Àngel Lozano, head of the Wireless & Secure Communications Group, holder of the Fractus-UPF Chair on 6G and Tech Transfer, and scientific director of the Maria de Maeztu Unit of Excellence in Information and Communication Technologies at UPF

Climate change is fuelling the frequency and intensity of wildfires, turning these natural phenomena into disasters of devastating proportions. In California, to cite just one region prone to wildfires, 2020 and 2021 were the worst and second-worst years on record in terms of acres burnt. This is an increasingly severe problem, and engineers are in a position to be part of the solution. Specifically, drone technology can play an important role in the fight against wildfires, and this role can be greatly enhanced by wireless communications and artificial intelligence.

In alignment with UPF’s Planetary Wellbeing initiative, and in the context of the Maria de Maeztu interdisciplinary research programme coordinated from the Department of Information and Communication Technologies, one project is tackling this challenge. I have the opportunity to lead this work, which is being conducted in collaboration with the University of California, Irvine. This university has a long track record of actions related to wildfire prevention and mitigation, as well as close ties with experts on wildfire modelling, fluid dynamics, and atmospheric science. Researchers from both UPF and the University of California are involved, with additional financial support provided by the Fractus-UPF Chair and the National Science Foundation.

An important milestone in the use of drones to combat fires was the 2019 Notre-Dame Cathedral accident. Drone footage contributed to many tactical decisions and helped stop that fire and reduce the damage. Since then, fire departments and agencies have started to make more extensive use of drones equipped with photographic and infrared cameras for different purposes, especially initial wildfire localization, surveillance during the fire-fighting operation, inspection of hard-to-reach sites, and monitoring of the fire perimeter and progression. The main advantage of drones is their flexibility and ease of deployment, especially under harsh conditions when pilot safety is a major concern, such as at night or when thick smoke makes it dangerous for manned aircraft. In addition, drones can play a key role in collecting the necessary data to develop dynamic models for predicting fire behaviour.

Currently, drones are mainly used individually, without being connected to each other to form a network. In most cases, they are operated manually, relaying information to a screen that is viewed by a human operator. Such manual drone operation is difficult, especially in the vicinity of a fire. Some of the challenges in using drones for wildfire monitoring include their short battery life and the ensuing limited flight time, as well as the small payload.

The growing use of drones in fire-fighting gives rise to a need for their automatic deployment and networked operation. Automating drone trajectories whilst communicating with the command-and-control centre and fire-fighters on the ground is an important challenge. These optimal trajectory and deployment algorithms need to consider complicated models for radio communication, interference, latency, drone energy consumption, obstacle and collision avoidance, and battery life. They also need to use prior information, such as the rough starting point of the fire or the location of inhabited areas and infrastructure. To confront this challenge of endowing the drones with collective intelligence, an artificial intelligence technique called reinforcement learning is being applied. The expected outcome of this research effort is a solution that automatically deploys a swarm of drones in a coordinated fashion, constantly re-optimizing their positions and arranging for their battery recharge in ordered turns, vastly improving their effectiveness.

The science and engineering developed under this project could be adapted to other applications beyond wildfires, including structural fires in urban and suburban settings, natural or man-made emergencies involving radiation, biological, or chemical leaks, or tracking atmospheric conditions surrounding imminent or ongoing extreme weather events.