FireCastNet: earth-as-a-graph for seasonal fire prediction
Dimitrios Michail, Charalampos Davalas, Konstantinos Chafis, Lefki-Ioanna Panagiotou, Ioannis Prapas, Nikolaos Ioannis Bountos, Spyros Kondylatos, Ioannis Papoutsis · 2025
Read FireCastNet: earth-as-a-graph for seasonal fire prediction by Dimitrios Michail, Charalampos Davalas, Konstantinos Chafis, Lefki-Ioanna Panagiotou, Ioannis Prapas, Nikolaos Ioannis Bountos, Spyros Kondylatos, Ioannis Papoutsis (2025) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-12783093.txt.
Description
Dimitrios Michail and co-authors forecast wildfires in a 2025 paper on seasonal prediction. As climate change worsens fire weather, seeing burned area months ahead aids planning. Their model, FireCastNet, treats Earth as a connected graph and pairs three-dimensional encoding with graph neural networks.
It trains on a global dataset blending climate, vegetation, and human factors, and predicts burned area up to six months out. Benchmarks against five leading models favor FireCastNet, with the strongest gains in fire-prone regions such as Africa, South America, and Southeast Asia. Longer input histories made forecasts sturdier, and local modeling sharpened regional detail. The authors argue that modeling Earth as one linked system is the key step.
Catalog record
| CREATOR | Dimitrios Michail, Charalampos Davalas, Konstantinos Chafis, Lefki-Ioanna Panagiotou, Ioannis Prapas, Nikolaos Ioannis Bountos, Spyros Kondylatos, Ioannis Papoutsis |
|---|---|
| YEAR | 2025 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 92 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |