A novel well log data imputation methods with CGAN and swarm intelligence optimization

Fengtao Qu, Hualin Liao, Jiansheng Liu, Tianyu Wu, Fang Shi and Yuqiang Xu

Energy, 2024, vol. 293, issue C

Abstract: Well log data plays a vital role in decision-making, resource assessment, production optimization, and environmental management of oil and gas development. However, when exploring and developing deep and ultra-deep oil and gas, the performance of logging equipment is greatly challenged by high temperature, high pressure, and high corrosion wellbore conditions. Log data often needs to be completed or corrected. Data imputation technology has become a powerful tool to fill the missing in well log data. A well log data imputation method based on deep learning is proposed. The proposed method combines conditional generative adversarial networks (CGAN) with swarm intelligence optimization algorithms. The seismic layer velocity is used as a constraint to guide CGAN to generate well log data that matches geological features. Establish an objective function based on multiple conditions to evaluate the quality of generated samples. The swarm intelligence optimization algorithm is used to minimize the objective function. The case study shows that the proposed method obtains pseudo samples that meet specific scenarios and perform better than other algorithms. The proposed method provides a new approach for deep learning algorithms in sequence data prediction.

Keywords: Conditional generative adversarial networks; Swarm intelligence optimization; Seismic layer velocity; Well log data imputation (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0360544224004663
Full text for ScienceDirect subscribers only

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:energy:v:293:y:2024:i:c:s0360544224004663

DOI: 10.1016/j.energy.2024.130694

Access Statistics for this article

Energy is currently edited by Henrik Lund and Mark J. Kaiser

More articles in Energy from Elsevier
Bibliographic data for series maintained by Catherine Liu ().