MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122146 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'hybrid random forest and neural network system for geophysical log data prediction.'
Inventor(s) include Dr. Deepika J; Aaditya Kumar; and Kumar Divyachaitanya.
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 for predicting missing values in spatially correlated 5 geophysical well log data. The method receives geophysical well log data including caliper, gamma ray, neutron porosity, bulk density, and resistivity measurements recorded at different depths in a wellbore. The data undergoes preprocessing using K-Nearest Neighbors imputation to handle missing values while preserving spatial correlations. A Random Forest 10 model (FIG. 1) trains on the preprocessed data to determine feature importance scores for each geophysical parameter. The method selects the most important parameters based on these scores. An Artificial Neural Network model (FIG. 1) trains using the selected parameters as input features and compressional wave slowness as target variable. The trained model generates predictions for missing 15 compressional wave slowness values."
Disclaimer: Curated by HT Syndication.
