MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202621080939 A) filed by Symbiosis International Deemed University on June 30, 2026, for Ai-Powered Air Quality Index Forecasting System Using Deep Learning.
Inventors include Bhoomika Kapde; Deepesh Srivastava; Saksham Sharma; Dr. Aniket K. Shahade; Dr. Priyanka V. Deshmukh; Dr. Shruti Patil; and Dr. Ketan Kotecha.
The application for the patent was published on August 21, 2026, under issue no. 34/2026.
Abstract: ABSTRACT AI-POWERED AIR QUALITY INDEX FORECASTING SYSTEM USING DEEP LEARNING The present invention discloses an AI-powered air quality index forecasting system (100) for predicting AQI across multiple cities using deep learning. The system (100) comprises a data acquisition and preprocessing module (110) with automated ingestion, forward-backward imputation, and feature engineering, a sequence encoding module (120) with 30-day temporal windowing and chronological partitioning, a model training module (130) with stacked LSTM network unit (132) of 64 and 32 units and parallel GRU network unit (134), an evaluation module (140) with regression and classification metrics across six CPCB severity categories, a multi-step forecasting module (150) with recursive seven-day prediction and severity mapping, and a dashboard deployment module (160) with Streamlit visualization. The LSTM achieves R-squared of 0.91 and classification accuracy of 88.7 percent across 26 Indian cities. [
Disclaimer: Curated by HT Syndication.
