Deep learning surrogate models of JULES-INFERNO for wildfire prediction on a global scale

TL;DR

This paper introduces deep learning surrogate models that significantly accelerate global wildfire predictions by approximating the JULES-INFERNO model, reducing computation time from hours to seconds with high accuracy.

Contribution

The work develops novel deep learning surrogates for JULES-INFERNO, enabling fast and accurate wildfire forecasting on a global scale, including a fine-tuning strategy for unseen scenarios.

Findings

Surrogate models predict wildfire area burnt with less than 0.3% error.

Models run in under 20 seconds for 30-year forecasts on a laptop.

High prediction accuracy with SSIM over 98%.

Abstract

Global wildfire models play a crucial role in anticipating and responding to changing wildfire regimes. JULES-INFERNO is a global vegetation and fire model simulating wildfire emissions and area burnt on a global scale. However, because of the high data dimensionality and system complexity, JULES-INFERNO's computational costs make it challenging to apply to fire risk forecasting with unseen initial conditions. Typically, running JULES-INFERNO for 30 years of prediction will take several hours on High Performance Computing (HPC) clusters. To tackle this bottleneck, two data-driven models are built in this work based on Deep Learning techniques to surrogate the JULES-INFERNO model and speed up global wildfire forecasting. More precisely, these machine learning models take global temperature, vegetation density, soil moisture and previous forecasts as inputs to predict the subsequent global area burnt on an iterative basis. Average Error per Pixel (AEP) and Structural Similarity Index Measure (SSIM) are used as metrics to evaluate the performance of the proposed surrogate models. A fine tuning strategy is also proposed in this work to improve the algorithm performance for unseen scenarios. Numerical results show a strong performance of the proposed models, in terms of both computational efficiency (less than 20 seconds for 30 years of prediction on a laptop CPU) and prediction accuracy (with AEP under 0.3\% and SSIM over 98\% compared to the outputs of JULES-INFERNO).