Search papers, labs, and topics across Lattice.
This study introduces a physics-guided machine learning framework for predicting fuel density, integrating physics constraints into deep learning models to improve accuracy and stability. By employing three architectures鈥擟onvLSTM, Adaptive Fourier Neural Operator (AFNONet), and Video Vision Transformer (ViViT)鈥攖he authors incorporate physics-informed loss terms, such as mass conservation and rate-of-spread estimation. Experimental results indicate that this PGML framework significantly outperforms traditional data-driven models, enhancing the reliability of fire forecasting for better management of prescribed burns.
Integrating physics into deep learning models can dramatically boost fuel density prediction accuracy and stability, outperforming conventional data-driven approaches.
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, averaged across multiple independent trials, demonstrate that the proposed PGML framework outperforms purely data-driven baselines without physics constraints in both accuracy and stability. This framework enables computationally efficient, physically plausible fire forecasting to support adaptive prescribed burn management.
