Metraipolis › archive › dc_e8a26e158762
A Simulation-Grounded Agentic VLM Framework for Wildfire Monitoring and Reporting — arXiv:2610.02451
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.02451
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T09:06:38.563Z
- SHA-256 of the archived text
f69936d238ae895f8afcd6cbfac3c2ea898b2048948271018b9a3778fe519637- Stable URL of this page
https://metraipolis.com/documento/dc_e8a26e158762
How to cite
A Simulation-Grounded Agentic VLM Framework for Wildfire Monitoring and Reporting — arXiv:2610.02451 — arXiv (en), https://arxiv.org/abs/2610.02451 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e8a26e158762 (Metraipolis archive dc_e8a26e158762, sha256 f69936d238ae895f8afcd6cbfac3c2ea898b2048948271018b9a3778fe519637)
BibTeX
@misc{dce8a26e158762,
title = {A Simulation-Grounded Agentic VLM Framework for Wildfire Monitoring and Reporting — arXiv:2610.02451},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.02451},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e8a26e158762; sha256 f69936d238ae895f8afcd6cbfac3c2ea898b2048948271018b9a3778fe519637},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02451. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Effective wildfire monitoring requires relating visual evidence to physical fire dynamics, yet real videos with synchronized physical annotations are scarce and high-fidelity 3D simulation is costly. We present a simulation-grounded vision-language model (VLM) framework that automatically converts 2D wildfire simulations into labeled video episodes. A fixed Blender mapping produces low-detail 3D proxies aligned with simulator terrain, fuel layout, fire activity, and wind cues; controllable video generation supplies richer appearance. The proxies are intermediate representations rather than finely rendered final scenes. Generated videos and simulator labels form reusable multimodal memory for a training-free multi-agent VLM system that retrieves reference episodes, reconciles visual and memory-based predictions, and produces structured wildfire reports. On held-out generated episodes, video memory achieves 51.5% exact four-tag accuracy, compared with 22.6% for direct VLM querying and 16-17% for text-only memory; the complete system achieves 77.3% accuracy on six simulator-derived report fields. Component ablations, cross-generator tests, and three real-UAV evaluations assess retrieval, reporting, generator changes, and observable monitoring tasks. The framework connects automatic simulation-to-proxy conversion with memory-based VLM reasoning under scarce real-world physical annotations. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Graphics (cs.GR). Pagina del lavoro: https://arxiv.org/abs/2610.02451 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T08:21:44.143Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).