🧠
Ph.D. Research Scholar · VIT Vellore
Muhammad Murtaza Tantry
I build Physics-Informed Neural Networks (PINNs) that simulate boundary layer flow, bridging classical computational fluid dynamics with modern scientific machine learning.
MMT
Ph.D. · PINNs · CFD
- Scopus
- 59762028000
- ResearcherID
- PXX-8171-2026
- ORCID
- 0009-0005-5311-7725
01 — Profile
About
I am a full-time Ph.D. Research Scholar in the Department of Mathematics, School of Advanced Sciences at Vellore Institute of Technology (VIT), Vellore, working under the supervision of Dr. Padigepati Naveen.
My doctoral research develops Physics-Informed Neural Networks for simulating boundary layer fluid flow, and deep-learning frameworks that solve the governing nonlinear differential equations without relying solely on classical numerical schemes.
02 — Focus
Research Interests
🌊
Boundary Layer Flow
💧
Computational Fluid Dynamics
⚙️
Scientific Machine Learning
03 — Output
Research Publications
Journal Articles
-
2026Accepted
Adaptive loss balanced physics-informed neural networks for non-similar flow of Maxwell fluid: A deep learning framework
Journal of Thermal Analysis and Calorimetry, accepted for publication, 2026.
-
2026
Thomson and Troian slip condition for radiating second-grade nanofluid flow with shape effects of gold nanoparticles
Numerical Heat Transfer, Part A: Applications, vol. 87, no. 1, p. 2527403.
-
2025
Artificial neural network modelling for Casson hybrid nanofluid flow with entropy generation analysis
Multiscale and Multidisciplinary Modeling, Experiments and Design, vol. 8, no. 6, p. 288.
-
2025
Aggregation kinematics on gold nanoparticles in radiating viscoelastic second-grade fluid flow with Thomson and Troian velocity slip condition
Journal of Thermal Analysis and Calorimetry, vol. 150, no. 12, pp. 9279–9291.
Manuscripts Communicated
-
2026Under review
A Deep Learning Approach with PINNs for Simulating Second-Grade Hybrid Nanofluid Flow over a Radially Extending Sheet
Under review.
-
2026Submitted
Development of Physics-informed Neural Network Solver for Radiative Flow of Jeffrey Fluid with Thompson-Troian Slip Condition: A Deep Learning Approach
Submitted, 2026.
-
2026Submitted
Physics-informed Neural Networks Framework for Non-similar Solutions of Maxwell Fluid Flow over a Thin Needle: A Deep Learning Approach
Submitted, 2026.
04 — Background
Education
-
2023 — Present
Ph.D., Mathematics
Vellore Institute of Technology, Vellore
Thesis: Physics-Informed Neural Networks for Simulating Boundary Layer Flow of Viscoelastic Fluids.
Advisor: Dr. Padigepati Naveen. -
2018 — 2020
M.Sc., Mathematics
University of Hyderabad
-
2015 — 2018
B.Sc. (Hons.), Mathematics
Jamia Millia Islamia
05 — Toolkit
Skills
Programming
ML & Scientific Computing
High-Performance Computing
Languages
Miscellaneous
06 — Also
Honors, Talks & Training
🏅 Awards & Honors
- GATE Mathematics — All India Rank 115.
🎤 Talks & Presentations
- 2026 PhD Colloquium, Department of Mathematics, VIT Vellore — presented four research problems on Physics-Informed Neural Networks for viscoelastic boundary layer flows.
📚 Workshops & Training
- 2024 NCMW — Numerical Methods for Partial Differential Equations, Indian Institute of Petroleum and Energy (IIPE), Visakhapatnam.
- 2023 5-Day International Workshop on Recent Advances in Differential Equations and Applications (IWRADEA), VIT-AP University, Andhra Pradesh. 27–31 October 2023.
👤 References
-
Dr. Padigepati Naveen
Assistant Professor, Department of Mathematics,
School of Advanced Sciences, Vellore Institute of Technology, Vellore.
Let's collaborate
Open to discussions on Physics-Informed Neural Networks, viscoelastic flow modelling, and research collaborations.