Publications
We reject: kings, presidents and voting. We believe in: rough consensus and running code. --David Clark, Internet Engineering Task Force
For a full list, check my Google Scholar
Peer-reviewed Journals (accepted/published/in-press/pre-prints)
Predicting clustered weather patterns: A test case for applications of convolutional neural networks to spatio-temporal climate data, Scientific Reports 2020 see paper
Analog Forecasting of Extreme-Causing Weather Patterns Using Deep Learning, Journal of Advances in Modeling Earth Systems. 2020 see paper
Media coverage: EOS , hpcwire , sciencedaily
Data-driven predictions of a multiscale Lorenz 96 chaotic system using machine-learning methods: reservoir computing, artificial neural network, and long short-term memory network, Nonlinear Processes in Geophysics, 2020, see paper
Data-driven super-parameterization using deep learning: Experimentation with multiscale Lorenz 96 systems and transfer learning, Journal of Advances in Modeling Earth Systems, 2020, see paper
Data-driven subgrid-scale modeling of forced Burgers turbulence using deep learning with generalization to higher Reynolds numbers via transfer learning, Physics of Fluids, 2021, see paper
Stable a posteriori LES of 2D turbulence using convolutional neural networks: Backscattering analysis and generalization to higher Re via transfer learning, Journal of Computational Physics, 2022, see paper
Learning physics-constrained subgrid-scale closures in the small-data regime for stable and accurate LES, Physica D: Nonlinear Phenomenon, 2022. see paper
Towards physics-inspired data-driven weather forecasting: integrating data assimilation with a deep spatial-transformer-based U-NET in a case study with ERA5, Geoscientific Model Development, 2022, see paper
Physics-informed machine learning: case studies for weather and climate modelling, Philosophical Transactions of the Royal Society A, 2021, see paper
Transfer learning of deep neural networks for predicting thermoacoustic instabilities in combustion systems, Energy and AI, 2021, see paper
Sensitivity of Viscosity on Molten Ti Infusion into a B4C-Packed Bed at the Microscale, Metallurgical and Materials Transactions B, 2018, see paper
Spline based shape prediction and analysis of uniformly rotating sessile and pendant droplets, Langmuir, 2018, see paper
Long-term stability and generalization of observationally-constrained stochastic data-driven models for geophysical turbulence, Environmental Data Science, 2022 see paper
FourCastNet: A global data-driven high-resolution weather model using adaptive Fourier neural operators, in revision, Nature Computational Science, 2022 see pre-print
Media coverage: NVIDIA GTC 2022, Keynote , NVIDIA
Closed-form discovery of structural errors in models of chaotic systems by integrating Bayesian sparse regression and data assimilation, Chaos: An interdisciplinary journal, 2022, see paper
Deep learning-enhanced ensemble-based data assimilation for high-dimensional nonlinear dynamical systems, Journal of Computational Physics, 2023, see paper
Media coverage: SIAM News
Explaining the physics of transfer learning a data-driven subgrid-scale closure to a different turbulent flow, Proceedings of the National Academy of Sciences Nexus, 2023, see paper
Media coverage: Rice News
Long-term (in-) stabilities in deep learning-based digital twins for the climate system: Cause and Solution, in review, Nature Computational Science
Recreating observed convection-generated gravity waves from weather radar observations via a neural network and a dynamical atmospheric model, in review, Journal of Advances in Modeling Earth Systems, pre-print
Peer-reviewed Conferences (accepted/published/in-press/pre-prints)
Computational Study of High Temperature Liquid Metal Infusion: Fluid Engineering Division Summer Meeting 2017 see paper
Data-driven surrogate models for climate modeling: application of echo state networks to the multi-scale Lorenz system as a test case: 36th International Conference on Machine Learning, CCAI workshop see paper
Identifying Clustered Weather Patterns Using a Deep Convolutional Neural Network: A Test Case: 8th International Workshop on Climate Informatics, Colorado, 2018, Boulder see proceedings
Leveraging Trilinos's Next Generation Computing Framework for an Exa-Scale Poro-Elastic Network Simulator Implementation: IEEE High Performance Extreme Computing 2016
Next Generation Exa-Scale Capable Multiphase Solver With Trilinos: ASME International Mechanical Engineering Congress and Exposition 2016, see paper
Spline Based Modeling of Two-dimensional droplets on Rough and Heterogeneous Surfaces: International Conference of Fluid Mechanics and Fluid Power, 2015. Also, a book chapter in Springer, Fluid Mechanics and Fluid Power: Contemporary Research (Book)
Deep spatial transformers for autoregressive data-driven forecasting of geophysical turbulence, International Conference on Climate Informatics, Oxford UK., 2020. Recommended as top 15% of accepted submissions. paper
A Framework to Integrate MFiX with Trilinos for High Fidelity Fluidized Bed Computations: IEEE High Performance Extreme Computing 2016 see paper