through the integration of the GET-it scenario modules within the Geohazards TEP (https://geohazards-tep.eu), a long-standing operational platform developed under ESA, and will continue through their future integration and federation with the Destination Earth (DestinE) framework. The project explores how EO data can effectively drive DTCs for volcanic and seismic geohazards within the Destination Earth framework.

The Geohazard DTC developed in GET-it is designed as a modular and customizable environment, capable of integrating multi-sensor EO data, primarily from the Copernicus programme, with established physical models and EO-driven analysis tools. The adoption of standardized input and output formats ensures interoperability and facilitates the uptake of DTC products by diverse user communities with different operational needs. These characteristics enable repeatable, timely EO-driven simulations and facilitate the integration of the Geohazard DTC into downstream pre-operational workflows.

The current prototype includes several scenario modules operating at increasing levels of EO data exploitation: GEOMOD, for modelling EO-derived geodetic signals; FALL3D, for volcanic ash and SO₂ dispersion constrained by EO observations; GPUFLOW, for lava flow modelling based on EO-derived effusion rates and topography; and DAMSAT, for EO-based change and damage detection. Together, these modules act as building blocks for pre-operational services, empowering stakeholders to explore realistic emergency scenarios and assess potential mitigation and adaptation strategies. 

A central aspect of GET-it is the systematic integration of stakeholder requirements into the DTC design. A structured engagement process, based on questionnaires and direct interactions, involved a broad range of public and private stakeholders, including civil protection authorities, aviation and transport stakeholders, infrastructure managers, insurance companies, energy providers, and decision-makers. All the scenario models were considered relevant, with FALL3D emerging as the most requested service. The collected feedback directly informed the definition of the scenario modules and the organization of a dedicated Demonstration Day, focused on the validation of EO-driven what-if scenarios.

The Geohazard DTC has been demonstrated through representative multi-hazard use cases, including the 2018 Mount Etna eruption, the 2021 La Palma eruption, and the 2016 Central Italy earthquake sequence. Based on these activities, a medium- to long-term roadmap is being defined, focusing on enhanced EO-driven simulations, advanced decision-support tools, interoperable visualization interfaces, scalable services, and extension to additional geohazards, in alignment with other DTC initiatives and community-building actions. This roadmap aims to consolidate the Geohazard DTC as a sustainable pre-operational platform, ready for future operational uptake.

How to cite: Ganci, G. and Stramondo, S. and the GET-IT team: Advancing the EO-based Geohazard Digital Twin from Prototype to Pre-operational Platform, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-17698, https://doi.org/10.5194/egusphere-egu26-17698, 2026.

Desert locusts are known as the world’s most destructive migratory pest. A single swarm can count 80 million locusts, traveling up to 150 km daily and consuming the same amount of food as 35.000 people per day. They are cause of major mid-to-long-term impacts on the economy, quality of life and the environment. Climate change is amplifying the occurrence of such pests: the increase of extreme events such as cyclones creates ideal conditions for locust breeding.

The Desert Locust Monitoring Service (DLMS) is the new system for preventing upsurges of desert locusts across Eastern Africa, Southwest Asia and northwest of India. It leverages the power of satellite observations, model outputs, in-situ measurements and advanced AI techniques to monitor the locust threat, help mitigate crop damage, and safeguard essential food supplies.

