Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2311.15288 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917557246623744 |
|---|---|
| author | Diab, Waleed Al-Kobaisi, Mohammed |
| author_facet | Diab, Waleed Al-Kobaisi, Mohammed |
| contents | FNO and DeepONet are by far the most popular neural operator learning algorithms. FNO seems to enjoy an edge in popularity due to its ease of use, especially with high dimensional data. However, a lesser-acknowledged feature of DeepONet is its modularity. This feature allows the user the flexibility of choosing the kind of neural network to be used in the trunk and/or branch of the DeepONet. This is beneficial because it has been shown many times that different types of problems require different kinds of network architectures for effective learning. In this work, we will take advantage of this feature by carefully designing a more efficient neural operator based on the DeepONet architecture. We introduce U-Net enhanced DeepONet (U-DeepONet) for learning the solution operator of highly complex CO2-water two-phase flow in heterogeneous porous media. The U-DeepONet is more accurate in predicting gas saturation and pressure buildup than the state-of-the-art U-Net based Fourier Neural Operator (U-FNO) and the Fourier-enhanced Multiple-Input Operator (Fourier-MIONet) trained on the same dataset. In addition, the proposed U-DeepONet is significantly more efficient in training times than both the U-FNO (more than 18 times faster) and the Fourier-MIONet (more than 5 times faster), while consuming less computational resources. We also show that the U-DeepONet is more data efficient and better at generalization than both the U-FNO and the Fourier-MIONet. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2311_15288 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | U-DeepONet: U-Net Enhanced Deep Operator Network for Geologic Carbon Sequestration Diab, Waleed Al-Kobaisi, Mohammed Computational Physics FNO and DeepONet are by far the most popular neural operator learning algorithms. FNO seems to enjoy an edge in popularity due to its ease of use, especially with high dimensional data. However, a lesser-acknowledged feature of DeepONet is its modularity. This feature allows the user the flexibility of choosing the kind of neural network to be used in the trunk and/or branch of the DeepONet. This is beneficial because it has been shown many times that different types of problems require different kinds of network architectures for effective learning. In this work, we will take advantage of this feature by carefully designing a more efficient neural operator based on the DeepONet architecture. We introduce U-Net enhanced DeepONet (U-DeepONet) for learning the solution operator of highly complex CO2-water two-phase flow in heterogeneous porous media. The U-DeepONet is more accurate in predicting gas saturation and pressure buildup than the state-of-the-art U-Net based Fourier Neural Operator (U-FNO) and the Fourier-enhanced Multiple-Input Operator (Fourier-MIONet) trained on the same dataset. In addition, the proposed U-DeepONet is significantly more efficient in training times than both the U-FNO (more than 18 times faster) and the Fourier-MIONet (more than 5 times faster), while consuming less computational resources. We also show that the U-DeepONet is more data efficient and better at generalization than both the U-FNO and the Fourier-MIONet. |
| title | U-DeepONet: U-Net Enhanced Deep Operator Network for Geologic Carbon Sequestration |
| topic | Computational Physics |
| url | https://arxiv.org/abs/2311.15288 |