Data-Driven Fire Modeling: Learning First Arrival Times and Model Parameters with Neural Networks
This work addresses challenges in fire modeling for researchers, but it is incremental as it uses simulated data and focuses on specific parameters without broad real-world validation.
The paper tackled the problem of applying neural networks to fire science by using simulated data to map key fire spread parameters to first arrival times and solve the inverse problem, resulting in quantified error, dataset size requirements, and parameter sensitivity estimates.
Data-driven techniques are being increasingly applied to complement physics-based models in fire science. However, the lack of sufficiently large datasets continues to hinder the application of certain machine learning techniques. In this paper, we use simulated data to investigate the ability of neural networks to parameterize dynamics in fire science. In particular, we investigate neural networks that map five key parameters in fire spread to the first arrival time, and the corresponding inverse problem. By using simulated data, we are able to characterize the error, the required dataset size, and the convergence properties of these neural networks. For the inverse problem, we quantify the network's sensitivity in estimating each of the key parameters. The findings demonstrate the potential of machine learning in fire science, highlight the challenges associated with limited dataset sizes, and quantify the sensitivity of neural networks to estimate key parameters governing fire spread dynamics.