Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping

DOI10.1016/J.JCP.2024.113224MaRDI QIDQ6589890FDOQ6589890

Authors: Zhaoyue Xu, Shizhao Wang, Xin-Lei Zhang, Guowei He 

Publication date: 20 August 2024

Published in: Journal of Computational Physics (Search for Journal in Brave)

Recommendations

• Optimal sensor placement using machine learning
• Linear and nonlinear sensor placement strategies for mean-flow reconstruction via data assimilation
• Optimal sensor placement for variational data assimilation of unsteady flows past a rotationally oscillating cylinder
• Efficient deep data assimilation with sparse observations and time-varying sensors
• Shallow neural networks for fluid flow reconstruction with limited sensors

zbMATH Keywords

optimal sensor placementensemble Kalman methodCNNGradCAM

Mathematics Subject Classification ID

Basic methods in fluid mechanics (76Mxx) Turbulence (76Fxx) Fluid mechanics (76-XX)

Cites Work

• DAFI: An Open-Source Framework for Ensemble-Based Data Assimilation and Field Inversion
• Regularized ensemble Kalman methods for inverse problems
• Turbulent Flows
• The ensemble Kalman filter for combined state and parameter estimation
• Ensemble Kalman methods for inverse problems
• Optimal sensor and actuator placement for feedback control of vortex shedding
• Physics-informed covariance kernel for model-form uncertainty quantification with application to turbulent flows
• Quantifying and reducing model-form uncertainties in Reynolds-averaged Navier-Stokes simulations: a data-driven, physics-informed Bayesian approach
• Optimal sensor placement for variational data assimilation of unsteady flows past a rotationally oscillating cylinder
• Approach for uncertainty of turbulence modeling based on data assimilation technique
• Enforcing boundary conditions on physical fields in Bayesian inversion
• Assimilation of disparate data for enhanced reconstruction of turbulent mean flows
• State estimation in wall-bounded flow systems. III: The ensemble Kalman filter
• Optimal sensor placement using machine learning
• Machine-learning-based spatio-temporal super resolution reconstruction of turbulent flows
• A bilevel learning approach for optimal observation placement in variational data assimilation
• Evaluation of ensemble methods for quantifying uncertainties in steady-state CFD applications with small ensemble sizes
• Unsupervised deep learning for super-resolution reconstruction of turbulence
• Optimal observations-based retrieval of topography in 2D shallow water equations using PC-EnKF
• Ensemble Kalman method for learning turbulence models from indirect observation data
• Ensemble Gradient for Learning Turbulence Models from Indirect Observations
• A physics-informed diffusion model for high-fidelity flow field reconstruction
• A cache-efficient reordering method for unstructured meshes with applications to wall-resolved large-eddy simulations
• Combining direct and indirect sparse data for learning generalizable turbulence models
• An information criterion for choosing observation locations in data assimilation and prediction

Cited In (1)

• Efficient deep data assimilation with sparse observations and time-varying sensors

This page was built for publication: Optimal sensor placement for ensemble-based data assimilation using gradient-weighted class activation mapping

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6589890)