Summary of Efficient and Generalizable Nested Fourier-deeponet For Three-dimensional Geological Carbon Sequestration, by Jonathan E. Lee et al.
Efficient and generalizable nested Fourier-DeepONet for three-dimensional geological carbon sequestration
by Jonathan E. Lee, Min Zhu, Ziqiao Xi, Kun Wang, Yanhua O. Yuan, Lu Lu
First submitted to arxiv on: 25 Sep 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computational Physics (physics.comp-ph)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed paper develops a novel framework called nested Fourier-DeepONet to accelerate geological carbon sequestration (GCS) simulations using data-driven machine learning. The framework combines the expressiveness of the Fourier neural operator (FNO) with the modularity of a deep operator network (DeepONet) to predict CO2 migration pathways and pressure distribution in storage formations. The authors demonstrate that their approach is twice as efficient as a nested FNO for training, requires at least 80% less GPU memory, and maintains prediction accuracy. Additionally, they evaluate the generalization and extrapolation abilities of the nested Fourier-DeepONet framework beyond its training range, showing superior performance in terms of time extrapolation and reservoir property changes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper creates a new tool to help make decisions in carbon storage projects by predicting how CO2 will move underground. It uses machine learning to speed up computer simulations, making them faster and more efficient. The authors test this new approach and show that it’s better than the old way at doing things like predicting what happens over time or when different conditions change. |
Keywords
* Artificial intelligence * Generalization * Machine learning
