Romit Maulik

  • Research Assistant Professor


PhD. Mechanical & Aerospace Engineering, Oklahoma State University, 2019.
M.S. Mechanical & Aerospace Engineering, Oklahoma State University, 2015.
B.E. Mechanical Engineering, Birla Institute of Technology, India, 2012.

Research Interests

Scientific machine learning, high-performance computing, reduced-order modeling, numerical methods,
stochastic processes, fluid dynamics, geophysical sciences.


1. K. Fukami, R. Maulik, N. Ramachandra, K. Taira, K. Fukagata: Global field reconstruction from
sparse sensors with Voronoi tessellation-assisted deep learning, Nature Machine Intelligence, Accepted,

2. B. Hamzi, R. Maulik, H. Owhadi: Simple, low-cost, and accurate, data-driven geophysical forecast-
ing with learned kernels, Proceedings of the Royal Society A, 477: 20210326, 2021.

3. G. Mengaldo, R. Maulik, PySPOD: A Python package for Spectral Proper Orthogonal Decomposition
(SPOD), Journal of Open Source Software, 6 (60), 2862, 2021.
4. R. Maulik, B. Lusch, P. Balaprakash: Reduced-order modeling of advection-dominated systems
with recurrent neural networks and convolutional autoencoders , Physics of Fluids, 33, 037106, 2021
(Editor’s pick).

5. S. Pawar, R. Maulik: Distributed deep reinforcement learning for simulation control, Machine Learn-
ing: Science and Technology, 2, 025029, 2021.

6. S. Renganathan, R. Maulik, J. Ahuja: Enhanced data efficiency using deep neural networks and
Gaussian processes for aerodynamic design optimization, Aerospace Science and Technology, 111, 106522,

7. J. Burby, Q. Tang, R. Maulik: Fast neural Poincaré maps for toroidal magnetic fields, Plasma Physics
and Controlled Fusion, 63, 024001, 2021.

8. R. Maulik, T. Botsas, N. Ramachandra, M. Lachlan, I. Pan: Latent-space time evolution of non-
intrusive reduced-order models using Gaussian process emulation, Physica D: Nonlinear Phenomena, 132797, 2021.

9. R. Maulik, H. Sharma, S. Patel, B. Lusch, E. Jennings : A turbulent eddy-viscosity surrogate modeling framework for Reynolds-Averaged Navier-Stokes simulations, Computers and Fluids, 104777, 2020.

10. R. Maulik, K. Fukami, N. Ramachandra, K. Fukagata, K. Taira : Probabilistic neural networks for
fluid flow model-order reduction and data recovery, Physical Review Fluids, 5, 104401, 2020.

11. R. Maulik, P. Balaprakash, B. Lusch: Non-autoregressive time-series methods for stable parameteric
reduced-order models, Physics of Fluids, 32, 087115, 2020 (Editor’s pick).

12. R. Maulik, N. Garland, X. Tang, P. Balaprakash: Neural network representability of fully ionized
plasma fluid model closures, Physics of Plasmas, 27, 072106, 2020.

13. J. Choi, S. Robinson, R. Maulik, W. Wehde: What Matters the Most for Individual Disaster Preparedness? Understanding Emergency Preparedness Using Machine Learning, Natural Hazards, 103, 1183-1200, 2020.

14. S. Renganathan R. Maulik, V. Rao : Machine learning for nonintrusive model order reduction of the
parametric inviscid transonic flow past an airfoil, Physics of Fluids, 32, 047110, 2020.

15. R. Maulik, O. San: Numerical assessments of a parametric implicit large eddy simulation model,
Journal of Computational and Applied Mathematics, 112866, 2020.

16. R. Maulik, O. San, J. Jacob: Spatiotemporally dynamic implicit large eddy simulation using machine
learning classifiers, Physica D: Nonlinear Phenomena, 406, 132409, 2020.

