Seminal
The magazine and atlas of EU-funded researchA new publication from the web and AI team at Scott Charnley

Atlas / Germany

European Research Council grant · Running

WildfireTwins Digital Forest Twins for AI-based Wildfire Assessment

Coordinator
Christian-Albrechts-Universitaet Zu Kiel, Germany
Runs
1 June 2025 to 31 May 2030
Status
Running
EU funding
€2.0m
Total cost
€2.0m
Partners
1 organisations in 1 countries
Type
European Research Council grant
Grant agreement
101170158

What the project is doing

In the project's own words, from its summary on CORDIS.

Wildfires have a devastating impact on the environment, infrastructure, animals, and human lives. The complex physical dynamics paired with their unpredictable development makes wildfires a dangerous natural phenomenon that is difficult to counteract. Recently, digital twins have emerged as a concept that combines geometric modeling, image synthesis, and physical simulation with broad applications in predicting real world processes.

This proposal aims to develop digital twins for wildfires – 3D models of ecosystems coupled with physical simulations – and to build AI-based tools for wildfire assessment. A wildfire twin with realistic physical simulations will have ground-breaking implications for firefighting services who will be able to use my framework as part of their decision making, resulting in an improved ability to combat wildfires, keep human lives safe and protect the environment.

In contrast to existing wildfire simulations, a novel digital twin will provide real-time simulations of wildfires and complex 3D representations of ecosystems. By relying on state-of-the-art computer graphics technology, a digital twin will support generating photorealistic images and videos of wildfires. Synthetically generated data with high visual fidelity will profoundly accelerate the development and adoption of AI-based solutions for managing wildfires, as it addresses the bottleneck of capturing and curating expensive real-world training datasets.

A digital twin that supports fast and accurate simulations of wildfires will have major impact on the analytical investigation conducted by the scientific community interested in understanding wildfires by accelerating the evaluation of hypotheses. Additionally, I plan to use the digital twin as a RobotGym – a virtual training environment for autonomous agents. A risk of this proposal is that a digital twin may not attain the required degree of realism – in which case it is still possible to identify options for higher quality.

Topics

Who is involved

OrganisationCityCountryRole
Christian-Albrechts-Universitaet Zu KielKielGermanyCoordinator

Source: CORDIS, European Commission. Data of 5 Nov 2026, reused under the Commission's reuse policy. View on CORDIS · Grant DOI