Reinforcement Learning for Wildfire Mitigation in Simulated Disaster Environments

TL;DR

This paper introduces SimFire and SimHarness, a simulation and machine learning framework for developing and testing wildfire mitigation strategies in realistic disaster scenarios, aiding researchers and practitioners.

Contribution

The paper presents a novel simulation environment and an agent-based machine learning wrapper for wildfire mitigation, enabling automated strategy generation and assessment.

Findings

Realistic wildfire scenarios generated by SimFire

Automated land management strategies produced by SimHarness

Open-source tools available for research and practice

Abstract

Climate change has resulted in a year over year increase in adverse weather and weather conditions which contribute to increasingly severe fire seasons. Without effective mitigation, these fires pose a threat to life, property, ecology, cultural heritage, and critical infrastructure. To better prepare for and react to the increasing threat of wildfires, more accurate fire modelers and mitigation responses are necessary. In this paper, we introduce SimFire, a versatile wildland fire projection simulator designed to generate realistic wildfire scenarios, and SimHarness, a modular agent-based machine learning wrapper capable of automatically generating land management strategies within SimFire to reduce the overall damage to the area. Together, this publicly available system allows researchers and practitioners the ability to emulate and assess the effectiveness of firefighter interventions and formulate strategic plans that prioritize value preservation and resource allocation optimization. The repositories are available for download at https://github.com/mitrefireline.