I'm a CFD Engineer and SciML researcher working at the crossroads of computational fluid dynamics and scientific machine learning. My work centers on making high-fidelity physics simulations faster, smarter, and scalable, through Physics-Informed Neural Networks, Neural Operators (FNO, DeepONet), Reduced Order Models, and Deep Learning frameworks.
Beyond surrogate modeling, my research interest extends into some of the sharper edges of the field, turbulence closure with data-driven models and operator learning for generalization across geometry and boundary conditions.
I'm actively looking to collaborate with research groups pushing the boundaries of SciML, computational physics, and AI-driven engineering, bringing both implementation depth and a genuine curiosity for open problems in the field.
MS Computational Science & Engineering
NUST, Islamabad
BS Mechanical Engineering
UET, Lahore
Ali, G., Khan, H., Tariq, B., Khalid, E., & Mushtaq, A.
5th International Conference on Digital Futures and Transformative Technologies (ICoDT2), Islamabad, Pakistan: IEEE Xplore.
Presents a CNN-based surrogate model that enables rapid and accurate prediction of flow fields around urban structures, achieving near real-time performance for architectural and urban planning applications.
BetaCodes
Computational Aeronautics Lab, SINES, NUST
Open to research collaborations at the frontier of computational physics and scientific machine learning.