MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122178 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'spatio-temporal variational autoencoder for urban growth prediction.'
Inventor(s) include Dr. Sunija. A. P; Mr. Harish K; Mr. Rahul Saxena; and Dr. Gayathri S.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a computer-implemented method (100) for predicting urban growth patterns. The method (100) includes acquiring (102) satellite imagery data from multiple time periods, extracting (104) building volume data from the satellite imagery data, calculating (106) Normalized Difference Vegetation Index and Normalized Difference Water Index spectral indices from the satellite imagery, processing (108) population density data, normalizing (110) the building volume data, spectral indices, and population density data to uniform spatial resolution, training (112) a spatio-temporal variational autoencoder with the normalized data as multi-modal inputs, generating (114) a latent representation of urban dynamics through the trained autoencoder, decoding (116) the latent representation to predict future urban growth patterns, and outputting (118) predicted maps for building volume, Normalized Difference Vegetation Index, Normalized Difference Water Index, and population density."
Disclaimer: Curated by HT Syndication.
