Dr. Andrei Gasic is a Physics-AI Applications Engineer at Geminus AI, specializing in combining first-principles physics modeling with machine learning to solve complex industrial challenges. His work focuses on building scalable, physics-informed AI systems for real-world applications. Prior to Geminus, he worked as a Research Scientist at Qwell and an NSF Postdoctoral Fellow at Rice University. He holds a Ph.D. in Physics from the University of Houston and a B.S. in Physics from Emory University, with strong expertise in machine learning, scientific computing, and advanced AI frameworks.
In his session, Dr. Gasic will explore how physics-based AI is enabling industrial systems to move beyond traditional digital twins into real-time optimization engines. He will explain why many digital twin initiatives fail to deliver real-time value and how combining physics-based models with small-data AI approaches leads to faster and more accurate operational decisions. The session will also highlight how existing infrastructure can be transformed into continuously learning systems that improve production, reliability, and emissions performance - without requiring major hardware upgrades. He will further discuss the future of industrial operations, where systems evolve into autonomous optimization platforms balancing efficiency, safety, and sustainability in real time.
Key Topics:
- Limitations of traditional digital twins in real-time operations
- Combining physics-based models with AI for better optimization
- Transforming infrastructure into continuously learning systems
- Improving efficiency, reliability, and emissions performance
- Future of autonomous, real-time industrial optimization
For more on this conference or to access the session, reach out to us at info@ptnevents.com.
This content is copyrighted by PTN Events Private Limited. Any recording and posting of this content is strictly prohibited.
