Development of a rule based model to predict CO2 storage stability in geological sites using logical analysis of data

Clicks: 2
ID: 284833
2023
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #2,289 of 3,757 articles by views in Malay Journal

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 3,757 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
Given the increasing amount of CO2 in the air, carbon sequestration underground in geological formations has become a necessity. The geological storage sites need to be secure to prevent the CO2 stored from leaking out and entering the atmosphere further contributing to the increase of greenhouse gases. However, site testing is expensive, inefficient and also poses a risk to human health. As such, Machine Learning (ML) techniques were utilized to analyze the data and transform the data into a model with the given information. In this study, the ML technique used was the Logical Analysis of Data (LAD), wherein the security of a storage site was evaluated using a set of significant attributes. Only selected quantitative attributes were considered: Depth, pressure, temperature, CO2%, CO2 density, reservoir thickness, seal thickness, and fault. LAD was used to determine the essential storage attributes, and Waikato Environment for Knowledge Analysis (WEKA) an entropy-based algorithm, determined the important attribute ranges. The LAD method was applied to three different sets of rule models, which were the single rule, multiple rules, and K-fold method. Using a dataset of 76 samples with 30 used for training and 46 for validation, the best performing model was the single rule model which resulted in 0% false positive and 46.81% not classified during training, and 0% false positives and 44.83% not classified during validation. The important attribute in determining storage security was pressure with a range of 15.92 MPa – 30.94 MPa, which further verified theory and past studies.
Reference Key
persistent_1760653814_68f171f6c9c04 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Yu, Jyllian Reine
Journal Malay Journal
Year 2023
DOI
DOI not found
URL
https://animorepository.dlsu.edu.ph/etdb_chemeng/28
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.