Summary of Reservoir History Matching Of the Norne Field with Generative Exotic Priors and a Coupled Mixture Of Experts — Physics Informed Neural Operator Forward Model, by Clement Etienam et al.
Reservoir History Matching of the Norne field with generative exotic priors and a coupled Mixture of Experts – Physics Informed Neural Operator Forward Model
by Clement Etienam, Yang Juntao, Oleg Ovcharenko, Issam Said
First submitted to arxiv on: 2 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computational Engineering, Finance, and Science (cs.CE)
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 novel reservoir characterization workflow developed by researchers couples a physics-informed neural operator (PINO) forward model with a mixture of experts’ approach called cluster classify regress (CCR). This combination enables rapid inverse uncertainty quantification during history matching. The workflow uses an adaptive Regularized Ensemble Kalman inversion (aREKI) method and parametrizes unknown permeability and porosity fields for non-Gaussian posterior measures using variational convolution autoencoders and denoising diffusion implicit models. The CCR works as a supervised model with the PINO surrogate, replicating nonlinear Peaceman well equations. The methodology was compared to a standard numerical black oil simulator on the Norne field, showing similar outputs. This workflow is suitable for ensemble-based approaches, where posterior density sampling is desirable for uncertainty quantification. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A team of researchers created a new way to study underground reservoirs. They used two different machine learning techniques: physics-informed neural operators and mixture of experts. These tools help figure out what’s happening inside the reservoir by looking at data from oil wells. The method was tested on a real field, the Norne field, and it worked well. This new way of studying reservoirs is much faster than traditional methods. |
Keywords
» Artificial intelligence » Diffusion » Machine learning » Mixture of experts » Supervised
