Research

My group builds machine learning methods that respect the laws of physics. Current work is on the home page; below are write-ups of earlier projects, each with code.

Hidden Fluid MechanicsA Navier-Stokes Informed Deep Learning Framework for Assimilating Flow Visualization DataWe present hidden fluid mechanics (HFM), a physics informed deep learning framework capable of encoding an important class of physical laws governing fluid motions, namely the Navier-Stokes equations. In particular, we seek to leverage the underlying conservation laws (i.e., for...
Deep Hidden Physics ModelsDeep Learning of Nonlinear Partial Differential EquationsA long-standing problem at the interface of artificial intelligence and applied mathematics is to devise an algorithm capable of achieving human level or even superhuman proficiency in transforming observed data into predictive mathematical models of the physical world. In the...
Physics Informed Deep LearningData-driven Solutions and Discovery of Nonlinear Partial Differential EquationsWe introduce physics informed neural networks -- neural networks that are trained to solve supervised learning tasks while respecting any given laws of physics described by general nonlinear partial differential equations. We present our developments in the context of solving...
Hidden Physics ModelsMachine Learning of Nonlinear Partial Differential EquationsWe introduce Hidden Physics Models, which are essentially data-efficient learning machines capable of leveraging the underlying laws of physics, expressed by time dependent and nonlinear partial differential equations, to extract patterns from high-dimensional data generated from experiments. The proposed methodology...
Numerical Gaussian ProcessesData-driven Solutions of Time-dependent and Non-linear Partial Differential EquationsWe introduce the concept of Numerical Gaussian Processes, which we define as Gaussian Processes with covariance functions resulting from temporal discretization of time-dependent partial differential equations. Numerical Gaussian processes, by construction, are designed to deal with cases where (1) all...
Multi-fidelity ModelingDesign Optimization of an Ultrafast Marine VehicleMulti-fidelity modeling enables the seamless fusion of information from a collection of heterogeneous sources of variable accuracy and cost (e.g., noisy experimental data, computer simulations, empirical models, etc.). By learning to exploit the cross-correlation structure between these sources, one can...
Parametric Gaussian Process Regression for Big DataModern datasets are rapidly growing in size and complexity, and there is a pressing need to develop new statistical methods and machine learning techniques to harness this wealth of data. This work presents a novel regression framework for encoding massive...
Conic EconomicsConic Economics is an attempt to model modern general equilibria under uncertainty based on the recognition that all risks cannot be eliminated, perfect hedging is not possible, and some risk exposures must be tolerated. Therefore, we need to define the...
Multistep Neural NetworksData-driven Discovery of Nonlinear Dynamical SystemsIn this work, we put forth a machine learning approach for identifying nonlinear dynamical systems from data. Specifically, we blend classical tools from numerical analysis, namely the multi-step time-stepping schemes, with powerful nonlinear function approximators, namely deep neural networks, to...
Forward Backward Stochastic Neural NetworksDeep Learning of High-dimensional Partial Differential EquationsClassical numerical methods for solving partial differential equations suffer from the curse of dimensionality mainly due to their reliance on meticulously generated spatio-temporal grids. Inspired by modern deep learning based techniques for solving forward and inverse problems associated with partial...
Deep Learning of Vortex Induced VibrationsVortex induced vibrations of bluff bodies occur when the vortex shedding frequency is close to the natural frequency of the structure. Of interest is the prediction of the lift and drag forces on the structure given some limited and scattered...

Full publication list: Google Scholar.