Umair
Hussain
Bridging the gap between physics-based simulation and data-driven AI — building intelligent solutions for complex engineering problems.
About
I am a Data Scientist at ChampionX (now part of SLB), developing AI and machine learning solutions for the oil & gas industry. My work sits at the intersection of data science and physics — building models that don't just fit data but respect the underlying physics of the systems they describe.
My technical foundation comes from a PhD at IIT Madras, where I specialized in computational mechanics, phase field modeling, and finite element methods. My doctoral research focused on modeling the electrochemical responses of Li-ion battery anodes using a coupled multiphysics framework — solving chemical diffusion under stress, coupled with electrochemical reactions.
I am proficient in the open-source C++ FEM library deal.II, and have contributed a standalone phase field solver to its code gallery. I also enhanced simulation performance by 60% through MPI parallelization using PETSc.
Research
Developed a coupled multiphysics framework using phase field modeling to simulate the electrochemical behavior of Li-ion battery anodes during (dis)charging. The model captures chemical diffusion under mechanical stress, coupled with electrochemical boundary conditions via Butler-Volmer kinetics.
- Demonstrated the impact of phase transformation, electrode size, and mechanical stresses on electrochemical responses using voltammograms — covering both elastic and elasto-plastic deformation regimes.
- Developed a generalized multi-phase field solver capable of handling multiple coexisting phases, including in-depth analysis of model parameters and their mapping to physical factors.
- Applied the multi-phase field framework to the peritectic solidification problem, demonstrating its versatility beyond battery systems.
- Implemented all solvers in deal.II (C++ FEM library) and contributed a standalone crystal growth solver to its public code gallery.
- Achieved 60% performance improvement via MPI parallelization using PETSc-based wrappers in deal.II.
Publications
Work Experience
- Developing AI and physics-based models for artificial lift systems including sucker rod pumps and ESPs.
- Working on corrosion prediction using machine learning for oil & gas applications.
- Developed a FEM model for the sucker rod pump to predict the dynamometer (pump) card.
- Built a machine learning pipeline to predict broken shaft events from sensor data.
Teaching Experience
Conference Presentations
Contact
Whether you're interested in research collaboration, discussing physics-informed AI, or exploring how computational mechanics meets data science — I'd love to hear from you.
Curriculum Vitae
Download my full CV for a detailed overview of my research, publications, and professional experience.
Download CV (PDF)Also reachable at me19d704@smail.iitm.ac.in