Adaptive Swarm Coordination for Wildfire Control via Q-Learning Tuned PSO with Quantum-Inspired Coupling
CSEF · 2026 Computational Science (Senior Division)
Overview
Wildfire suppression is increasingly challenging due to the fast, unpredictable spread of fires and the limited availability of aerial resources. Coordinated drone swarms offer a promising solution by distributing sensing and firefighting tasks across multiple autonomous agents. This study evaluates three swarm strategies using a terminal based simulation: standard Particle Swarm Optimization (Vanilla PSO), Reinforcement Learning-tuned PSO (RL PSO), and Reinforcement Learning enhanced PSO with adaptive quantum inspired coupling (Quantum Coupled RL PSO). The simulation incorporates terrain, wind, fire spread, and resource constraints, while modeling drone limitations such as water capacity, refill times, and extinguishing actions. Performance metrics include extinguished number of fires, trees preserved, response time, and operational efficiency. Quantum Coupled RL PSO improved tree survival by ~12% over Vanilla PSO. Results indicate that Quantum Coupled RL PSO achieves the highest overall performance, improving fire suppression effectiveness and forest preservation compared to Vanilla PSO and RL PSO. RL PSO increases adaptability but at the cost of operational speed, while Vanilla PSO is fast but less effective in dynamic conditions. These findings demonstrate that integrating reinforcement learning with quantum inspired swarm coordination allows drone swarms to adapt to complex, changing environments, avoid suboptimal search patterns, and optimize resource allocation. The study highlights the potential of intelligent, adaptive swarms for improving autonomous wildfire monitoring and suppression.
Competition history
- CSEF 2026
Related projects
CSEF · 2026
How Autonomous Drone Swarms Detect and Map Wildfires Faster
CWSF · 2026
Phoenix: Wildfire Prevention using an Autonomous Bionic Morphing Ornithopter and AI Models
CSEF · 2023
Leveraging Genetic Algorithms and Mathematical Wildfire Propagation Models to Determine Optimal Firebreak Placement
ISEF · 2026
FireAIDSS: Real-Time and In-Situ Reconstruction of Wildfire Thermofluid Dynamics Through Physics-Constrained Inverse PDE Modeling
CWSF · 2026
Emergent Collective Intelligence in Swarm Robotics via Stigmergic Multi-Agent Reinforcement Learning
ISEF · 2021
FyreWatch: Deep Learning for Accurate Wildfire Environmental Conditions Detection
ISEF · 2022
It's Flaming Out: Using Artificial Intelligence To Emulate Critical Aspects of Wildfire Growth
CSEF · 2023
A Novel AI Pipeline for Predicting Next Day Wildfire Spread
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects