MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202611065830 A) filed by Indian Institute Of Technology Roorkee on May 25, 2026, for System And Method For High-Resolution Spatial Downscaling Of Hydrological Data Using A Pixel-Wise Random Forest Scaler (pirfs).
Inventors include Sharma, Ravi; Silva, Karunakalage Anuradha Anushika; Daqiq, Mohammad Taqi; and Sharma, Mridul.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The present disclosure provides a system and method, termed the Pixel-wise Random Forest Scaler (PiRFS), for the spatial downscaling of coarse-resolution hydrological data to predict high-resolution Terrestrial Water Storage Anomalies (TWSA) and Groundwater storage Anomalies (GWSA). The PiRFS framework trains a predictive machine learning model on a pixel-by-pixel basis using co-located spatio-temporal datasets and reference TWSA measurements sharing a native first, coarse spatial resolution, thereby eliminating spatial resampling errors. The pixel-wise trained model isolates localized physical correlations and is subsequently applied to target hydrological datasets at a higher, second spatial resolution. This generates downscaled, physically consistent TWSA predictions without reliance on predefined basinal boundaries. Furthermore, the PiRFS system computes localized GWSA measurements from the downscaled TWSA. Ultimately, PiRFS provides a computationally efficient, scalable, and lightweight architecture for downscaling global data sets for precision local water resource management and groundwater monitoring.
Disclaimer: Curated by HT Syndication.
