Related Experiment Video
Updated: Dec 7, 2025

O-cresol Concentration Online Measurement Based On Near Infrared Spectroscopy Via Partial Least Square Regression
Published on: November 8, 2019
Genetic algorithm based support vector machine regression for prediction of SARA analysis in crude oil samples using
Mahsa Mohammadi1, Mohammadreza Khanmohammadi Khorrami1, Ali Vatani2
1Department of Chemistry, Faculty of Science, Imam Khomeini International University, Qazvin, Iran.
This study introduces a rapid method for analyzing saturates, aromatics, resins, and asphaltenes (SARA) in crude oil using ATR-FTIR spectroscopy and a GA-SVM-R model, offering a superior alternative to traditional techniques.
Area of Science:
- Petroleum Geochemistry
- Analytical Chemistry
- Spectroscopy
Background:
- Conventional saturates, aromatics, resins, and asphaltenes (SARA) analysis is time-consuming, costly, and environmentally unfriendly.
- Accurate SARA fraction determination is crucial for the oil industry for various applications.
- There is a need for faster, more efficient methods for crude oil characterization.
Purpose of the Study:
- To develop and validate a rapid quantitative method for SARA analysis of crude oil samples.
- To evaluate the performance of a hybrid genetic algorithm-support vector machine regression (GA-SVM-R) model coupled with ATR-FTIR spectroscopy.
- To compare the proposed GA-SVM-R model with a genetic algorithm-partial least square regression (GA-PLS-R) model for SARA determination.
Main Methods:
- Utilized attenuated total reflection Fourier-transform infrared (ATR-FTIR) spectroscopy for crude oil sample analysis.
- Developed a hybrid genetic algorithm-support vector machine regression (GA-SVM-R) model for predicting SARA fractions.
- Compared the predictive accuracy of GA-SVM-R against GA-PLS-R using correlation coefficient (R²) and root mean square error (RMSE).
Main Results:
- The GA-SVM-R model demonstrated superior performance in the quantitative determination of SARA fractions compared to the GA-PLS-R model.
- High correlation coefficients (R²) and low root mean square errors (RMSE) were achieved for both calibration and prediction.
- The proposed method successfully predicted SARA analysis of crude oil samples from different Iranian oil fields.
Conclusions:
- The GA-SVM-R model coupled with ATR-FTIR spectroscopy is a reliable and effective alternative for rapid SARA analysis of crude oil.
- This approach offers significant advantages over conventional ASTM methods in terms of speed, cost, and sample requirements.
- The developed method holds substantial value for the oil industry, enabling faster crude oil evaluations.
More Related Videos
08:17Chemical Analysis of Water-accommodated Fractions of Crude Oil Spills Using TIMS-FT-ICR MS
Published on: March 3, 2017
10:50Detection and Quantification of Plasmodium falciparum in Aqueous Red Blood Cells by Attenuated Total Reflection Infrared Spectroscopy and Multivariate Data Analysis
Published on: November 2, 2018
Related Concept Videos
Attenuated Total Reflectance (ATR) Infrared Spectroscopy: Overview
The ATR process begins by directing a beam...
Atomic Absorption Spectroscopy: Lab
Solutions containing organic solvents, such as low-molecular-mass alcohols, esters, or ketones, enhance absorbances by increasing...
Spectroscopy of Carboxylic Acid Derivatives
IR Spectroscopy: Hooke's Law Approximation of Molecular Vibration
According to Hooke's law, the vibrational frequency is directly proportional to...
NMR Spectroscopy of Aromatic Compounds
Mass Spectrometry: Branched Alkane Fragmentation