Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{176757,
        author = {Shreya Rao and Paavan Jaitly and Gautam Pataskar and Prathamesh Narute and Dr. D.S. Waghole},
        title = {AI-BASED AVALANCHE ASSISTANCE AND SURVEILLANCE SYSTEM},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {6150-6154},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176757},
        abstract = {This study introduces AvAlert, an innovative AI-powered system for detecting avalanches and providing early warnings to reduce associated risks. The system integrates sophisticated machine learning techniques, including a VGG-ResNet hybrid for in-depth feature extraction, YOLOv8 for identifying hazardous zones in real-time, and a combined model of SVM, Random Forest, and XGBoost for precise early predictions. Notable features of AvAlert include real-time visualization of data, adjustable alert thresholds, and a user-friendly interface compatible with both mobile devices and web browsers. The system utilizes satellite imagery, data from ground sensors, and predictive modeling to deliver dependable and prompt alerts to communities at risk. Designed to support vulnerable populations in mountainous areas, AvAlert has plans for future enhancements, such as improved integration of IoT sensors and cloud-based data storage to increase scalability. This research underscores the vital importance of AI and real-time data processing in enhancing safety and resilience in avalanche-prone regions, pushing forward the potential for responsive and life-saving interventions in natural disaster management.},
        keywords = {Avalanche detection, Early warning system, AI-driven safety, Real-time monitoring, Feature extraction, VGG-ResNet, YOLOv8, Ensemble model, Hazardous zone marking.},
        month = {April},
        }