Spatiotemporal Wildfire Prediction and Reinforcement Learning for Helitack Suppression

TL;DR

FireCastRL is an AI framework that combines wildfire prediction with reinforcement learning-based suppression strategies, aiming to enable proactive wildfire management and resource optimization.

Contribution

The paper introduces a novel integrated AI system that combines deep spatiotemporal forecasting with reinforcement learning for real-time wildfire suppression tactics.

Findings

Accurate wildfire ignition prediction using deep spatiotemporal models.

Effective reinforcement learning-based suppression strategies in physics-informed simulations.

Public release of a large-scale wildfire-related environmental dataset.

Abstract

Wildfires are growing in frequency and intensity, devastating ecosystems and communities while causing billions of dollars in suppression costs and economic damage annually in the U.S. Traditional wildfire management is mostly reactive, addressing fires only after they are detected. We introduce \textit{FireCastRL}, a proactive artificial intelligence (AI) framework that combines wildfire forecasting with intelligent suppression strategies. Our framework first uses a deep spatiotemporal model to predict wildfire ignition. For high-risk predictions, we deploy a pre-trained reinforcement learning (RL) agent to execute real-time suppression tactics with helitack units inside a physics-informed 3D simulation. The framework generates a threat assessment report to help emergency responders optimize resource allocation and planning. In addition, we are publicly releasing a large-scale, spatiotemporal dataset containing $\mathbf{9.5}$ million samples of environmental variables for wildfire prediction. Our work demonstrates how deep learning and RL can be combined to support both forecasting and tactical wildfire response. More details can be found at https://sites.google.com/view/firecastrl.