Sim2Real-Fire: A Multi-modal Simulation Dataset for Forecast and Backtracking of Real-world Forest Fire

Yanzhi Li, Keqiu Li, LI GUOHUI, zumin wang, Chanqing Ji, Lubo Wang, Die Zuo, Qing Guo, Feng Zhang, Manyu Wang, Di Lin

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 the use of 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 relatively brand-new topic in the research community of fire spread analysis. 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 network, S2R-FireTr, which excels in considering the multi-model environmental information for forecasting and backtracking the wildfire. S2R-FireTr surpasses state-of-the-art methods in the real-world scenarios of wildfire.