Identifying regions of importance in wall-bounded turbulence through explainable deep learning

• URL: http://arxiv.org/abs/2302.01250v4
• Date: Mon, 19 Feb 2024 18:10:37 GMT
• Title: Identifying regions of importance in wall-bounded turbulence through explainable deep learning
• Authors: Andres Cremades, Sergio Hoyas, Rahul Deshpande, Pedro Quintero, Martin Lellep, Will Junghoon Lee, Jason Monty, Nicholas Hutchins, Moritz Linkmann, Ivan Marusic, Ricardo Vinuesa
• Abstract summary: We study interactions among the energy-containing coherent structures in a turbulent flow for the first time using an explainable deep-learning method. Based on the predicted flow, we assess the importance of each structure for this prediction using the game-theoretic algorithm of SHapley Additive exPlanations. This framework has the potential to shed light on numerous fundamental phenomena of wall-bounded turbulence, including novel strategies for flow control.
• Score: 1.6365624921211983
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Despite its great scientific and technological importance, wall-bounded turbulence is an unresolved problem in classical physics that requires new perspectives to be tackled. One of the key strategies has been to study interactions among the energy-containing coherent structures in the flow. Such interactions are explored in this study for the first time using an explainable deep-learning method. The instantaneous velocity field obtained from a turbulent channel flow simulation is used to predict the velocity field in time through a U-net architecture. Based on the predicted flow, we assess the importance of each structure for this prediction using the game-theoretic algorithm of SHapley Additive exPlanations (SHAP). This work provides results in agreement with previous observations in the literature and extends them by revealing that the most important structures in the flow are not necessarily the ones with the highest contribution to the Reynolds shear stress. We also apply the method to an experimental database, where we can identify completely new structures based on their importance score. This framework has the potential to shed light on numerous fundamental phenomena of wall-bounded turbulence, including novel strategies for flow control.

