Sim2Real-Fire: A Multi-Modal Simulation Dataset for Forecast and Backtracking of Real-World Forest Fire

Abstract

The latest research on wildfire forecast and backtracking has adopted AI models, which require a large amount of data from wildfire scenarios to capture fire spread patterns. This paper explores using cost-effective simulated wildfire scenarios to train AI models and apply them to the analysis of real-world wildfire. This solution requires AI models to minimize the Sim2Real gap, a brand-new topic in the fire spread analysis research community. To investigate the possibility of minimizing the Sim2Real gap, we collect the Sim2Real-Fire dataset that contains 1M simulated scenarios with multi-modal environmental information for training AI models. We prepare 1K real-world wildfire scenarios for testing the AI models. We also propose a deep transformer, S2R-FireTr, which excels in considering the multi-modal environmental information for forecasting and backtracking the wildfire. S2R-FireTr surpasses state-of-the-art methods in real-world wildfire scenarios.

Cite

Text

Li et al. "Sim2Real-Fire: A Multi-Modal Simulation Dataset for Forecast and Backtracking of Real-World Forest Fire." Neural Information Processing Systems, 2024. doi:10.52202/079017-0045

Markdown

[Li et al. "Sim2Real-Fire: A Multi-Modal Simulation Dataset for Forecast and Backtracking of Real-World Forest Fire." Neural Information Processing Systems, 2024.](https://mlanthology.org/neurips/2024/li2024neurips-sim2realfire/) doi:10.52202/079017-0045

BibTeX

@inproceedings{li2024neurips-sim2realfire,
  title     = {{Sim2Real-Fire: A Multi-Modal Simulation Dataset for Forecast and Backtracking of Real-World Forest Fire}},
  author    = {Li, Yanzhi and Li, Keqiu and Li, Guohui and Wang, Zumin and Ji, Changqing and Wang, Lubo and Zuo, Die and Guo, Qing and Zhang, Feng and Wang, Manyu and Lin, Di},
  booktitle = {Neural Information Processing Systems},
  year      = {2024},
  doi       = {10.52202/079017-0045},
  url       = {https://mlanthology.org/neurips/2024/li2024neurips-sim2realfire/}
}