English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Monitoring changes inside a reservoir in real time is crucial for the successof CO2 injection and long-term storage. Machine learning (ML) is well-suitedfor real-time CO2 monitoring because of its computational efficiency. However,most existing applications of ML yield only one prediction (i.e., theexpectation) for a given input, which may not properly reflect the distributionof the testing data, if it has a shift with respect to that of the trainingdata. The Simultaneous Quantile Regression (SQR) method can estimate the entireconditional distribution of the target variable of a neural network via pinballloss. Here, we incorporate this technique into seismic inversion for purposesof CO2 monitoring. The uncertainty map is then calculated pixel by pixel from aparticular prediction interval around the median. We also propose a noveldata-augmentation method by sampling the uncertainty to further improveprediction accuracy. The developed methodology is tested on syntheticKimberlina data, which are created by the Department of Energy and based on aCO2 capture and sequestration (CCS) project in California. The results provethat the proposed network can estimate the subsurface velocity rapidly and withsufficient resolution. Furthermore, the computed uncertainty quantifies theprediction accuracy. The method remains robust even if the testing data aredistorted due to problems in the field data acquisition. Another testdemonstrates the effectiveness of the developed data-augmentation method inincreasing the spatial resolution of the estimated velocity field and inreducing the prediction error.

Enhanced prediction accuracy with uncertainty quantification in monitoring CO2 sequestration using convolutional neural networks