Umair
Hussain
Building AI, machine learning, and physics-based models for the energy industry. PhD in computational mechanics, day job in data science, and a soft spot for anything that lets me draw a mesh over the real world.
About
I am a Data Scientist at ChampionX, an SLB company, where I build AI, machine learning, and physics-based models for the oil & gas industry. My work sits at the intersection of data science and physics, focusing on 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 modelled the electrochemical response of Li-ion battery anodes using a coupled multiphysics framework, solving chemical diffusion under stress alongside electrochemical reactions.
Today, I bring that same rigor into industry. I enjoy problems where an engineering system has strong physics behind it but also messy real-world data, and where the right answer is rarely pure ML or pure simulation, but a thoughtful combination of both.
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 improved simulation performance by ~60% through MPI parallelization using PETSc.
Journey
-
2025 – PresentData ScientistChampionX, an SLB companyBuilding AI, ML, and physics-based models for the oil & gas industry. Working across artificial lift systems, equipment diagnostics, and corrosion prediction; integrating physics-informed modeling with modern ML and generative AI.
-
2024 – 2025Research Analyst, InternChampionX, an SLB companyFirst step into industry. Contributed physics-based and ML models for artificial lift systems, applying my FEM background to real-world downhole equipment.
-
2019 – 2025M.S. + Ph.D., Mechanical EngineeringIIT MadrasDoctoral research on multiphysics phase field modeling for Li-ion battery anodes. Built C++/deal.II solvers, published in Computational Materials Science and Journal of The Electrochemical Society, and contributed to the deal.II open-source code gallery.
-
2020Awarded Prime Minister Research Fellowship (PMRF)Government of IndiaReceived the prestigious PMRF fellowship supporting doctoral research (2020 – 2024).
-
2015 – 2019B.Tech, Mechanical EngineeringJamia Millia Islamia, New DelhiUndergraduate degree in Mechanical Engineering. First hands-on with computational tools, FEM, and design.
Work Experience
- Building AI, machine learning, and physics-based models across multiple oil & gas product lines, including artificial lift systems, corrosion prediction, and equipment diagnostics.
- Working on AI-on-Edge initiatives spanning anomaly detection, autonomous optimization, and generative AI (Small Language Models) for equipment diagnostics.
- Integrating physics-informed modeling (FEM, multiphysics) with modern ML/DL to deliver interpretable, high-fidelity models suitable for field deployment.
- Owning the end-to-end modeling workflow, from problem framing and data curation to SME-driven validation and hand-off for productionization.
- Contributed to a team-wide FEM modelling effort for sucker rod pumps, developing a novel deviated-well version of the model.
- Built a machine learning model to predict broken shafts from operational sensor data, supporting predictive maintenance.
- Multiphysics phase field modeling for Li-ion battery anodes using C++/deal.II with PETSc parallelization (~60% speed-up).
- Data-driven Gaussian Process Regression model mapping voltammogram features to microstructure grain size.
- Published 3 peer-reviewed journal articles and 1 conference proceeding; contributed a standalone solver to the deal.II code gallery.
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 stress on electrochemical response through voltammogram analysis, 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
Conferences
Gallery
Conferences
12 photos
PhD Convocation
2 photos
Life at IIT Madras
4 photos
Teaching Experience
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