Talks

Conference talks
  1. Efficient high-dimensional variational data assimilation with machine-learned reduced-order models, R. Maulik, V. Rao, J. Wang, G. Mengaldo, E. Constantinescu, B. Lusch, P. Balaprakash, I. Foster, R. Kotamarthi, Bulletin of the American Physical Society, Division of Fluid Dynamics, 2022
  2. Application of Quantum Approximate Optimization to Reduced Order Modeling, K. Asztalos, R. Maulik, R. Steijl, Bulletin of the American Physical Society, Division of Fluid Dynamics, 2022
  3. Stabilized Neural Ordinary Differential Equations for Learning Chaotic Dynamical Systems, SIAM Mathematics of Data Science, San Diego, 28 September 2022.
  4. Quantifying Uncertainty in Deep Learning for Fluid Flow Reconstruction, Invited talk, USACM Thematic Conference on Uncertainty Quantification for Machine Learning Integrated Physics Modeling (UQ-MLIP), Crystal City, Virginia, August 18-19, 2022.
  5. Learning nonlinear dynamical systems from data using scientific machine learning, Invited talk, Argonne Training Program on Exascale Computing (ATPESC), August 12, 2022.
  6. Learning nonlinear dynamical systems from data using scientific machine learning, Invited Tutorial, 2022 AI + Science Summer School, University of Chicago, Data Sciences Institute, August 9, 2022.
  7. Non-intrusive reduced-order modeling using scientific machine learning, Invited talk, Summer School on Reduced Order Methods in CFD, SISSA Trieste, July 13, 2022
  8. Learning nonlinear dynamical systems from data using scientific machine learning, Invited talk, Accurate ROMs for Industrial Applications, Virginia Tech, July 8, 2022
  9. Simple, low-cost and accurate data-driven geophysical forecasting with learned kernels, Invited talk, SIAM UQ, Atlanta, 2022.
  10. Emulating nonlinear dynamical systems from data using scientific machine learning, Invited seminar, APS March Meetings, 2022.
  11. PyParSVD: A streaming, distributed and randomized singular-value-decomposition library, R. Maulik, G. Mengaldo, 7th International Workshop on Data Analysis and Reduction for Big Scientific Data (DRBSD-7), Supercomputing 2021, November 14, 2021.
  12. Parallelized emulator discovery and uncertainty quantification using DeepHyper, Invited talk, Machine Learning for Industry (ML4I) forum, Lawrence Livermore National Laboratory, August 10-12, 2021.
  13. Parallelized emulator discovery and uncertainty quantification using DeepHyper, Invited talk, Mechanistic Machine Learning and Digital Twins for Computational Science, Engineering & Technology, September 26-29, 2021.
  14. Non-intrusive projection-based surrogate models for rapid geophysical forecasting , R. Maulik, J. Wang, P. Balaprakash, E. Constantinescu, S. Collis, R. Kotamarthi, ASR/ARM PI Meeting Machine Learning Breakout, June 2021.
  15. Scalable scientific machine learning for computational fluid dynamics, (Plenary Talk), Computational Sciences and AI in Industry, June 7-9, 2021.
  16. Scalable Recurrent Neural Architecture Search for Geophysical Emulation, R. Maulik, Romain Egele, Bethany Lusch, Prasanna Balaprakash, SIAM-CSE, 2021.
  17. Surrogate modeling with learned kernels (Kernel Flows), Invited talk, Uncertainty Quantification in Climate Science, NASA JPL Climate Center Virtual Workshop, March 24, 2021.
  18. Unstructured fluid flow data recovery using machine learning and Voronoi diagrams, K. Fukami, R. Maulik, N. Ramachandra, K. Fukagata, K. Taira, Bulletin of the American Physical Society, Division of Fluid Dynamics, 2020
  19. Machine learning enablers for system optimization and design, R. Maulik, Second Symposium on Machine Learning and Dynamical Systems, Fields Institute, Toronto, Sept. 21-25, 2020
  20. Spatiotemporally dynamic implicit large eddy simulation using machine learning classifiers, R. Maulik, O. San, J. Jacob, June 15, AIAA Aviation Forum 2020, Reno NV.
