MUMBAI, India, Aug. 24 -- Intellectual Property India has published a patent application (202621081497 A) filed by Symbiosis International Deemed University on July 01, 2026, for A Spatially Weighted Ensemble Learning Framework For Predicting Capacity Factors Of Global Power Plants.
Inventors include Nishit Bohra M; Avantika R. Patil; Omkar H. Thorve; Dr. Aniket K. Shahade; and Dr. Priyanka V. Deshmukh.
The application for the patent was published on August 21, 2026, under issue no. 34/2026.
Abstract: ABSTRACT A SPATIALLY WEIGHTED ENSEMBLE LEARNING FRAMEWORK FOR PREDICTING CAPACITY FACTORS OF GLOBAL POWER PLANTS The present invention discloses a spatially weighted ensemble learning framework (100) for predicting capacity factors of global power plants. The framework (100) integrates a spatial autocorrelation module (120) confirming geographic clustering, a base model training module (130) with random forest (132), gradient boosting (134), and ridge regression (136) models, a geographically weighted regression module (140) with sparse neighbor optimization (142) reducing computational complexity from quadratic to near-linear, and a spatially weighted ensemble module (150) combining predictions through location-adaptive weights. The framework captures spatial heterogeneity in power plant performance, achieving R-squared of 0.9344 surpassing fixed-weight approaches, supporting evidence-based energy infrastructure planning. [
Disclaimer: Curated by HT Syndication.
