Intellectual Property India Publishes Patent Application for 'An Intelligent System For Agricultural Risk Monitoring Using Machine Learning Techniques' Filed by Raju Egala; Sirisha Korrai; Dr. M. V. S. Sairam; Peluri Shasi Kumar; Jagannadha Venkata Karthik; Tatikonda Krishna Phaneendra; and Patchipala Lohit Kumar

MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641051827 A) filed by Raju Egala; Sirisha Korrai; Dr. M. V. S. Sairam; Peluri Shasi Kumar; Jagannadha Venkata Karthik; Tatikonda Krishna Phaneendra; and Patchipala Lohit Kumar, Visakhapatnam, Andhra Pradesh, on April 23, for 'an intelligent system for agricultural risk monitoring using machine learning techniques.'

Inventor(s) include Raju Egala; Sirisha Korrai; Dr. M. V. S. Sairam; Peluri Shasi Kumar; Jagannadha Venkata Karthik; Tatikonda Krishna Phaneendra; and Patchipala Lohit Kumar.

The application for the patent was published on May 1, under issue no. 18/2026.

According to the abstract released by the Intellectual Property India: "The present invention discloses a real-time ground monitoring system (RTGS) for agricultural risk assessment using artificial intelligence and ensemble learning techniques. The system comprises a multi-layered architecture including a data acquisition layer, processing layer, analytical layer, visualization layer, and output layer supported by a scalable infrastructure. The data acquisition layer is configured to collect heterogeneous data from meteorological sources, temporal-spatial streams, and distributed repositories. The processing layer performs data standardization, preprocessing, feature engineering, and quality assurance. The analytical layer employs ensemble machine learning models including Random Forest and Gradient Boosting, along with a risk assessment engine and statistical analysis modules to generate predictive outputs. The visualization layer provides an interactive multilingual dashboard with geospatial mapping and real-time monitoring capabilities. The output layer generates risk alerts, policy recommendations, and data export services. The system is configured to process large-scale streaming data and incorporates a feedback mechanism for continuous model improvement. Experimental evaluation on multi-district datasets demonstrates high prediction accuracy, enabling identification of vulnerable agricultural regions and supporting timely decision-making for improved agricultural sustainability and climate resilience."

Disclaimer: Curated by HT Syndication.