A Spatio-Temporal Neural Network Forecasting Approach for Emulation of Firefront Models
This provides a more efficient surrogate model for wildfire forecasting, addressing uncertainty quantification in computational simulations, though it is incremental as it applies neural networks to a specific domain problem.
The paper tackled the problem of computationally expensive wildfire spread simulations by proposing a spatio-temporal neural network framework for model emulation, achieving an average Jaccard score of 0.76 in approximating firefronts with robustness to small training sets.
Computational simulations of wildfire spread typically employ empirical rate-of-spread calculations under various conditions (such as terrain, fuel type, weather). Small perturbations in conditions can often lead to significant changes in fire spread (such as speed and direction), necessitating a computationally expensive large set of simulations to quantify uncertainty. Model emulation seeks alternative representations of physical models using machine learning, aiming to provide more efficient and/or simplified surrogate models. We propose a dedicated spatio-temporal neural network based framework for model emulation, able to capture the complex behaviour of fire spread models. The proposed approach can approximate forecasts at fine spatial and temporal resolutions that are often challenging for neural network based approaches. Furthermore, the proposed approach is robust even with small training sets, due to novel data augmentation methods. Empirical experiments show good agreement between simulated and emulated firefronts, with an average Jaccard score of 0.76.