MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202541129916 A) filed by Dr. V. Sujatha; Dr. G. Harish; P. Abishek; V. Giri; A. Arunraj; A. Ashwin Raj; M. Pushparaj; E. Rajesh; K. Archana; and L. Sripriya, Salem, Tamil Nadu, on Dec. 22, 2025, for 'real-time air quality hazard forecasting system using spatio-temporal graph attention networks.'
Inventor(s) include Dr. V. Sujatha; Dr. G. Harish; P. Abishek; V. Giri; A. Arunraj; A. Ashwin Raj; M. Pushparaj; E. Rajesh; K. Archana; and L. Sripriya.
The application for the patent was published on Feb. 27, under issue no. 09/2026.
According to the abstract released by the Intellectual Property India: "Air pollution has become a critical environmental and public health concern due to rapid urbanization, industrial growth, and vehicular emissions. Existing air quality monitoring systems primarily rely on static sensor data and conventional machine learning models, which often fail to capture complex spatial and temporal dependencies among pollutants, meteorological factors, and geographic regions. This limitation results in inaccurate forecasting of hazardous air quality conditions, thereby reducing the effectiveness of early warning systems. The present invention proposes a Real-Time Air Quality Hazard Forecasting System using Spatio-Temporal Graph Attention Networks (ST-GAT). The system integrates distributed air quality sensors, meteorological data sources, and advanced deep learning techniques to model spatial correlations between monitoring locations and temporal variations of pollutants. By representing sensor locations as graph nodes and dynamically learning attention weights among them, the proposed system accurately forecasts air quality hazards in real time. The invention enables early warnings, improved decision-making for environmental authorities, and enhanced public health protection."
Disclaimer: Curated by HT Syndication.
