fairfolio
Saved Projects

How Autonomous Drone Swarms Detect and Map Wildfires Faster

CSEF · 2026 Environmental Engineering (Track 2) (Senior Division)

Ilayda Koker

Overview

Wildfires are becoming increasingly frequent and devastating, threatening lives, ecosystems, and infrastructure across the globe. The 2025 Los Angeles fires alone caused an estimated $250–275 billion in damage and claimed dozens of lives — underscoring the urgent need for faster, safer, and more scalable wildfire detection and response technology. Traditional detection methods including satellite imagery, fixed watchtowers, and manned aircraft are too slow, too limited in coverage, and place human lives at risk. This project investigates whether an autonomous drone swarm can meaningfully improve the speed, coverage, accuracy, and reliability of wildfire detection and targeted suppression compared to a single drone operating alone. The central research question asks how increasing swarm size from one drone to multiple drones affects detection speed, field coverage time, localization accuracy, and suppression success in a simulated outdoor wildfire environment. It was hypothesized that as swarm size increases, each of these performance metrics would improve proportionally — because each additional drone reduces individual search area and enables simultaneous multi-point detection and parallel suppression response. To test this, a 100ft × 100ft outdoor field was used as the testing environment, with a fire simulation mat placed at known GPS coordinates to represent a wildfire hotspot. A custom Python RED color detection algorithm was developed and deployed on each drone to identify the simulated fire target in real time from the optical camera feed, automatically logging GPS coordinates and timestamp upon detection. Trials were conducted at two altitudes — 10ft and 20ft — under both clear and simulated smoke conditions using a fog machine, comparing single drone and two-drone swarm configurations across 64 total trials using a pre-programmed lawn mower waypoint pattern. Results demonstrated that the two-drone swarm outperformed the single drone in every metric tested. Detection speed improved by 35–37%, full field coverage was completed 44–45% faster, and suppression success rate improved from 62.5% to 87.5% under optimal conditions. Most critically, a single drone failed to detect the hotspot in 50% of trials at 20ft altitude under smoke conditions — the most representative proxy for real wildfire environments — while the swarm cut that miss rate to 25%. These findings establish autonomous drone swarm technology as a technically feasible and operationally valuable solution for early wildfire intervention, with significant potential to reduce firefighter risk, accelerate emergency response, and ultimately save lives.

Competition history

  • CSEF 2026 Environmental Engineering (Track 2) (Senior Division) · Entry S-12-14

Related projects

Closest projects by meaning, across every fair and year in the corpus.

Browse more like this

Source: California Science & Engineering Fair public projects

Save projects to your library

Sign in with Google to keep track of projects you find interesting, organized into folders. An account also raises your daily allowance for “Has this been done?”, and lets you create a key for the MCP server with a much higher limit than anonymous use. Browsing stays public.

Continue with Google