Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Interpretable white-box modeling for nitrogen storage in metal-organic frameworks.

Scientific reports·2026
Same author

Synergistic effects of alkalines, salts, and silica nanoparticles on in-situ surfactant generation from different crude oils in relation to enhanced oil recovery.

Scientific reports·2026
Same author

White-box modeling of asphaltene precipitation during natural depletion of oil reservoirs.

Scientific reports·2026
Same author

Experimental investigation of coal tailing-derived nanoparticles for CO<sub>2</sub> foam stabilization.

Environmental research·2026
Same author

Adapted two-phase capacitance-resistance modeling of polymer flooding in synthetic and benchmark reservoirs with varying degree of heterogeneity.

Scientific reports·2026
Same author

Predicting methane adsorption in coal and shale with white-box and black-box machine learning models.

Scientific reports·2026

Related Experiment Video

Updated: Jul 8, 2025

Biomass Conversion to Produce Hydrocarbon Liquid Fuel Via Hot-vapor Filtered Fast Pyrolysis and Catalytic Hydrotreating
11:28

Biomass Conversion to Produce Hydrocarbon Liquid Fuel Via Hot-vapor Filtered Fast Pyrolysis and Catalytic Hydrotreating

Published on: December 25, 2016

26.5K

Modeling crude oil pyrolysis process using advanced white-box and black-box machine learning techniques.

Fahimeh Hadavimoghaddam1,2, Alexei Rozhenko3, Mohammad-Reza Mohammadi4

  • 1Key Laboratory of Continental Shale Hydrocarbon Accumulation and Efficient Development, Ministry of Education, Northeast Petroleum University, Daqing, 163318, China.

Scientific Reports
|December 19, 2023
PubMed
Summary

Accurate modeling of fuel deposition in crude oil pyrolysis using machine learning predicts outcomes for in-situ combustion enhanced oil recovery (ISC EOR). XGBoost demonstrated superior accuracy in estimating residual crude oil during pyrolysis.

More Related Videos

In Situ Visualization of the Phase Behavior of Oil Samples Under Refinery Process Conditions
11:20

In Situ Visualization of the Phase Behavior of Oil Samples Under Refinery Process Conditions

Published on: February 21, 2017

6.7K
Microfluidic Devices for Characterizing Pore-scale Event Processes in Porous Media for Oil Recovery Applications
08:38

Microfluidic Devices for Characterizing Pore-scale Event Processes in Porous Media for Oil Recovery Applications

Published on: January 16, 2018

10.5K

Related Experiment Videos

Last Updated: Jul 8, 2025

Biomass Conversion to Produce Hydrocarbon Liquid Fuel Via Hot-vapor Filtered Fast Pyrolysis and Catalytic Hydrotreating
11:28

Biomass Conversion to Produce Hydrocarbon Liquid Fuel Via Hot-vapor Filtered Fast Pyrolysis and Catalytic Hydrotreating

Published on: December 25, 2016

26.5K
In Situ Visualization of the Phase Behavior of Oil Samples Under Refinery Process Conditions
11:20

In Situ Visualization of the Phase Behavior of Oil Samples Under Refinery Process Conditions

Published on: February 21, 2017

6.7K
Microfluidic Devices for Characterizing Pore-scale Event Processes in Porous Media for Oil Recovery Applications
08:38

Microfluidic Devices for Characterizing Pore-scale Event Processes in Porous Media for Oil Recovery Applications

Published on: January 16, 2018

10.5K

Area of Science:

  • Petroleum Engineering
  • Chemical Engineering
  • Computational Science

Background:

  • Accurate prediction of fuel deposition during crude oil pyrolysis is crucial for optimizing in-situ combustion enhanced oil recovery (ISC EOR).
  • Existing models may lack the precision required for effective application in complex EOR scenarios.
  • Understanding pyrolysis behavior is key to managing the combustion front and maximizing oil recovery.

Purpose of the Study:

  • To develop and compare machine learning models for precise prediction of fuel deposition during crude oil pyrolysis.
  • To identify the most influential parameters affecting residual crude oil formation.
  • To provide a tool for swift estimation of crude oil residue for improved ISC EOR strategies.

Main Methods:

  • Utilized 2071 experimental thermogravimetric analysis (TGA) datasets from 13 diverse crude oil samples.
  • Applied machine learning techniques: Extreme Gradient Boosting (XGBoost), Gaussian Process Regression (GPR), Categorical Gradient Boosting (CatBoost), and Genetic Programming (GP).
  • Performed sensitivity analysis to determine the impact of input parameters on fuel deposition.

Main Results:

  • The XGBoost model achieved the highest accuracy with a Mean Absolute Percentage Error (MAPE) of 0.7796% and R² of 0.9999.
  • GPR, CatBoost, and GP models also demonstrated strong performance in estimating residual crude oil.
  • Temperature and asphaltenes content were identified as the most significant factors influencing pyrolysis and fuel deposition.

Conclusions:

  • Machine learning, particularly XGBoost, offers highly accurate prediction of fuel deposition during crude oil pyrolysis.
  • Input parameters like temperature, asphaltenes, resins, oil API gravity, and heating rates significantly impact fuel deposition.
  • The developed models provide valuable insights for enhancing the effectiveness of ISC EOR operations.