Robust asphaltene onset pressure prediction using ensemble learning

Most works on asphaltene onset pressure (AOP) prediction rely on a single model without making them robust against noise. This paper adopts a robust approach to training three machine learning models—Multi-Layer Perceptron (MLP), CatBoost, and Random Forest (RF)—to predict AOP as a function of oil c...

Full description

Saved in:
Bibliographic Details
Main Authors: Jafar Khalighi, Alexey Cheremisin
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123024017353
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850053696801472512
author Jafar Khalighi
Alexey Cheremisin
author_facet Jafar Khalighi
Alexey Cheremisin
author_sort Jafar Khalighi
collection DOAJ
description Most works on asphaltene onset pressure (AOP) prediction rely on a single model without making them robust against noise. This paper adopts a robust approach to training three machine learning models—Multi-Layer Perceptron (MLP), CatBoost, and Random Forest (RF)—to predict AOP as a function of oil composition, SARA fractions, saturation pressure, and temperature. Moreover, a Power-Law Ensemble Model (PLEM) is used to integrate the predictions obtained from the individual experts. Robustness was achieved by tuning the hyperparameters using 5-fold cross-validation with multiple sets of noisy data. Results revealed that the robust approach enabled models to outperform standard ones on noisy data by >10 %, while keeping a good performance on original data. The PLEM could increase the coefficient of determination by a minimum of 3.4 % relative to the best individual data-driven model, regardless of the tuning strategy. Additionally, the proposed approach outperformed thermodynamic and mathematical models. In the end, Sobol's sensitivity analysis showed that the concentration of C1C7+, asphaltenes, saturates, CO2, and the saturation pressure had a positive impact on AOP, while the temperature and the concentration of N2, H2S, resins, and aromatics had negative effects. The value of the work is leveraging three distinct models to predict AOP and employing a robust hyperparameter tuning approach to make the models robust against measurement errors. The findings indicate that robust hyperparameter tuning increases the stability of the models, while combining the outputs of the models improves the prediction accuracy.
format Article
id doaj-art-abf088634ef44faca28d1628c2a3e433
institution DOAJ
issn 2590-1230
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-abf088634ef44faca28d1628c2a3e4332025-08-20T02:52:27ZengElsevierResults in Engineering2590-12302024-12-012410348310.1016/j.rineng.2024.103483Robust asphaltene onset pressure prediction using ensemble learningJafar Khalighi0Alexey Cheremisin1Corresponding author.; Center for Hydrocarbon Recovery, Skolkovo Institute of Science and Technology, Moscow, RussiaCenter for Hydrocarbon Recovery, Skolkovo Institute of Science and Technology, Moscow, RussiaMost works on asphaltene onset pressure (AOP) prediction rely on a single model without making them robust against noise. This paper adopts a robust approach to training three machine learning models—Multi-Layer Perceptron (MLP), CatBoost, and Random Forest (RF)—to predict AOP as a function of oil composition, SARA fractions, saturation pressure, and temperature. Moreover, a Power-Law Ensemble Model (PLEM) is used to integrate the predictions obtained from the individual experts. Robustness was achieved by tuning the hyperparameters using 5-fold cross-validation with multiple sets of noisy data. Results revealed that the robust approach enabled models to outperform standard ones on noisy data by >10 %, while keeping a good performance on original data. The PLEM could increase the coefficient of determination by a minimum of 3.4 % relative to the best individual data-driven model, regardless of the tuning strategy. Additionally, the proposed approach outperformed thermodynamic and mathematical models. In the end, Sobol's sensitivity analysis showed that the concentration of C1C7+, asphaltenes, saturates, CO2, and the saturation pressure had a positive impact on AOP, while the temperature and the concentration of N2, H2S, resins, and aromatics had negative effects. The value of the work is leveraging three distinct models to predict AOP and employing a robust hyperparameter tuning approach to make the models robust against measurement errors. The findings indicate that robust hyperparameter tuning increases the stability of the models, while combining the outputs of the models improves the prediction accuracy.http://www.sciencedirect.com/science/article/pii/S2590123024017353Asphaltene onset pressureMachine learningEnsemble learningRobust optimizationDigital oilfield
spellingShingle Jafar Khalighi
Alexey Cheremisin
Robust asphaltene onset pressure prediction using ensemble learning
Results in Engineering
Asphaltene onset pressure
Machine learning
Ensemble learning
Robust optimization
Digital oilfield
title Robust asphaltene onset pressure prediction using ensemble learning
title_full Robust asphaltene onset pressure prediction using ensemble learning
title_fullStr Robust asphaltene onset pressure prediction using ensemble learning
title_full_unstemmed Robust asphaltene onset pressure prediction using ensemble learning
title_short Robust asphaltene onset pressure prediction using ensemble learning
title_sort robust asphaltene onset pressure prediction using ensemble learning
topic Asphaltene onset pressure
Machine learning
Ensemble learning
Robust optimization
Digital oilfield
url http://www.sciencedirect.com/science/article/pii/S2590123024017353
work_keys_str_mv AT jafarkhalighi robustasphalteneonsetpressurepredictionusingensemblelearning
AT alexeycheremisin robustasphalteneonsetpressurepredictionusingensemblelearning