Kiran Kumar Yalamanchi

Kiran Yalamanchi is an Associate Research Scientist at Argonne National Laboratory, where he develops artificial intelligence and machine learning methods for combustion, fuels, and high-performance energy systems. His work focuses on combining physics-based understanding with modern data-driven approaches to address challenges in modeling complex reacting flows and fuel design.

His research spans multimodal foundation models for multi-physics systems, generative models for inverse molecular design, and uncertainty-aware machine learning for predictive modeling. He has experience working with large-scale simulation and experimental datasets and developing scalable workflows on high-performance computing systems. His work has been carried out in collaboration with industrial and energy-sector partners, including applications in fuel optimization and performance-critical systems.

Research Summary

Yalamanchi’s research centers on building robust and scalable AI/ML frameworks for scientific discovery and engineering applications in energy systems. His work includes developing vision transformer-based foundation models for spatiotemporal prediction in fluid dynamics, as well as generative deep learning approaches for designing novel fuel molecules using molecular representations such as SMILES.

He also focuses on uncertainty quantification in machine learning models to improve reliability in scientific predictions, particularly for fuel property estimation. His broader contributions include creating high-quality datasets, designing feature representations for complex chemical systems, and validating models against experimental and high-fidelity simulation benchmarks.

Education

• Ph.D., Mechanical Engineering, King Abdullah University of Science and Technology (KAUST), 2022
• B.Tech (Honours) & M.Tech, Mechanical Engineering, Indian Institute of Technology Madras, 2017

Awards

• Outstanding Postdoctoral Performance Award (2025), Argonne National Laboratory
• Impact Argonne Award for Innovation (2024)
• Dean’s Award, KAUST Mechanical Engineering Program (2022)

Publications

• Available on schol​ar​.google​.com