AI-Driven Real-Time Disaster Data Aggregation System for Enhanced NDRF Response

View at publisher Summarise with VIRAT
Authors: Natesan K., Lok Prasanth Kumar B, Harish N, Mekala N, Sasirekha SP, Shalini M
Cited by: 0
References: 6

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

India experiences frequent natural calamities such as floods, cyclones, and earthquakes that necessitate rapid response and accurate situational awareness. Traditional disaster management systems often suffer from delayed reporting and limited data sources, affecting the efficiency of response operations. This paper proposes an AI-driven, real-time disaster data aggregation system that leverages multi-modal data from social media platforms (X, Instagram) and news portals, in combination with official meteorological APIs, to enhance the responsiveness of the National Disaster Response Force (NDRF). The system employs advanced natural language processing (NLP) using Transformer models, image captioning via BLIP, and audio transcription through Whisper to analyze text, image, and video content. Critical information such as disaster type, severity, time, and location is extracted and validated using credibility scoring and cross-verification with authoritative sources like the India Meteorological Department (IMD). The processed data is visualized on a GIS-integrated dashboard built with Next.js and Leaflet, and automated alerts are issued to relevant authorities through SMS and email. Initial experiments demonstrate over 85% accuracy in misinformation detection and 3–5 second response latency. By integrating diverse AI models and real-time communication tools, the proposed system aims to significantly improve disaster awareness, minimize casualties, and optimize resource allocation.

Fields of Study & Subjects

Public Relations and Crisis Communication Energy and Environmental Systems Disaster Management and Resilience

Publication details

Journal / source
International Conference on Cognitive Systems and Computer Interaction (ICoSCI)
Pages
1–6
Publication date
15 January 2026
Language
EN