Predicting asphaltene precipitation during natural depletion of oil reservoirs by integrating SARA fractions with advanced intelligent models

Abstract Asphaltene precipitation during natural depletion can lead to substantial issues in oil transport and production systems, requiring close assessment of crude oil stability through thermodynamic and structural factors. This precipitation can alter wettability, reduce permeability, and block...

Full description

Saved in:
Bibliographic Details
Main Authors: Behnam Amiri-Ramsheh, Sara Sahebalzamani, Reza Zabihi, Abdolhossein Hemmati-Sarapardeh
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-11966-z
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849387789411418112
author Behnam Amiri-Ramsheh
Sara Sahebalzamani
Reza Zabihi
Abdolhossein Hemmati-Sarapardeh
author_facet Behnam Amiri-Ramsheh
Sara Sahebalzamani
Reza Zabihi
Abdolhossein Hemmati-Sarapardeh
author_sort Behnam Amiri-Ramsheh
collection DOAJ
description Abstract Asphaltene precipitation during natural depletion can lead to substantial issues in oil transport and production systems, requiring close assessment of crude oil stability through thermodynamic and structural factors. This precipitation can alter wettability, reduce permeability, and block flow, causing increased pressure drops in wells, upstream facilities, and pipelines. Determining asphaltene precipitation experimentally is time-consuming and costly. Thus, it is essential to find fast and precise techniques for determining asphaltene precipitation. This research aims to accurately predict asphaltene precipitation values using an extensive databank containing 380 experimental data points. Pressure, bubble point pressure, temperature, oil °API gravity, and saturated-aromatic-resin-asphaltene (SARA) fractions of the crude oil samples were treated as input variables, while asphaltene precipitation was the output of the models. Four smart models, namely, extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), cascade forward neural network (CFNN), and generalized regression neural network (GRNN) were constructed. To train the CFNN, the Levenberg-Marquardt (LM) algorithm was implemented. Various statistical and visual assessments were conducted to validate the reliability and precision of constructed models. Findings revealed that the developed LightGBM technique could outperform other models in estimating output values with the lowest absolute error value of 8.57% and the highest correlation coefficient (R2) of 0.9904. Besides, all developed models in this study could forecast asphaltene precipitation values with an absolute error of less than 10%. Also, trend assessment indicated that predicted output values by the LightGBM paradigm have a satisfactory agreement with actual asphaltene precipitation values. Sensitivity evaluation indicated that pressure and the amount of asphaltene exert the most significant negative and positive effects on the output, respectively. Lately, outlier discovery utilizing the Leverage technique illustrated that almost 96% of the used data points seem to be valid and reliable, statistically.
format Article
id doaj-art-7d5baf9f6f294a7591f4dff85109f5b7
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-7d5baf9f6f294a7591f4dff85109f5b72025-08-20T03:42:35ZengNature PortfolioScientific Reports2045-23222025-07-0115111610.1038/s41598-025-11966-zPredicting asphaltene precipitation during natural depletion of oil reservoirs by integrating SARA fractions with advanced intelligent modelsBehnam Amiri-Ramsheh0Sara Sahebalzamani1Reza Zabihi2Abdolhossein Hemmati-Sarapardeh3Department of Petroleum Engineering, Shahid Bahonar University of KermanDepartment of Petroleum Engineering, Shahid Bahonar University of KermanDepartment of Petroleum Engineering, Shahid Bahonar University of KermanDepartment of Petroleum Engineering, Shahid Bahonar University of KermanAbstract Asphaltene precipitation during natural depletion can lead to substantial issues in oil transport and production systems, requiring close assessment of crude oil stability through thermodynamic and structural factors. This precipitation can alter wettability, reduce permeability, and block flow, causing increased pressure drops in wells, upstream facilities, and pipelines. Determining asphaltene precipitation experimentally is time-consuming and costly. Thus, it is essential to find fast and precise techniques for determining asphaltene precipitation. This research aims to accurately predict asphaltene precipitation values using an extensive databank containing 380 experimental data points. Pressure, bubble point pressure, temperature, oil °API gravity, and saturated-aromatic-resin-asphaltene (SARA) fractions of the crude oil samples were treated as input variables, while asphaltene precipitation was the output of the models. Four smart models, namely, extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), cascade forward neural network (CFNN), and generalized regression neural network (GRNN) were constructed. To train the CFNN, the Levenberg-Marquardt (LM) algorithm was implemented. Various statistical and visual assessments were conducted to validate the reliability and precision of constructed models. Findings revealed that the developed LightGBM technique could outperform other models in estimating output values with the lowest absolute error value of 8.57% and the highest correlation coefficient (R2) of 0.9904. Besides, all developed models in this study could forecast asphaltene precipitation values with an absolute error of less than 10%. Also, trend assessment indicated that predicted output values by the LightGBM paradigm have a satisfactory agreement with actual asphaltene precipitation values. Sensitivity evaluation indicated that pressure and the amount of asphaltene exert the most significant negative and positive effects on the output, respectively. Lately, outlier discovery utilizing the Leverage technique illustrated that almost 96% of the used data points seem to be valid and reliable, statistically.https://doi.org/10.1038/s41598-025-11966-zAsphaltene precipitationSARA fractionLightGBMOutlier discovery
spellingShingle Behnam Amiri-Ramsheh
Sara Sahebalzamani
Reza Zabihi
Abdolhossein Hemmati-Sarapardeh
Predicting asphaltene precipitation during natural depletion of oil reservoirs by integrating SARA fractions with advanced intelligent models
Scientific Reports
Asphaltene precipitation
SARA fraction
LightGBM
Outlier discovery
title Predicting asphaltene precipitation during natural depletion of oil reservoirs by integrating SARA fractions with advanced intelligent models
title_full Predicting asphaltene precipitation during natural depletion of oil reservoirs by integrating SARA fractions with advanced intelligent models
title_fullStr Predicting asphaltene precipitation during natural depletion of oil reservoirs by integrating SARA fractions with advanced intelligent models
title_full_unstemmed Predicting asphaltene precipitation during natural depletion of oil reservoirs by integrating SARA fractions with advanced intelligent models
title_short Predicting asphaltene precipitation during natural depletion of oil reservoirs by integrating SARA fractions with advanced intelligent models
title_sort predicting asphaltene precipitation during natural depletion of oil reservoirs by integrating sara fractions with advanced intelligent models
topic Asphaltene precipitation
SARA fraction
LightGBM
Outlier discovery
url https://doi.org/10.1038/s41598-025-11966-z
work_keys_str_mv AT behnamamiriramsheh predictingasphalteneprecipitationduringnaturaldepletionofoilreservoirsbyintegratingsarafractionswithadvancedintelligentmodels
AT sarasahebalzamani predictingasphalteneprecipitationduringnaturaldepletionofoilreservoirsbyintegratingsarafractionswithadvancedintelligentmodels
AT rezazabihi predictingasphalteneprecipitationduringnaturaldepletionofoilreservoirsbyintegratingsarafractionswithadvancedintelligentmodels
AT abdolhosseinhemmatisarapardeh predictingasphalteneprecipitationduringnaturaldepletionofoilreservoirsbyintegratingsarafractionswithadvancedintelligentmodels