An IoT-Based Framework for Wildfire Detection Using Multi-Sensors Integration and CNN Image Classification

Wildfires are a growing threat to ecosystems, property, and human lives, especially in rural and forest-adjacent areas where monitoring infrastructure is limited. Traditional detection methods, such as satellite imaging and human surveillance, often suffer from delayed response and low precision during early fire stages. This study proposes a novel IoT-based wildfire detection framework that combines multi-sensor data with deep learning for rapid and localized fire identification. The system integrates smoke and flame sensors with a YOLOv4-based convolutional neural network (CNN) for image classification, all deployed on a Raspberry Pi 5 platform. A dual-layer detection mechanism enables immediate threshold-based alerts and visual confirmation via AI-driven analysis. Real-time notifications are delivered through a Telegram bot, while environmental data are logged and visualized using the ThingSpeak dashboard. The system, developed in Python, is optimized for deployment in low-resource environments. Experimental results demonstrate high detection accuracy and reliable performance across diverse conditions. This work demonstrates the practical potential of lightweight, AI-enhanced IoT systems for early wildfire detection and offers a scalable solution for remote monitoring. Future enhancements will explore more efficient CNN architectures and predictive analytics for proactive fire management.