Skip to main content
Go to the home page of the European Commission (opens in new window)
English en
CORDIS - EU research results
CORDIS

Digital Forest Twins for AI-based Wildfire Assessment

Project description

Fighting fires with digital twins

Wildfires are one of the most destructive natural disasters. Their unpredictable behaviour and complex physical dynamics make them incredibly challenging to manage. Traditional methods often fall short in keeping up with their fast-moving nature, creating a need for more effective solutions. Digital twins, which combine virtual models and real-world simulations, have emerged as a promising tool to address this issue. With this in mind, the ERC-funded WildfireTwins project aims to create detailed 3D models of ecosystems, coupled with physical simulations, to develop real-time wildfire simulations. These digital twins will enable better decision-making for firefighting services. By using photorealistic imagery and AI-driven tools, the project will offer innovative solutions for combating this global threat.

Objective

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.

Fields of science (EuroSciVoc)

Keywords

Programme(s)

Topic(s)

Funding Scheme

HORIZON-ERC - HORIZON ERC Grants

See all projects funded under this funding scheme

Call for proposal

(opens in new window) ERC-2024-COG

See all projects funded under this call

Host institution

CHRISTIAN-ALBRECHTS-UNIVERSITAET ZU KIEL
Net EU contribution
€ 1 986 200,00
Address
OLSHAUSENSTRASSE 40
24118 Kiel
Germany
Region
Schleswig-Holstein Schleswig-Holstein Kiel, Kreisfreie Stadt
Activity type
Higher or Secondary Education Establishments
Links
Total cost
€ 1 986 200,00

Beneficiaries (1)