Intellectual Property India Publishes Patent Application for 'Stacking Ensemble Learning Framework For Landslide Susceptibility Mapping With Multidimensional Feature Collaboration And Pseudo-Labeling Validation' Filed by Amity University

MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541134705 A) filed by Amity University, Hyderabad, Telangana, on Dec. 31, 2025, for 'stacking ensemble learning framework for landslide susceptibility mapping with multidimensional feature collaboration and pseudo-labeling validation.'

Inventor(s) include Dr. Praveen Kumar Maduri; Vipin Kumar; and Diwakar Rai.

The application for the patent was published on Jan. 9, under issue no. 02/2026.

According to the abstract released by the Intellectual Property India: "The present invention provides a stacking ensemble learning framework for landslide susceptibility mapping that combines multidimensional feature collaboration with validated semi-supervised learning. As illustrated in FIGURE 1, the overall system (100) integrates parallel specialized base classifiers: one-dimensional branch (200) with Random Forest (206) and TabNet (208) optimize for statistical conditioning factor relationships, while three-dimensional branch (300) with LeNet-5 (306) and Vision Transformer (308) optimize for spatial terrain pattern learning. The invention addresses the complementarity gap between ensemble and deep learning methods, providing practical deployment suitable for geological surveys, disaster management, infrastructure assessment, and environmental hazard mapping."

Disclaimer: Curated by HT Syndication.