Related papers

• Information-theoretic machine learning for time-varying mode decomposition of separated aerodynamic flows [0.0]
  We consider four examples of separated flows around a wing, namely, laminar periodic wake at post-stall angles of attack, strong gust-wing interactions, and a turbulent wake.<n>The present approach reveals informative vortical structures associated with a time-varying lift response.<n>This study provides causality-based insights into a range of unsteady aerodynamic problems.
  arXiv  Detail & Related papers  (2025-05-30T01:59:59Z)
• A critical assessment of reinforcement learning methods for microswimmer navigation in complex flows [0.0]
  Navigating in a fluid flow while being carried by it, using only accessible information from on-board sensors, is a problem commonly faced by small planktonic organisms.<n>In the last ten years, the fluid mechanics community has widely adopted reinforcement learning, often in the form of its simplest implementations.<n>But it is unclear how good are the strategies learned by these algorithms.
  arXiv  Detail & Related papers  (2025-05-08T09:17:26Z)
• In-Context Linear Regression Demystified: Training Dynamics and Mechanistic Interpretability of Multi-Head Softmax Attention [52.159541540613915]
  We study how multi-head softmax attention models are trained to perform in-context learning on linear data. Our results reveal that in-context learning ability emerges from the trained transformer as an aggregated effect of its architecture and the underlying data distribution.
  arXiv  Detail & Related papers  (2025-03-17T02:00:49Z)
• Physics-informed DeepONet with stiffness-based loss functions for structural response prediction [0.07538606213726905]
  This study introduces an innovative method for real-time prediction of structural static responses using DeepOnet. The trained DeepONet can generate solutions for the entire domain, within a fraction of a second.
  arXiv  Detail & Related papers  (2024-09-02T07:19:47Z)
• A Survey on Physics Informed Reinforcement Learning: Review and Open Problems [25.3906503332344]
  We present a review of the literature on incorporating physics information, as known as physics priors, in reinforcement learning approaches. We introduce a novel taxonomy with the reinforcement learning pipeline as the backbone to classify existing works. This nascent field holds great potential for enhancing reinforcement learning algorithms by increasing their physical plausibility, precision, data efficiency, and applicability in real-world scenarios.
  arXiv  Detail & Related papers  (2023-09-05T02:45:18Z)
• End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics [61.44793171735013]
  We introduce a novel unified architecture, termed latent variation models, which combines the latent learning of cutting-edge generative art approaches with an end-to-end variational framework. Our unified approach achieves a distribution-free distance to the truth of over 20 times less than non-latent state-of-the-art baseline.
  arXiv  Detail & Related papers  (2023-05-17T17:43:10Z)
• Physics-Inspired Temporal Learning of Quadrotor Dynamics for Accurate Model Predictive Trajectory Tracking [76.27433308688592]
  Accurately modeling quadrotor's system dynamics is critical for guaranteeing agile, safe, and stable navigation. We present a novel Physics-Inspired Temporal Convolutional Network (PI-TCN) approach to learning quadrotor's system dynamics purely from robot experience. Our approach combines the expressive power of sparse temporal convolutions and dense feed-forward connections to make accurate system predictions.
  arXiv  Detail & Related papers  (2022-06-07T13:51:35Z)
• Unified Field Theory for Deep and Recurrent Neural Networks [56.735884560668985]
  We present a unified and systematic derivation of the mean-field theory for both recurrent and deep networks. We find that convergence towards the mean-field theory is typically slower for recurrent networks than for deep networks. Our method exposes that Gaussian processes are but the lowest order of a systematic expansion in $1/n$.
  arXiv  Detail & Related papers  (2021-12-10T15:06:11Z)
• A Quantum Inspired Approach to Exploit Turbulence Structures [0.0]
  We introduce a new paradigm for analyzing the structure of turbulent flows by quantifying correlations between different length scales. We present results for interscale correlations of two paradigmatic flow examples, and use these insights to design a structure-resolving algorithm for simulating turbulent flows.
  arXiv  Detail & Related papers  (2021-06-10T14:33:53Z)
• Physics Guided Machine Learning Methods for Hydrology [21.410993515618895]
  We propose an LSTM based deep learning architecture that is coupled with SWAT (Soil and Water Assessment Tool) The efficacy of the approach is being analyzed on several small catchments located in the South Branch of the Root River Watershed in southeast Minnesota.
  arXiv  Detail & Related papers  (2020-12-02T19:17:19Z)
• Frequency-compensated PINNs for Fluid-dynamic Design Problems [3.0168882791480978]
  We propose a physics-informed neural network (PINN) architecture for learning the relationship between simulation output and underlying geometry and boundary conditions. In addition to using a physics-based regularization term, the proposed approach also exploits the underlying physics to learn a set of Fourier features, i.e. frequency and phase parameters. We demonstrate this approach by predicting simulation results over out of range time interval and for design conditions.
  arXiv  Detail & Related papers  (2020-11-03T03:56:41Z)
• An Ode to an ODE [78.97367880223254]
  We present a new paradigm for Neural ODE algorithms, called ODEtoODE, where time-dependent parameters of the main flow evolve according to a matrix flow on the group O(d) This nested system of two flows provides stability and effectiveness of training and provably solves the gradient vanishing-explosion problem.
  arXiv  Detail & Related papers  (2020-06-19T22:05:19Z)
• A Data Scientist's Guide to Streamflow Prediction [55.22219308265945]
  We focus on the element of hydrologic rainfall--runoff models and their application to forecast floods and predict streamflow. This guide aims to help interested data scientists gain an understanding of the problem, the hydrologic concepts involved, and the details that come up along the way.
  arXiv  Detail & Related papers  (2020-06-05T08:04:37Z)
• Neural Topological SLAM for Visual Navigation [112.73876869904]
  We design topological representations for space that leverage semantics and afford approximate geometric reasoning. We describe supervised learning-based algorithms that can build, maintain and use such representations under noisy actuation.
  arXiv  Detail & Related papers  (2020-05-25T17:56:29Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.