Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders
Abstract A non-intrusive reduced-order model based on convolutional autoencoders is proposed as a data-driven tool to build an efficient nonlinear reduced-order model for stochastic spatiotemporal large-scale flow problems. The objective is to perform accurate and rapid uncertainty analyses of the f...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-05-01
|
| Series: | Advanced Modeling and Simulation in Engineering Sciences |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40323-023-00244-0 |
| _version_ | 1797822740618543104 |
|---|---|
| author | Azzedine Abdedou Azzeddine Soulaimani |
| author_facet | Azzedine Abdedou Azzeddine Soulaimani |
| author_sort | Azzedine Abdedou |
| collection | DOAJ |
| description | Abstract A non-intrusive reduced-order model based on convolutional autoencoders is proposed as a data-driven tool to build an efficient nonlinear reduced-order model for stochastic spatiotemporal large-scale flow problems. The objective is to perform accurate and rapid uncertainty analyses of the flow outputs of interest for which the input parameters are deemed uncertain. The data are constituted from a set of high-fidelity snapshots, collected using an inhouse high-fidelity flow solver, which correspond to a sample of the uncertain input parameters. The method uses a 1D-convolutional autoencoder to reduce the spatial dimension of the unstructured meshes used by the flow solver. Another convolutional autoencoder is used for the time compression. The encoded latent vectors, generated from the two compression levels, are then mapped to the input parameters using a regression-based multilayer perceptron. The proposed model allows for rapid predictions for unseen parameter values, allowing the output statistical moments to be computed efficiently. The accuracy of the proposed approach is compared to that of the linear reduced-order technique based on an artificial neural network through two benchmark tests (the one-dimensional Burgers and Stoker’s solutions) and a hypothetical dam break flow problem, with an unstructured mesh and over a complex bathymetry river. The numerical results show that the proposed methods present strong predictive capabilities to accurately approximate the statistical moments of the outputs. In particular, the predicted statistical moments are oscillations-free, unlike those obtained with the traditional proper orthogonal decomposition method. The proposed reduction framework is simple to implement and can be applied to other parametric and time-dependent problems governed by partial differential equations, which are commonly encountered in many engineering and science problems. |
| first_indexed | 2024-03-13T10:13:38Z |
| format | Article |
| id | doaj.art-7b3e7a3a2ef34d2db2cba87bb3d145f3 |
| institution | Directory Open Access Journal |
| issn | 2213-7467 |
| language | English |
| last_indexed | 2024-03-13T10:13:38Z |
| publishDate | 2023-05-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Advanced Modeling and Simulation in Engineering Sciences |
| spelling | doaj.art-7b3e7a3a2ef34d2db2cba87bb3d145f32023-05-21T11:21:52ZengSpringerOpenAdvanced Modeling and Simulation in Engineering Sciences2213-74672023-05-0110112710.1186/s40323-023-00244-0Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencodersAzzedine Abdedou0Azzeddine Soulaimani1Department of Mechanical Engineering, Ecole de technologie superieureDepartment of Mechanical Engineering, Ecole de technologie superieureAbstract A non-intrusive reduced-order model based on convolutional autoencoders is proposed as a data-driven tool to build an efficient nonlinear reduced-order model for stochastic spatiotemporal large-scale flow problems. The objective is to perform accurate and rapid uncertainty analyses of the flow outputs of interest for which the input parameters are deemed uncertain. The data are constituted from a set of high-fidelity snapshots, collected using an inhouse high-fidelity flow solver, which correspond to a sample of the uncertain input parameters. The method uses a 1D-convolutional autoencoder to reduce the spatial dimension of the unstructured meshes used by the flow solver. Another convolutional autoencoder is used for the time compression. The encoded latent vectors, generated from the two compression levels, are then mapped to the input parameters using a regression-based multilayer perceptron. The proposed model allows for rapid predictions for unseen parameter values, allowing the output statistical moments to be computed efficiently. The accuracy of the proposed approach is compared to that of the linear reduced-order technique based on an artificial neural network through two benchmark tests (the one-dimensional Burgers and Stoker’s solutions) and a hypothetical dam break flow problem, with an unstructured mesh and over a complex bathymetry river. The numerical results show that the proposed methods present strong predictive capabilities to accurately approximate the statistical moments of the outputs. In particular, the predicted statistical moments are oscillations-free, unlike those obtained with the traditional proper orthogonal decomposition method. The proposed reduction framework is simple to implement and can be applied to other parametric and time-dependent problems governed by partial differential equations, which are commonly encountered in many engineering and science problems.https://doi.org/10.1186/s40323-023-00244-0Uncertainty propagationReduced-order modelingDeep learningConvolutional autoencoders |
| spellingShingle | Azzedine Abdedou Azzeddine Soulaimani Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders Advanced Modeling and Simulation in Engineering Sciences Uncertainty propagation Reduced-order modeling Deep learning Convolutional autoencoders |
| title | Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders |
| title_full | Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders |
| title_fullStr | Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders |
| title_full_unstemmed | Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders |
| title_short | Reduced-order modeling for stochastic large-scale and time-dependent flow problems using deep spatial and temporal convolutional autoencoders |
| title_sort | reduced order modeling for stochastic large scale and time dependent flow problems using deep spatial and temporal convolutional autoencoders |
| topic | Uncertainty propagation Reduced-order modeling Deep learning Convolutional autoencoders |
| url | https://doi.org/10.1186/s40323-023-00244-0 |
| work_keys_str_mv | AT azzedineabdedou reducedordermodelingforstochasticlargescaleandtimedependentflowproblemsusingdeepspatialandtemporalconvolutionalautoencoders AT azzeddinesoulaimani reducedordermodelingforstochasticlargescaleandtimedependentflowproblemsusingdeepspatialandtemporalconvolutionalautoencoders |