New Approaches in Turbulence and Transition Modeling Using Data-driven Techniques

By Karthik Duraisamy, Ze Jia Zhang, Anand Pratap Singh. 2015

237 citations recorded by the source corpus.

Subfields: Atmospheric Science, Computational Mechanics, Statistics and Probability

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atmospheric Science

In Computational Mechanics

In Statistics and Probability

Citations in the corpus

Simulation-assisted machine learning (2018, methodology): “Inversely to the SimKern approach to exploit simulation to enhance ML algorithms, machine learning is also used to correct the inputs to physics simulations (Duraisamy et al., 2015), an idea which is also pursued in the context of traffic prediction (Othman and Tan, 2018).”
PDE-Net 2.0: Learning PDEs from Data with A Numeric-Symbolic Hybrid Deep Network (2018, methodology): “It is common practice in model reduction to use a function approximator to express the unknown terms in the reduced models, such as approximating subgrid stress for large-eddy simulation[27, 28, 29] or approximating interatomic forces for coarse-grained molecular dynamic systems[30, 31].”
Machine learning strategies for systems with invariance properties (2016, unknown): “[12] used neural networks and Gaussian processes to model intermittency in transitional turbulence, and Zhang et al.”
Adaptive activation functions accelerate convergence in deep and physics-informed neural networks (2019, background): “[33] and Duraisamy & co-workers in a series of papers [39, 20, 12].”
Machine Learning-augmented Predictive Modeling of Turbulent Separated Flows over Airfoils (2016, background): “Duraisamy and co-workers [26–29] In this work, we extend the paradigm of data-driven modeling to assist in the development FIG.”
Physics-informed machine learning approach for reconstructing Reynolds stress modeling discrepancies based on DNS data (2016, background): “Duraisamy et al. [16, 18] performed a priori studies to show the potential universality of their discrepancy term β among a class of similar ﬂows, but their performances in a posteriori tests, i.e., using the calibrated discrepancy in one ﬂow to predict another ﬂow, have yet to be demonstrated.”
Machine learning methods for turbulence modeling in subsonic flows around airfoils (2018, methodology): “unction neural networks (RBFNN). In fact, the research work that formally adopts data-driven method to improve or replace RANS model is mainly carried out in the past five years [7]. Duraisamy et al. [8, 9, 10, 11] modeled the source terms in SA turbulence model by neural networks and embedded it in”
Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework (2017, unknown): “ion lies on their choice of input features (i.e., physic coordinates x). As a result, the prediction can only be applied to the ows in the same geometry at the same location. Duraisamy and co-workers [6, 14] used non-dimensional ow and model variables to construct the input feature space for calibra”
Turbulence Modeling in the Age of Data (2018, methodology): “Duraisamy et al. (2015) and Parish and Duraisamy (2016) have explored this avenue.”