Modeling of asphaltic sludge formation during acidizing process of oil well reservoir using machine learning methods

Sina Shakouri and Maysam Mohammadzadeh-Shirazi

Energy, 2023, vol. 285, issue C

Abstract: Considering the global need for fossil fuels and its limited resources, maximum production from oil reservoirs is important. Acid treatment is a common method to stimulate oil reservoirs, but acid and oil interaction may form undesirable asphaltic sludge, and the prediction of this phenomenon by using machine learning models can be useful for field application. In this study, multi-layer perceptron (MLP), extreme gradient boosting (XGBoost), random forest (RF), and categorical boosting (CatBoost) as four machine learning models were employed to estimate the weight of asphaltic sludge formed. To this end, a data set containing 199 experimental data for seven different oil samples including a wide range of SARA fractions was used. The input parameters of the models included oil properties, acid properties, and the content of protective additives. The statistical analysis indicated that the MLP model has the highest accuracy with the coefficient of determination (R2) of 0.9517. In addition, the impact analysis of the input variables showed that the ferric ion concentration has the highest impact on asphaltic sludge formation with a relevance factor of 0.2755. Finally, using the leverage method, only 4 outlier data points were identified, which proved the validity of the model.

Keywords: Acid stimulation; Asphaltic sludge; Machine learning; Multi-layer perceptron; Extreme gradient boosting; Categorical boosting (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S036054422302827X
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:285:y:2023:i:c:s036054422302827x

DOI: 10.1016/j.energy.2023.129433

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 ().