FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle
Mario Markov (1), Stefan Maria Ailuro (1), Luc Van Gool (1), Konrad Schindler (2), Danda Pani Paudel (1) ((1) INSAIT, Sofia University "St. Kliment Ohridski", (2) ETH Zurich)

TL;DR
FireScope introduces a reasoning-based framework and benchmark dataset for wildfire risk prediction that enhances generalization and interpretability across continents using multimodal data.
Contribution
It is the first to demonstrate language-based reasoning improves visual risk prediction and provides a cross-continental wildfire risk model with a new benchmark dataset.
Findings
FireScope achieves significant performance gains in cross-continental wildfire risk prediction.
Reasoning traces are faithful and semantically meaningful, confirmed by expert feedback.
The framework improves model generalization and interpretability in spatial risk modeling.
Abstract
Predicting wildfire risk is a reasoning-intensive spatial problem that requires the integration of visual, climatic, and geographic factors to infer continuous risk maps. Existing methods lack the causal reasoning and multimodal understanding required for reliable generalization. We introduce FireScope-Bench, a large-scale dataset and benchmark that couples Sentinel-2 imagery and climate data with expert-defined risk rasters across the USA, and real wildfire events in Europe for cross-continental evaluation. Building on this dataset, we propose FireScope, a VLM-based reasoning-to-generation framework that learns from both reinforcement learning and visual supervision to predict risk rasters with complementary reasoning traces. When trained in the USA and tested in Europe, FireScope achieves substantial performance gains, while expert feedback and automated analysis confirm that its…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
