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{176761,
        author = {Shreya Rao and Paavan Jaitly and Gautam Pataskar and Prathamesh Narute and Dr. D.S. Waghole},
        title = {Intelligent Avalanche Risk Mitigation: A Real-Time AI Framework for Autonomous Surveillance and Predictive Assistance},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {6296-6301},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176761},
        abstract = {This study details the practical implementation of AvAlert, an AI-driven avalanche forecasting and early warning platform designed for deployment in mountainous, high-risk regions. The system integrates a multi-stage machine learning pipeline: a VGG-ResNet hybrid network is utilized for extracting high-dimensional spatial features from satellite and environmental data, YOLOv8 performs real-time object detection to localize and track potential avalanche zones, and a composite ensemble model—combining Support Vector Machine (SVM), Random Forest, and XGBoost—delivers robust classification for early avalanche prediction. AvAlert ingests data from ground-based IoT sensors, including snow depth, temperature, and seismic activity, alongside satellite imagery, which is preprocessed and transmitted to the backend inference engine. Alerts are triggered based on configurable thresholds and disseminated through synchronized mobile and web platforms. Key system features include a real-time visual risk map, user-specific alert customization, and support for cloud-based scalability. The solution has been tested for accuracy, latency, and usability, demonstrating effective early detection and operational reliability. Future upgrades will emphasize enhanced IoT integration, edge processing, and geospatial model refinement. This implementation confirms the viability of intelligent systems for autonomous, real-time avalanche hazard mitigation and community-level resilience.},
        keywords = {Avalanche Forecasting, Real-Time Monitoring, AI-Based Early Warning System, VGG-ResNet, YOLOv8, Ensemble Learning, Random Forest, XGBoost, SVM, IoT Sensor Integration, Geospatial Hazard Detection, Disaster Risk Reduction, Autonomous Alert System, Cloud-Based Analytics, Edge Computing},
        month = {April},
        }