Summary of Ai Enhanced Data Assimilation and Uncertainty Quantification Applied to Geological Carbon Storage, by G. S. Seabra (1 et al.
AI enhanced data assimilation and uncertainty quantification applied to Geological Carbon Storage
by G. S. Seabra, N. T. Mücke, V. L. S. Silva, D. Voskov, F. Vossepoel
First submitted to arxiv on: 9 Feb 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
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 This paper explores the integration of machine learning (ML) and data assimilation (DA) techniques for Geological Carbon Storage (GCS) projects. The authors evaluate the surrogate modeling capabilities of Fourier Neural Operators (FNOs) and Transformer UNet (T-UNet) in CO2 injection simulations within channelized reservoirs. They introduce two novel methods: Surrogate-based hybrid ESMDA (SH-ESMDA), which uses FNOs and T-UNet as surrogate models, and Surrogate-based Hybrid RML (SH-RML), a variational data assimilation approach that leverages the randomized maximum likelihood method. The authors demonstrate that SH-RML offers better uncertainty quantification compared to conventional ESMDA for the case study. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This research combines two powerful techniques, machine learning and data assimilation, to improve our understanding of underground carbon storage. The scientists tested different models to see which ones work best in simulating how carbon dioxide behaves in reservoirs. They developed new methods that can process large amounts of data quickly and accurately, making it easier to predict the spread of carbon dioxide underground. This is important for storing carbon dioxide safely and effectively, helping to reduce greenhouse gas emissions and combat climate change. |
Keywords
* Artificial intelligence * Likelihood * Machine learning * Transformer * Unet
