AI-Driven Wildfire Suppression System Leveraging IoT and Drone Technology

Patil, Anita Keshav (2024) AI-Driven Wildfire Suppression System Leveraging IoT and Drone Technology. In: Science and Technology - Recent Updates and Future Prospects Vol. 8. B P International, pp. 83-96. ISBN 978-81-976653-8-7

Full text not available from this repository.

Abstract

The wildfire is the most alarming threat to ecosystems, whether human-made or natural. Unfortunately, fires destroy many hectares of forest area each year due to late and ineffective fire detection. It is crucial to detect forest fires early to prevent them from spreading widely and harming the environment. Many research has been conducted in this field, but effective fire detection and reduction remain a challenge. The proposed system aims to address this challenge by developing a firefighting machine using advanced Artificial Intelligence (AI) and Internet of Things (IoT) technology. Currently, it is undergoing field trials. The primary objective of this machine is to generate artificial rain through drones equipped with sodium bicarbonate. This process aims to seed clouds and produce rain droplets to mitigate fire outbreaks. Data collection is automated, with information being captured and stored in a cloud-based system via the IoT. Images of both fire and normal conditions are collected and used to train AI models for wildfire detection. TensorFlow is utilized to support drone operations in this process. The IoT cloud platform, Thing Speak, is chosen for its efficiency and reliability in managing data modules. The stored data in the cloud is crucial for training AI models effectively, enabling accurate wildfire detection and timely response. The designed AI and IoT-enabled drones can accurately detect fires and deploy artificial rain to suppress them immediately.

Item Type: Book Section
Subjects: STM Digital Library > Multidisciplinary
Depositing User: Unnamed user with email support@stmdigitallib.com
Date Deposited: 15 Jul 2024 07:25
Last Modified: 15 Jul 2024 07:25
URI: http://archive.scholarstm.com/id/eprint/1794

Actions (login required)

View Item
View Item