Physics-informed machine learning approach for augmenting turbulence models: A comprehensive framework

By Jin-Long Wu, Heng Xiao, Eric Paterson. Physical Review Fluids, 2017

542 citations recorded by the source corpus.

We present a comprehensive framework for augmenting turbulence models with physics-informed machine learning, illustrating a complete workflow from identification of input/output to prediction of mean velocities. The learned model has Galilean invariance and coordinate rotational invariance.

Subfields: Computer Vision and Pattern Recognition, Materials Chemistry, Statistical and Nonlinear Physics

View Paper: https://www.semanticscholar.org/paper/f129974e7322b25cbafe58ced9af9151599b82ad

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Materials Chemistry

In Statistical and Nonlinear Physics

Citations in the corpus

Physics‐Informed Neural Networks (PINNs) for Wave Propagation and Full Waveform Inversions (2021, background): “, 2021), solution of Navier-Stokes equations in fluid mechanics (Wu et al., 2018; Jin et al., 2021), high speed fluid flow (Mao et al.”
Enhancing computational fluid dynamics with machine learning (2021, methodology): “Other ML-based approaches [50, 51] rely on physics-informed random forests to improve RANS models, with applications to cases with secondary ﬂows and separation.”
Reynolds-averaged Navier–Stokes equations with explicit data-driven Reynolds stress closure can be ill-conditioned (2018, unknown): “Therefore, it can be expected that the solved mean velocity by using implicit treatment of DNS Reynolds stress have a better agreement with the DNS mean velocity, which has been confirmed by Wu et al. (2018). In this work, the local condition number assess the relative error of solved mean velocity ”
Integrating Physics-Based Modeling with Machine Learning: A Survey (2020, unknown): “Improve prediction beyond physical model [287] [35] [102] [104] [271] [247] [4] [199] [139][128] [160] [183] [66] [74] [119] [153] [182] [213] [295] [109] [113] [165] [79] [285] [158] [276] [162] [248] [31] [230] [239] [114] [119] [213] [276] [152] [56] [17] [238] [6] [11] [183] [182] [193] [196] [2”
Enforcing Analytic Constraints in Neural Networks Emulating Physical Systems. (2019, background): “Despite the need for physically informed NNs for complex physical systems [2–5], enforcing hard constraints [6] has been limited to physical systems governed by specific equations, such as advection equations [7–9], Reynolds-averaged Navier-Stokes equations [10,11], boundary conditions of idealized ”
Quantification of model uncertainty in RANS simulations: A review (2018, background): “[186] performed the same propagation for fully developed turbulent flows in square ducts at various Reynolds numbers and found that the propagated velocities agree with DNS data satisfactorily.”
Informed Machine Learning – A Taxonomy and Survey of Integrating Prior Knowledge into Learning Systems (2019, background): “In physics, Noether’s theorem states that certain symmetries (invariants) lead to conserved quantities (first integrals) and thus integrate Hamiltonian systems or equations of motion [52], [50].”
Integrating Scientific Knowledge with Machine Learning for Engineering and Environmental Systems (2020, unknown): “1) [266] [10] [219] [158] [140] [182] [203] [76] [86] [130] [174] [204] [231] [313] [121] [125] [187] [92] [306] [180] [298] [184] [267] [39] [247] [133] [130] [231] [298] [173] [66] [24] [255] [12] [17] [203] [204] [213] [239] [125] [281] [214] [176] [249] [310] [309] [311] [245] [78] [266] [297] [”
Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows (2020, background): “In addition to the above references, combinations of machine learning and ﬂuid dynamics have attracted increasing attentions in the community (Maulik & San 2017; Maulik et al. 2019 a ; Lui & Wolf 2019; Salehipour & Peltier 2019; Wu et al. 2018).”
Digital Twin: Values, Challenges and Enablers From a Modeling Perspective (2019, methodology): “Physics-informedML ideas have also been utilized in various areas including inorganic scintillator discovery [358], fluid dynamics [359]–[361], projection-based model reduction [362], cardiovascular system modeling [363], and wind farm applications [364].”
Adaptive activation functions accelerate convergence in deep and physics-informed neural networks (2019, background): “onlinear problems by Raissi and Karniadakis [23] and Raissi et al [24] in the context of solution inference and system identiﬁcation. Data-driven turbulence modeling has been developed by Wang et al. [33] and Duraisamy & co-workers in a series of papers [39, 20, 12]. Physics-informed neural netw”
Deep learning of vortex-induced vibrations (2018, unknown): “[19] in the context of turbulence modeling.”