%O cited By 0; Conference of 2024 Offshore Technology Conference Asia, OTCA 2024 ; Conference Date: 27 February 2024 Through 1 March 2024; Conference Code:197405
%L scholars20153
%J Offshore Technology Conference Asia, OTCA 2024
%D 2024
%R 10.4043/34676-MS
%K Climate change; Decision trees; Digital storage; Environmental Protection Agency; Learning algorithms; Machine learning; Natural gas wells; Offshore oil well production; Offshore oil wells; Offshore technology; Sustainable development; Taxation, Class II; Decision-tree algorithm; Decisions makings; Energy landscape; Geologic carbon storages; Geologic sequestrations; Injection wells; Oil and gas well; Storage sites; Tax credits, Carbon dioxide
%X This paper aims to guide decision-makers, particularly in the United States, through the transformation of oil and gas wells into geologic carbon storage sites, with a focus on regulatory nuances. The primary objective of this study is to facilitate informed decision-making for a sustainable energy landscape. The paper presents a simple decision tree algorithm with a dataset consisting of few injection wells from Denver unit of the Wasson Field, West Texas. Data was collected from publicly available sources and the step=by-step approach of collecting data from Texas Railroad commission sources is also provided. The decision tree algorithm assess class II wells' eligibility for class VI permits. Class II wells are injection wells, typically used for EOR. Class VI permits are for injecting carbon dioxide into deep rock formations for long term storage (geologic sequestration). These permits are governed by the U.S. Environmental Protection Agency (EPA) under the Underground Injection Control (UIC) program. EPA has outlined some rules for transforming class II wells into class VI wells. The decision tree algorithm categorizes wells for class VI permits into distinct classes: those suitable for conversion with minor modifications, those requiring additional information, those needing significant modifications, and those deemed unsuitable for this purpose. This approach provides a user-friendly and simplified initial step for decision-making, particularly beneficial for operators without a background in machine learning. The transformation of existing oil and gas wells into geologic carbon storage sites, as outlined in this paper, not only aligns with environmental sustainability goals but also presents a financially advantageous prospect for operators. Repurposing these wells for geologic sequestration of carbon dioxide offers a dual benefit-contributing to the global effort in mitigating climate change while potentially qualifying operators for the 45Q tax credit in the United States. The 45Q tax credit serves as a powerful economic incentive, providing operators with financial rewards for successfully implementing CCS technologies, thereby fostering a more sustainable and economically viable energy landscape. Copyright © 2024, Offshore Technology Conference.
%T Reusing Existing Oil and Gas Wells for CO2 Storage with Machine Learning Algorithm
%A R. Islam
%A R. Sohel
%A F.R. Redzuan
%A F. Hasan
%I Offshore Technology Conference