Reinforcement Learning for Wildfire Mitigation in Simulated Disaster Environments
This work addresses wildfire mitigation for researchers and practitioners by providing a publicly available simulation system, though it is incremental as it builds on existing simulation and agent-based methods.
The authors tackled the problem of increasing wildfire severity by developing SimFire, a realistic wildfire simulator, and SimHarness, an agent-based machine learning wrapper that generates land management strategies to reduce damage.
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.