Summary of Deep Learning Framework For History Matching Co2 Storage with 4d Seismic and Monitoring Well Data, by Nanzhe Wang et al.
Deep Learning Framework for History Matching CO2 Storage with 4D Seismic and Monitoring Well Data
by Nanzhe Wang, Louis J. Durlofsky
First submitted to arxiv on: 2 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Geophysics (physics.geo-ph); Machine Learning (stat.ML)
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 A novel deep learning-based history matching strategy is proposed for geological carbon storage, addressing the challenge of uncertain formation properties. Two fit-for-purpose surrogate models predict in-situ monitoring well data and interpreted time-lapse (4D) seismic saturation data, enabling early-time assessments to ensure operation performance. The approach involves integrating these models into a hierarchical Markov chain Monte Carlo (MCMC) history matching procedure, demonstrating substantial uncertainty reduction in key geomodel parameters and accurate CO2 plume dynamics predictions. This study showcases the efficiency of integrating multiple data types for geological carbon storage. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Geological carbon storage is like storing a big tank of gas underground. But we don’t know exactly what’s down there, which makes it hard to store the gas safely. Scientists are using special computer models called deep learning models to help figure out what’s going on below ground. They’re building two separate models that can predict different types of data, like how much gas is in certain areas or where the gas is moving. This helps them make sure their storage plans are working correctly. By combining these models with other tools, they were able to reduce uncertainty and make more accurate predictions about what’s happening underground. |
Keywords
* Artificial intelligence * Deep learning
