Thotakuri Rachana, G. Neeraja, Rekha Gangula, S. Mahanvitha, Kaluva Manasa, Kandula Nagaraju 03 04 The rapid increase in global wildfires driven by climate change demands a transition from reactive suppression to proactive intelligencebased detection systems Traditional wildfire monitoring methods such as human surveillance and satellite remote sensing often suffer from high latency high operational costs and limited temporal resolution A major challenge in current automated systems is the false alarm problem where modern Convolutional Neural Networks CNNs including You Only Look Once YOLO misclassify nonfire elements like sunsets industrial glare or redcolored objects as fire These inaccuracies lead to unnecessary emergency responses and increased alert fatigue among authorities To address these limitations this research proposes VLMFireNet a hybrid cascade architecture that combines the speed of edge computing with advanced contextual reasoning The system utilizes YOLOv8 for rapid initial detection at the edge achieving inference times below 50 milliseconds Detected instances are then validated using a Transformerbased VisionLanguage Model VLM which applies a global selfattention mechanism to analyze the broader scene context and eliminate false positives This dualcheck framework significantly enhances detection reliability The system is implemented using a multithreaded Python environment integrating a local Tkinterbased interface with a remote Telegram Bot API for realtime alert notifications The proposed approach improves detection accuracy while maintaining realtime performance By reducing false positives by approximately 20 VLMFireNet provides a scalable and costeffective solution for smart city and forest monitoring contributing to more efficient and reliable disaster management systems Copyright (c) Journal of Science Engineering Technology and Management Science. All rights reserved 2026