Artificial Intelligence for Early Detection of Forest Fire Events
Carl Beierkuhnlein1, Christopher Shatto1, Wolfgang Dorner2, Tobias Heuser3, Karim Garri3, Peter Hofmann2, Pierre Ulfig4, Frank Weiser1, Peter Wolff5, Leonardos Leonardos5, Anke Jentsch5
1 Biogeography, University of Bayreuth
2 Technical University of Deggendorf
3 Urban Mobility Innovations [ui!]
4 Quantum Systems GmbH
5 Disturbance Ecology, University of Bayreuth
2 Technical University of Deggendorf
3 Urban Mobility Innovations [ui!]
4 Quantum Systems GmbH
5 Disturbance Ecology, University of Bayreuth
P 1.21 in Poster Session Thursday (15:15-16:00)
Forest fires contribute significantly to global CO2 emissions. They are responsible for about 5 to 10% of global CO2 emissions. Climate change is accelerating this contribution in different biomes, particularly in conifer forest ecosystems. Sensitivity, resilience and responses may differ between native and non-native needle-leaved forests.
In KIWA universities and companies cooperate in developing early warning systems for forest fires linking UAVs, satellite data, geoinformation, and knowledge on ecosystem dynamics and resilience with AI algorithms. KIWA exploits big data in real-time to support decision making in fire hazard control, civil protection, and nature conservation.