Onboarded on the Destination Earth (DestinE) platform, the service consists of two layers: the Early-Stage Locust Appearance and the Locust Swarm Migration. The first layer relies on a customized Maxent model, a statistical approach widely used in species distribution modeling (SDM): it allows identifying areas with favorable environmental conditions for desert locust breeding. There are two available modes: the Safe Mode makes use of 50 days of climate data from ERA5-Land (soil water content, precipitation, and temperature) and normalized difference vegetation index (NDVI) from Sentinel-3 to generate daily probability forecasts; the Experimental Mode extends forecasts to two days thanks to the advanced projections of DestinE’s Weather Extremes Digital Twin. The variables used are: skin temperature, total precipitation and runoff.
The second layer forecasts adult locust swarm migration under biological and climatic conditions, accounting for their rapid and unpredictable long-distance movements. It takes as primary input the Early-Stage layer output, which provides initial location predictions under specific environmental conditions. Environmental variables, including the Leaf Area Index (LAI) from Copernicus, as well as wind velocity components and temperature from DestinE’s Climate Change Adaptation Digital Twin, inform the model of conditions that may trigger migration events. Swarm behavior is then represented using a stochastic model, which simulates an environment-biased random movement on a 2D lattice, generating batches of diverse potential scenarios. In this framework, locusts move based on environmental cues, including climate conditions and the availability of resources, such as vegetation. Finally, the model performs a statistical analysis across all generated scenarios to produce output maps estimating future locations of adult locusts and the size of their swarms.
Both Maxent and stochastic models were trained using a presence-only dataset provided by FAO’s Locust Watch. Prediction results have been validated with FAO data on desert locust activity and independent data provided by the International Center of Insect Physiology and Ecology (ICIPE).

Enabled by Destination Earth’s cutting-edge modeling and data infrastructure, the DLMS offers high-quality insights to anticipate risks, mitigate impacts and support the protection of crops, communities, and ecosystems in the most affected regions. Forecasting maps are available to all DestinE registered users, with some features reserved to users with upgraded access.

How to cite: Outmani, S., Grassi, A., Azami, W., Bellotto, K., and Houël, M.: The Desert Locust Monitoring Service: a new Destination Earth service for Environmental Pest prediction, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-22287, https://doi.org/10.5194/egusphere-egu26-22287, 2026.

Operating in the polar regions is growing increasingly important due to expanding research needs, emerging economic opportunities and efforts to protect national sovereignty.

Ships operating in the Arctic and Antarctic face heightened risks and more severe consequences in the event of an accident due to sea ice, icebergs, harsh sea states, low visibility and extreme temperatures. These hazards are compounded by sparse infrastructures and remoteness, with immediate assistances not readily available during emergencies.

While climate change is quickly reducing the amount of sea ice, this does not necessarily translate to a reduction in risk in the short-term. On the contrary, uncertainly due to changing sea ice conditions, and an increase in icebergs due to melting glaciers, can increase risk.

The operational sea ice community provides information to lessen risk to life, property and the environment and to improve operational efficiency. That information is used by ships to avoid or navigate through sea ice, by ship operators in planning polar voyages, and by policy makers to assess the impact of climate change on future decisions regarding polar operations. Beyond safety, these services also increase operational efficiency by enabling optimized routing, reduced fuel consumption, and shorter transit times.

The information provided by the operational sea ice community comes from in-situ measurements, satellite earth observation data, and sophisticated models of the atmosphere, oceans, sea ice, and icebergs. These data streams have historically been assembled and interpreted by highly trained human analysts. Given the rapid increase in the amount of data that needs to be analyzed and the constraints on workforces due to government fiscal reductions, their work is increasingly being assisted by artificial intelligence. Furthermore, because sea ice is highly dynamic and can change within a matter of hours, automation and AI are indispensable for providing real-time and forecast information.

The operational sea ice workflows have many of the attributes of an Earth System Digital Twin:

• Utilization of detailed digital models of relevant earth systems (atmosphere, ocean, sea ice),
• Continuous incorporation of near-real-time data from in-situ sensors and earth observation satellites,
• Use of artificial intelligence and machine learning,
• Generation of predictive models and forecasts, and
• Provision of advance analytics and decision support tools to allow end-users to optimize their choices.

In fact, much of the information both used and generated by the operational sea ice community is available in Destination Earth, the initiative of the European Commission to develop a digital twin of the Earth.

This presentation will examine the provision of operational sea ice information as an example of the application of digital twins to provide actionable insights on climate adaptation and disaster risk reduction. It will present current capabilities, AI-enabled workflows, and lessons learned from operational implementation, with a focus on supporting safe and sustainable polar shipping.

How to cite: Arthurs, D., Rabenstein, L., Dolezalova, T., Puestow, T., Rasmussen, T., and Korosov, A.: Operational Sea Ice Information as a Digital Twin, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-14321, https://doi.org/10.5194/egusphere-egu26-14321, 2026.