17. R. Maulik, A. Mohan, B. Lusch, S. Madireddy, P. Balaprakash, D. Livescu: Time-series learning of
latent-space dynamics for reduced-order model closure, Physica D: Nonlinear Phenomena, 405, 132368,

18. Y. Hossain, R. Maulik, H. Park, M. Ahmed, C. Bach, O. San: Improvement of Unitary Equipment
and Heat Exchanger Testing Methods, ASHRAE Transactions, 125.2, 2019.

19. R. Maulik, O. San, J. Jacob, C. Crick: Online turbulence model classification for large eddy simula-
tion using deep learning, Journal of Fluid Mechanics, 870, 784-812, 2019.

20. O. San, R. Maulik, M. Ahmed: An artificial neural network framework for reduced order modeling
of transient flows, Communications in Nonlinear Science and Numerical Simulation, 77, 271-287, 2019.

21. R. Maulik, O. San, A. Rasheed, P. Vedula: Subgrid modeling for two-dimensional turbulence using
artificial neural networks, Journal of Fluid Mechanics, 858, 122-144, 2019.

22. R. Maulik, O. San, A. Rasheed, P. Vedula: Data-driven deconvolution for large eddy simulation of
Kraichnan turbulence, Physics of Fluids, 30, 125109, 2018.

23. O. San, R. Maulik: Stratified Kelvin-Helmholtz turbulence of compressible shear flows, Nonlinear
Processes in Geophysics, 25, 457–476, 2018.

24. O. San, R. Maulik: Extreme learning machine for reduced order modeling of turbulent geophysical
flows, Physical Review E, 97, 042322, 2018.

25. O. San, R. Maulik: Machine learning closures for model order reduction of thermal fluids, Applied
Mathematical Modelling, 60, 681-710, 2018.

26. R. Maulik, O. San, R. Behera : An adaptive multilevel wavelet framework for scale-selective WENO
reconstruction schemes, International Journal of Numerical Methods in Fluids, 87 (5), 239-269, 2018.

27. O. San, R. Maulik: Neural network closure models for nonlinear model order reduction, Advances
in Computational Mathematics, 44, 1717-1750, 2018.

28. R. Maulik, O. San: A dynamic closure modeling framework for large eddy simulation using approximate deconvolution: Burgers equation, Cogent Physics, 5, 1464368, 2018.

29. R. Maulik, O. San: A neural network approach for the blind deconvolution of turbulent flows,
Journal of Fluid Mechanics, 831, 151-181, 2017.

30. R. Maulik, O. San: A novel dynamic framework for subgrid-scale parametrization of mesoscale
eddies in quasigeostrophic turbulent flows, Computers and Mathematics with Applications, 74, 420-445,

31. R. Maulik, O. San: Explicit and implicit LES closures for Burgers turbulence, Journal of Computational
and Applied Mathematics, 327, 12-40, 2017.

32. R. Maulik, O. San: Resolution and energy dissipation characteristics of implicit LES and explicit
filtering models for compressible turbulence, Fluids, 2(2)-14, 2017.

33. R. Maulik, O. San: A dynamic subgrid-scale modeling framework for Boussinesq turbulence, International Journal of Heat and Mass Transfer, 108, 1656-1675, 2017.

34. R. Maulik, O. San: A dynamic framework for scale-aware parameterizations of eddy viscosity co-
efficient in two-dimensional turbulence, International Journal of Computational Fluid Dynamics, 31(2), 69-92, 2017.

35. R. Maulik, O. San: A stable and scale-aware dynamic modeling framework for subgrid-scale parameterizations of two-dimensional turbulence, Computers & Fluids 158, 11-38, 2016.

36. R. Maulik, O. San: Dynamic modeling of the horizontal eddy viscosity coefficient for quasigeostrophic
ocean circulation problems, Journal of Ocean Engineering and Science 1, 300-324, 2016.

37. H. H. Marbini, R. Maulik: A biphasic transversely isotropic poroviscoelastic model for the uncon-
fined compression of hydrated soft tissue, Journal of Biomechanical Engineering 138, 031003, 2016.