Intellectual Property India Publishes Patent Application for 'AI-Based Predictive Framework For Catalyst Selection And Reaction Efficiency Improvement In Biodiesel Production' Filed by Dr. Vustelamuri Padmavathi; Ms. Varddineni Saritha; Ms. Maria Martina; Mr. Senivarapu Ankit Reddy; Ms. Veguru Sai Hasini; Ms. C. Tarunanjali; and Ms. R. Sai Divya

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541124361 A) filed by Dr. Vustelamuri Padmavathi; Ms. Varddineni Saritha; Ms. Maria Martina; Mr. Senivarapu Ankit Reddy; Ms. Veguru Sai Hasini; Ms. C. Tarunanjali; and Ms. R. Sai Divya, Hyderabad, Telangana, on Dec. 9, 2025, for 'ai-based predictive framework for catalyst selection and reaction efficiency improvement in biodiesel production.'

Inventor(s) include Dr. Vustelamuri Padmavathi; Ms. Varddineni Saritha; Ms. Maria Martina; Mr. Senivarapu Ankit Reddy; Ms. Veguru Sai Hasini; Ms. C. Tarunanjali; and Ms. R. Sai Divya.

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 invention provides a development of the increasing global demand for sustainable energy calls for effective biodiesel production methodologies, in particular those that optimize catalyst selection and reaction performance. An AI-based predictive framework to enhance catalyst identification and improve reaction efficiency in transesterification processes. The proposed system incorporates machine learning models with reaction parameter data comprising temperature, molar ratio, catalyst concentration, and feedstock composition to forecast the type of catalysts and operating conditions. By considering both historical production datasets and real-time sensor inputs, this framework provides automated decision-making, minimum trial-and-error experimentations, and minimum production costs. Advanced machine learning algorithms are implemented on nonlinear interactions associated with the yield of biodiesel, including random forests, gradient boosting, and deep neural networks. Validations through experiments prove the significant enhancement in reaction conversion rates and energy efficiency. Thus, the recommended framework ensures a scalable and data-driven solution for a modern biodiesel industry seeking high-quality fuel production with reduced environmental impacts."

Disclaimer: Curated by HT Syndication.