AI Article Synopsis
- Current seismic processing in the oil and gas industry relies on experts working together to enhance data quality through tasks like noise reduction and analysis.
- The paper introduces "geocycles," a cyclic machine learning approach that replicates this collaborative iterative process, applying it to various pre-stack seismic processing tasks.
- Results indicate that this method significantly boosts data quality—up to 128% improvement—compared to conventional single-cycle machine learning techniques.
Article Abstract
Current seismic processing workflows in the oil and gas industry involve several interactions between different experts to optimize the overall data quality in various tasks, such as noise attenuation, velocity analysis and horizon picking. While many machine learning-based approaches have been proposed to support each of those steps, most of them disregard expert interactions to guide the overall optimization. This paper presents geocycles, a cyclic learning approach that mimics this iterative process, which can be applied to different pre-stack seismic processing tasks. Our method refactor these processes considering training, testing, and evaluation sub-tasks, which allow the selection of samples for greedy sequential processes targeting an overall optimum quality for very large seismic datasets. We present encouraging results showing that a cyclic structure and efficient quality metrics improved overall outcomes in up to 128% for two different seismic processing tasks in comparison to a 1-cycle machine learning approach.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC8060324 | PMC |
| http://dx.doi.org/10.1038/s41598-021-87794-8 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!