Deep convolutional architectures for extrapolative forecasts in time-dependent flow problems

Bhatt, Pratyush, Kumar, Yash et Soulaïmani, Azzeddine. 2023. « Deep convolutional architectures for extrapolative forecasts in time-dependent flow problems ». Advanced Modeling and Simulation in Engineering Sciences, vol. 10, nº 1.

Prévisualisation

PDF Soulaimani-A-2023-28161.pdf - Version publiée Licence d'utilisation : Creative Commons CC BY. Télécharger (5MB) | Prévisualisation

Résumé

Physical systems whose dynamics are governed by partial differential equations (PDEs) find numerous applications in science and engineering. The process of obtaining the solution from such PDEs may be computationally expensive for large-scale and parameterized problems. In this work, deep learning techniques developed especially for time-series forecasts, such as LSTM and TCN, or for spatial-feature extraction such as CNN, are employed to model the system dynamics for advection-dominated problems. This paper proposes a Convolutional Autoencoder(CAE) model for compression and a CNN future-step predictor for forecasting. These models take as input a sequence of high-fidelity vector solutions for consecutive time steps obtained from the PDEs and forecast the solutions for the subsequent time steps using auto-regression; thereby reducing the computation time and power needed to obtain such high-fidelity solutions. Non-intrusive reduced-order modeling techniques such as deep auto-encoder networks are utilized to compress the high-fidelity snapshots before feeding them as input to the forecasting models in order to reduce the complexity and the required computations in the online and offline stages. The models are tested on numerical benchmarks (1D Burgers’ equation and Stoker’s dam-break problem) to assess the long-term prediction accuracy, even outside the training domain (i.e. extrapolation). The most accurate model is then used to model a hypothetical dam break in a river with complex 2D bathymetry. The proposed CNN future-step predictor revealed much more accurate forecasting than LSTM and TCN in the considered spatiotemporal problems.

Type de document:	Article publié dans une revue, révisé par les pairs
Professeur:	Professeur Soulaïmani, Azzeddine
Affiliation:	Génie mécanique
Date de dépôt:	18 déc. 2023 19:08
Dernière modification:	08 janv. 2024 19:37
URI:	https://espace2.etsmtl.ca/id/eprint/28161

Actions (Authentification requise)

Dernière vérification avant le dépôt