A Novel AI-Powered Network of Sensors with Wireless Data Transmission for Real-Time Wildfire Detection

CSEF · 2023 Environmental Engineering Honorable_mention Award

Overview

Wildfires affect the lives of many California residents, costing counties billions of dollars in damages and impacting the health of those in the near proximity due to prolonged smoke inhalation. I aim to address the issue of wildfire detection as a means of alerting firefighting agencies and enabling early-stage fire suppression. I rely on the pre-existing framework of Wireless Sensing Networks (WSNs) and create a network of sensors equipped with the Raspberry Pi Zero. Unlike a standard microcontroller, the Raspberry Pi is able to run advanced Deep Learning and Convolutional Neural Network Models, creating a novel Intelligent Wireless Sensing Network (IWSN). I demonstrate that these models can detect smoke in images (AUC=0.88), with especially high performance for detecting larger regions of smoke (AUC=0.92). This novel IWSN architecture allows the most intensive computing to take place within the sensor nodes, reducing the amount of information that needs to be processed and sent between the nodes, enabling each node to cover at least 0.5 square kilometers through the use of cameras. The architecture solves the issue of long range wireless communication between the nodes. Each sensor node is equipped with a Raspberry Pi Zero computer, an HC-12 radio module, an MQ-135 air quality sensor, a camera, and a lithium battery. The total cost of each sensor node is $22.25 when manufactured individually, providing a cost-effective solution to the issue of effective and scalable fire detection.

Source coverage

This record comes from a published award list, not a complete project archive. Its abstract comes from CSEF's public project showcase as archived by the Internet Archive before judging (https://web.archive.org/web/20230401224130/https://ca-csef.zfairs.com/showcase/ShowcaseInfo?f=838e60b7-ea75-46e8-865c-fde4864244b3); the version presented may differ.

Awards (1)

  • Category Award: HM

Competition history

  • CSEF 2023 Environmental Engineering · Entry S1112

Resources

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