The Global Fish Tracking System (GFTS) and Pangeo-Fish integrate biologging data with high-resolution environmental data in a digital-twin framework to address key challenges in marine conservation and fisheries management. Linking fish movement models with climate projections from Europe’s Destination Earth (DestinE) Climate Change Adaptation digital twin yields an evidence-based tool for decision support in habitat conservation and fisheries management under climate change. The implementation is built on the open-source Pangeo ecosystem and deployed on the DestinE platform.

Pangeo-Fish is an open-source package that ingests multiple biologging data types—including archival tags, pop-up satellite archival tags (PSATs), and acoustic telemetry detections. It processes time series observed by fish (e.g., depth, temperature, and light) together with geolocation constraints derived from external sources such as acoustic receiver networks and tag-based positioning. These heterogeneous observations are harmonised in a cloud-native workflow to support scalable track reconstruction and downstream habitat-relevant products.

Tracks are reconstructed using a Hidden Markov Model (HMM) geolocation approach that combines tag-recorded time series (e.g., depth, temperature, and light) with external geolocation constraints (e.g., acoustic detections), together with priors such as bathymetry and release/recapture information. Processing leverages cloud-native tools (Jupyter, Dask, Xarray) and chunked cloud-optimised storage (Zarr) for scalable analysis. A key design choice is the use of HEALPix as the base spatial grid and indexing scheme from ingestion to visualisation, enabling efficient path-likelihood evaluation on an equal-area, iso-latitude grid while avoiding distortive resampling. Environmental reference fields are primarily sourced from the Copernicus Marine Service, but the workflow can also ingest user-defined datasets. In addition, in situ observations (e.g., Argo float temperature) can be incorporated to represent uncertainty in the ocean physics fields used by the geolocation model and better account for model–data discrepancies.

The Pangeo-Fish workflow yields most-probable tracks and daily presence-probability maps, while GFTS supports aggregation of distributions for management-relevant analyses. GFTS intersects these outputs with climate projections from the DestinE Climate Change Adaptation Digital Twin to assess potential habitat exposure under climate change. GFTS has so far been demonstrated for Atlantic applications, while Pangeo-Fish has been extended to the Pacific Ocean, enabled by portable cloud-native processing and the availability of cloud-accessible datasets. As an early DestinE platform use case, this work illustrates how Earth system digital twins can be operationalised for reproducible, scalable biologging analytics to inform marine conservation and sustainable fisheries management.

How to cite: Odaka, T. E., Cap, E., Mazouni, Q., Hue, C., Delouis, J.-M., Woillez, M., Fouilloux, A., Ragan-Kelley, B., and Wiesmann, D.: Pangeo-Fish and the Global Fish Tracking System: Scaling Biologging Analytics with Earth System Digital Twins for evidence-based policy support, EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-19040, https://doi.org/10.5194/egusphere-egu26-19040, 2026.

Mountain glaciers are critical elements of the Earth’s hydrological and climate systems. The rapid changes in glaciers due to climate change hinder our ability to monitor and address associated risks effectively. To address these challenges, we present the Digital Twin Component for Glaciers (DTC Glaciers), part of ESA’s Digital Twin Earth (DTE) programme. In this presentation, we will demonstrate the early prototype of the DTC Glaciers system, developed through close co-design with our stakeholders in the hydropower and water sectors. The demonstration will highlight current capabilities, including regional glacier mass-balance assessment, runoff estimation, and user-informed scenarios. We will also share key lessons learned from Phase 1, focussing on data assimilation of heterogeneous datasets, the practicalities of building adaptive architectures, and the challenges of meeting diverse user needs within a unified framework. Despite these challenges, DTC Glaciers offers a well defined test case to assess the transformative potential of digital twins in climate risk assessments.

How to cite: Maussion, F., Bizon, J., Gampierakis, N., Gourmelen, N., Jakob, L., Michael, C., Nagler, T., Nussbaumer, S., Schmitt, P., Schwaizer, G., and Zemp, M.: Lessons learned from the pilot phase of the Digital Twin Component for Glaciers project (DTC Glaciers), EGU General Assembly 2026, Vienna, Austria, 3–8 May 2026, EGU26-8395, https://doi.org/10.5194/egusphere-egu26-8395, 2026.