  21. What Matters the Most for Individual Disaster Preparedness? Understanding Emergency Preparedness Using Machine Learning, SPSA Conference on Politics of Disasters, Resilience, and Recovery, J. Choi, S. Robinson, R. Maulik, W. Wehde, San Juan, Puerto Rico, 2020
  22. Machine learning of sequential data for non-intrusive reduced-order models, R. Maulik, A. Mohan, S. Madireddy, B. Lusch, P. Balaprakash, D. Livescu, Bulletin of the American Physical Society 72, 2019
  23. Data-driven deconvolution for the sub-grid modeling of large eddy simulations of two-dimensional turbulence, R.Maulik, O.San, A. Rasheed, P. Vedula, SIAM-CSE, 2019.
  24. Data-driven deconvolution for the large eddy simulation of Kraichnan turbulence, R. Maulik, O. San, A. Rasheed, P. Vedula, Bulletin of the American Physical Society, Division of Fluid Dynamics, 2018
  25. A computational investigation of the effect of ground clearance in vertical ducting systems, R. Maulik, O. San, C. Bach, Herrick Labs Conferences, Purdue University, 2018
  26. A neural network approach for the blind deconvolution of turbulent flows, R.Maulik, O.San, Bulletin of the American Physical Society, Division of Fluid Dynamics, 2017.
  27. A generalized wavelet based grid-adaptive and scale-selective implementation of WENO schemes for conservation laws, R. Maulik, R. Behera, O. San, Texas Applied Mathematics and Engineering Symposium, 2017.
  28. An explicit filtering framework based on Perona-Malik anisotropic diffusion for shock capturing and subgrid scale modeling of Burgers' turbulence, R. Maulik, O. San, Bulletin of the American Physical Society, Division of Fluid Dynamics, 2016.
  29. A dynamic hybrid subgrid-scale modeling framework for large eddy simulations, R. Maulik, O. San, Bulletin of the American Physical Society, Division of Fluid Dynamics, 2016.
  30. A dynamic framework for subgrid-scale parametrization of mesoscale eddies in geophysical flows, O.San, R. Maulik, Bulletin of the American Physical Society, Division of Fluid Dynamics, 2016
Seminar talks
  1. Accelerating scientific discovery using physics-informed machine learning, Invited talk, Machine Learning for e-Science, Swedish e-Science Research Centre, November 30, 2022.
  2. Stabilized Neural Ordinary Differential Equations for Long-Time Forecasting of Dynamical Systems, DataLearning group seminar series, Imperial College UK, November 1, 2022.
  3. Neural forecasting of high-dimensional dynamical systems, Invited talk, University of Pittsburgh Computational Mathematics Seminar, September 20, 2022.
  4. Learning nonlinear dynamical systems from data using scientific machine learning, Invited talk, Brown University CRUNCH Seminar Series, May 27, 2022.
  5. Reduced-order modeling of high-dimensional dynamical systems using scientific machine learning, Invited talk, IBiM Seminar Series, March 2022
  6. Reduced-order modeling of high-dimensional dynamical systems using scientific machine learning, Invited talk, National University of Singapore, Department of Mechanical Engineering Distinguished Seminar Series, February 10, 2022.
  7. Emulating complex systems from data using scientific machine learning, Invited talk, North Carolina State University, Department of Mathematics, February 1, 2022.
  8. Research at the intersection of mathematics, computation, and data, Invited Webinar, BIT Mesra Alumni Association North America, January 29, 2022.
  9. Reduced-order modeling of high-dimensional dynamical systems using scientific machine learning, Invited talk, University of Waterloo, Department of Applied Mathematics, January 18, 2022.
  10. Reduced-order modeling of high-dimensional dynamical systems using scientific machine learning, Invited talk, Florida State university, Department of Scientific Computing, November 19, 2021.
  11. Research at the intersection of mathematics, computation, and data, Physics and Engineering Speaker Series, North Park University, November 17, 2021.
  12. Reduced-order modeling of high-dimensional systems using machine learning, Civil and Environmental Engineering Seminar Series, Duke University, November 12, 2021.
