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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

In carbon capture and sequestration, developing effective monitoring methodsis needed to detect and respond to CO2 leakage. CO2 leakage detection methodsrely on geophysical observations and monitoring sensor network. However,traditional methods usually require the development of site-specific physicalmodels and expert interpretation, and the effectiveness of these methods can belimited to different application locations, operational scenarios, andconditions. In this paper, we developed a novel data-driven leakage detectionmethod based on densely connected convolutional neural networks. Our methoddiffers from conventional leakage monitoring methods by directly learning amapping relationship between seismic data and the CO2 leakage mass. To accountfor the spatial and temporal characteristics of seismic data, our novelnetworks architecture combines 1D and 2D convolutional neural networks. Toovercome the computational expense of solving optimization problems, we apply adensely-connecting strategy in our network architecture that reduces the numberof network parameters. Based on the features generated by our convolutionalneural networks, we further incorporate a long short-term memory network toutilize time-sequential information, which further improves the detectionaccuracy. Finally, we employ our detection method to synthetic seismic datasetsgenerated based on flow simulations of a hypothetical CO2 storage scenario withinjection into a partially compartmentalized sandstone storage reservoir. Toevaluate method performance, we conducted multiple experiments including arandom leakage test, a sequential test, and a robustness test. Numericalresults show that our CO2 leakage detection method successfully detects theleakage and accurately predicts the leakage mass, suggesting that it has thepotential for application in monitoring of real CO2 storage sites.

A Data-Driven CO2 Leakage Detection Using Seismic Data and Spatial-Temporal Densely Connected Convolutional Neural Networks