Date of Publication

4-2023

Document Type

Bachelor's Thesis

Degree Name

Bachelor of Science in Chemical Engineering

Subject Categories

Chemical Engineering | Engineering

College

Gokongwei College of Engineering

Department/Unit

Chemical Engineering

Thesis Advisor

Kathleen B. Aviso
Lawrence P. Belo

Defense Panel Chair

John Frederick D. Tapia

Defense Panel Member

Allan N. Soriano
Raymond R. Tan

Abstract/Summary

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.

Abstract Format

html

Language

English

Format

Electronic

Keywords

Carbon sequestration

Upload Full Text

wf_yes

Embargo Period

5-12-2023

Download

Share

COinS