Name
Abstract | ||
|---|---|---|
•Combine multiscale model reduction and deep learning.•Use sufficient coarse simulation data and limited fine observed data in training.•Derive surrogate coarse-grid models which take into account observed data.•The multiscale concepts provide appropriate information for the design of DNN.•Incorporate fine observation data can improve the coarse grid model. |
Year | DOI | Venue |
|---|---|---|
2020 | 10.1016/j.jcp.2019.109071 | Journal of Computational Physics |
Keywords | Field | DocType |
Multiscale,Deep learning,Upscaling,Neural network,Porous media | Scale model,Mathematical optimization,Nonlinear system,Flow (psychology),Artificial intelligence,Deep learning,Porous medium,Artificial neural network,Mathematics,Model learning | Journal |
Volume | ISSN | Citations |
406 | 0021-9991 | 3 |
PageRank | References | Authors |
0.42 | 2 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yating Wang | 1 | 3 | 0.42 |
| Siu Wun Cheung | 2 | 4 | 1.79 |
| Eric T. Chung | 3 | 388 | 46.61 |
| Yalchin Efendiev | 4 | 581 | 67.04 |
| Min Wang | 5 | 59 | 4.91 |