  13. Reduced-order modeling of high-dimensional systems using machine learning, 2021 CBE Computing Seminar Series, University of Wisconsin-Madison, October 22, 2021.
  14. Modified neural ordinary differential equations for stable learning of chaotic dynamics, Applied Mathematics Seminar Series, Texas Tech University, September 1, 2021.
  15. Neural architecture search for surrogate modeling, Invited talk, DDPS Seminar Series, Lawrence Livermore National Laboratory, May 27, 2021.
  16. Surrogate modeling with learned kernels (Kernel Flows), Invited talk, Data Assimilation Seminar Series, CliMA group, Caltech, May 5, 2021.
  17. In-situ scientific machine learning for computational physics with OpenFOAM, Invited talk at Intel High Performance Computing, April 27, 2021.
  18. Incorporating inductive biases for the surrogate modeling of dynamical systems, Invited talk at Machine Learning for Dynamical Systems Special Interest Group, Alan Turing Institute, Imperial College London, April 14, 2021.
  19. Incorporating Inductive Biases as Hard Constraints for Scientific Machine Learning, MCS-LANS seminar, Argonne National Laboratory, February 17, 2021.
  20. Coupling simulation and machine learning: Tutorial at SDL Workshop, ALCF 2020, Argonne National Laboratory.
  21. Scalable scientific machine learning for computational fluid dynamics, Invited talk, Department of Mechanical Engineering, The City College of New York, October 1, 2020.
  22. Scalable scientific machine learning for computational fluid dynamics, Invited talk, Department of Mechanical Engineering, Rice University, September 9, 2020.
  23. Machine Learning Enablers for System Optimization and Design, MCS-LANS seminar, Argonne National Laboratory, August 19, 2020.
  24. Machine learning enablers for system optimization and design, SCIDAC-TDS invited talk, Los Alamos National Laboratory
  25. Autoencoders for science: Tutorial at ATPESC 2020, Argonne National Laboratory.
  26. Non-intrusive reduced-order model search for geophysical emulation, MAE259a: Data science for fluid dynamics (offered by Kunihiko Taira), University of California Los Angeles, June 3, 2020
  27. Machine learning for computational fluid dynamics, PyData Meetup Chicago, May 28, 2020. (Recording/Slides available)
  28. Recurrent neural architecture search for geophysical emulation using DeepHyper, R. Maulik, R. Egele, B. Lusch, P. Balaprakash, AI-HPC seminar, Argonne National Laboratory, April 17, 2020.
  29. Machine Learned Reduced-Order Models for Advective Partial Differential Equations, Stochastic & Multiscale Modeling and Computation Seminar, Illinois Institute of Technology, February 28, 2020.
  30. Machine Learned Reduced-Order Models for Advective Partial Differential Equations, MCS-LANS seminar, Argonne National Laboratory, February 26, 2020.
  31. Statistical methods for learning from data, AI4Science Workshop Tutorial, Argonne Leadership Computing Facility, 2019.
  32. Data-driven sub-grid models for the large-eddy simulation of turbulence, John Zink Hamworthy Combustion, Tulsa, 2019.
  33. Scalable deployments of generalizable turbulence closures using physics-informed machine learning, Argonne Leadership Computing Facility Seminar, 2019.
  34. Sub-grid model development for large eddy simulations using artificial neural networks, MCS-LANS Seminar, 2019.
Posters
  1. General purpose data science for general purpose CFD: Integrating Tensorflow into OpenFOAM at scale, R. Maulik, H. Sharma, S. Patel, B. Lusch, E. Jennings, Machine Learning for Transport Phenomena 2020, Dallas, TX.
  2. RANS acceleration using machine learning, R. Maulik, H. Sharma, S. Patel, B. Lusch, E. Jennings, Argonne National Laboratory Postdoctoral Symposium, 2019.
  3. Nonlinear physics inference using artificial neural networks, R. Maulik, E. Ozbenli, O. San, P. Vedula, Oklahoma State University High Performance Computing Conference, 2018
  4. Implicit LES Modeling of Stratified Shear Layer Turbulence, R. Maulik, O. San, Oklahoma State University High Performance Computing Conference, 2017
Plain Academic