Workflow for predicting undersaturated oil viscosity using machine learning
Undersaturated oil viscosity is a dominant fluid parameter to be measured in oil reservoirs due to its direct involvement in flow calculations. Since PVT experimental work is expensive and time costly, prediction methods are essential. In this work, viscosity data from in-house and literature measur...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-12-01
|
Series: | Results in Engineering |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2590123023006291 |
_version_ | 1797385140267122688 |
---|---|
author | Sofianos Panagiotis Fotias Vassilis Gaganis |
author_facet | Sofianos Panagiotis Fotias Vassilis Gaganis |
author_sort | Sofianos Panagiotis Fotias |
collection | DOAJ |
description | Undersaturated oil viscosity is a dominant fluid parameter to be measured in oil reservoirs due to its direct involvement in flow calculations. Since PVT experimental work is expensive and time costly, prediction methods are essential. In this work, viscosity data from in-house and literature measurements (500+ reports, 20,000+ data points) has been utilized for the first time to develop machine learning models predicting undersaturated oil viscosity using easy-to-get measurements. Several popular statistical metrics are used to judge the accuracy of each algorithm. Our goal is to introduce a complete workflow that demonstrates the integrity of the steps followed and guides in further research in predicting similar PVT properties. The workflow showcases the advantages of combining engineers expertise to the art of data driven models development, specifically on accuracy and ease of implementation, as well as their limitations. |
first_indexed | 2024-03-08T21:49:50Z |
format | Article |
id | doaj.art-3468cd6c0d7b4e14a0bfd97b19400345 |
institution | Directory Open Access Journal |
issn | 2590-1230 |
language | English |
last_indexed | 2024-03-08T21:49:50Z |
publishDate | 2023-12-01 |
publisher | Elsevier |
record_format | Article |
series | Results in Engineering |
spelling | doaj.art-3468cd6c0d7b4e14a0bfd97b194003452023-12-20T07:35:59ZengElsevierResults in Engineering2590-12302023-12-0120101502Workflow for predicting undersaturated oil viscosity using machine learningSofianos Panagiotis Fotias0Vassilis Gaganis1School of Mining and Metallurgical Engineering, National Technical University of Athens, Athens 157 73, Greece; Corresponding author.School of Mining and Metallurgical Engineering, National Technical University of Athens, Athens 157 73, Greece; Institute of Geoenergy, Foundation for Research and Technology, Chania, 73100, GreeceUndersaturated oil viscosity is a dominant fluid parameter to be measured in oil reservoirs due to its direct involvement in flow calculations. Since PVT experimental work is expensive and time costly, prediction methods are essential. In this work, viscosity data from in-house and literature measurements (500+ reports, 20,000+ data points) has been utilized for the first time to develop machine learning models predicting undersaturated oil viscosity using easy-to-get measurements. Several popular statistical metrics are used to judge the accuracy of each algorithm. Our goal is to introduce a complete workflow that demonstrates the integrity of the steps followed and guides in further research in predicting similar PVT properties. The workflow showcases the advantages of combining engineers expertise to the art of data driven models development, specifically on accuracy and ease of implementation, as well as their limitations.http://www.sciencedirect.com/science/article/pii/S2590123023006291Undersaturated oil viscosityModel-based correlationsData-based correlationsMachine learningSupervised regression learningSupport vector machines |
spellingShingle | Sofianos Panagiotis Fotias Vassilis Gaganis Workflow for predicting undersaturated oil viscosity using machine learning Results in Engineering Undersaturated oil viscosity Model-based correlations Data-based correlations Machine learning Supervised regression learning Support vector machines |
title | Workflow for predicting undersaturated oil viscosity using machine learning |
title_full | Workflow for predicting undersaturated oil viscosity using machine learning |
title_fullStr | Workflow for predicting undersaturated oil viscosity using machine learning |
title_full_unstemmed | Workflow for predicting undersaturated oil viscosity using machine learning |
title_short | Workflow for predicting undersaturated oil viscosity using machine learning |
title_sort | workflow for predicting undersaturated oil viscosity using machine learning |
topic | Undersaturated oil viscosity Model-based correlations Data-based correlations Machine learning Supervised regression learning Support vector machines |
url | http://www.sciencedirect.com/science/article/pii/S2590123023006291 |
work_keys_str_mv | AT sofianospanagiotisfotias workflowforpredictingundersaturatedoilviscosityusingmachinelearning AT vassilisgaganis workflowforpredictingundersaturatedoilviscosityusingmachinelearning |