This paper presents a physics-guided machine learning (PGML) framework for fuel density prediction, integrating physics constraints and domain knowledge into deep learning models to enhance model accuracy and stability. We explore three deep learning architectures—ConvLSTM, Adaptive Fourier Neural Operator (AFNONet), and Video Vision Transformer (ViViT)—to model the spatiotemporal evolution of fuel density.
Our approach incorporates differentiable physics-informed terms in the loss function, including a mass-conserving fuel transport term and a rate-of-spread estimation. Experimental results demonstrate that the proposed PGML framework outperforms purely data-driven baselines without physics constraints in both accuracy and stability across multiple independent trials. This framework enables computationally efficient, physically plausible fire forecasting to support adaptive prescribed burn management.
Blogger's Review: The application of physics-guided deep learning models in fuel density prediction highlights the potential of integrating domain knowledge with machine learning. By incorporating physical constraints, the model's performance is significantly enhanced, providing an effective tool for future fire management and showcasing the immense value of interdisciplinary research.