Modeling Viscosity of CO2–N2 Gaseous Mixtures Using Robust Tree-Based Techniques: Extra Tree, Random Forest, GBoost, and LightGBM

Carbon dioxide (CO2) has an essential role in most enhanced oil recovery (EOR) methods in the oil industry. Oil swelling and viscosity reduction are the dominant mechanisms in an immiscible CO2-EOR process. Besides numerous CO2 applications in EOR, most oil reservoirs do not have access to natural CO2, and capturing it from flue gas and other sources is costly. Flue gases are available in huge quantities at a significantly lower price and can be considered economically viable agents for EOR operations. In this work, four powerful machine learning algorithms, namely, extra tree (ET), random forest (RF), gradient boosting (GBoost), and light gradient boosted machine (LightGBM) were utilized to accurately estimate the viscosity of CO2–N2 mixtures. To this aim, a databank was employed, containing 3036 data points over wide ranges of pressures and temperatures. Temperature, pressure, and CO2 mole fraction were applied as input parameters, and the viscosity of the CO2–N2 mixture was the output. The RF smart model had the highest precision with the lowest average absolute percent relative error (AAPRE) of 1.58%, root mean square error (RMSE) of 2.221, and determination coefficient (R2) of 0.9993. The trend analysis showed that the RF model could precisely predict the real physical behavior of the CO2–N2 viscosity variation. Finally, the outlier detection was performed using the leverage approach to demonstrate the validity of the utilized databank and the applicability area of the developed RF model. Accordingly, nearly 96% of the data points seemed to be dependable and valid, and the rest of them were located in the suspected and out-of-leverage data zones.

[1]  R. Span,et al.  Viscosity measurements of CO2-rich; CO2 + N2 and CO2 + H2 mixtures in gas or supercritical phase at temperatures between 273 and 473 K and pressures up to 8.7 MPa , 2022, Fluid Phase Equilibria.

[2]  A. Naseri,et al.  Experimental measurement and compositional modeling of bubble point pressure in crude oil systems: Soft computing approaches, correlations, and equations of state , 2022, Journal of Petroleum Science and Engineering.

[3]  Á. Miklósi,et al.  Human activity recognition of children with wearable devices using LightGBM machine learning , 2021, Scientific Reports.

[4]  M. N. Amar,et al.  Predicting viscosity of CO2–N2 gaseous mixtures using advanced intelligent schemes , 2022 .

[5]  Abdolhossein Hemmati-Sarapardeh,et al.  Predicting formation damage of oil fields due to mineral scaling during water-flooding operations: Gradient boosting decision tree and cascade-forward back-propagation network , 2022 .

[6]  J. Abdi,et al.  Modeling of CO2 adsorption capacity by porous metal organic frameworks using advanced decision tree-based models , 2021, Scientific Reports.

[7]  R. Zabihi,et al.  Modeling of wax disappearance temperature (WDT) using soft computing approaches: Tree-based models and hybrid models , 2021, Journal of Petroleum Science and Engineering.

[8]  A. M. Al-Khudafi,et al.  Prediction of Gas Viscosity of Yemeni Gas Fields Using Machine Learning Techniques , 2021, Day 2 Tue, October 19, 2021.

[9]  Sungil Kim,et al.  Data-driven estimation of three-phase saturation during gas hydrate depressurization using CT images , 2021 .

[10]  Nadhir Al-Ansari,et al.  An Extra Tree Regression Model for Discharge Coefficient Prediction: Novel, Practical Applications in the Hydraulic Sector and Future Research Directions , 2021, Mathematical Problems in Engineering.

[11]  A. Mosavi,et al.  Modeling hydrogen solubility in hydrocarbons using extreme gradient boosting and equations of state , 2021, Scientific Reports.

[12]  O. Massarweh,et al.  A review of recent developments in CO2 mobility control in enhanced oil recovery , 2021 .

[13]  M. Schaffie,et al.  Application of cascade forward neural network and group method of data handling to modeling crude oil pyrolysis during thermal enhanced oil recovery , 2021 .

[14]  Shahin Kord,et al.  Application of Machine Learning Techniques for Selecting the Most Suitable Enhanced Oil Recovery Method; Challenges and Opportunities , 2021 .

[15]  Emmanuel E. Okoro,et al.  Application of artificial intelligence in predicting the dynamics of bottom hole pressure for under-balanced drilling: Extra tree compared with feed forward neural network model , 2021 .

[16]  C. Dombry,et al.  Gradient boosting for extreme quantile regression , 2021, Extremes.

[17]  Mohammad Islam Miah,et al.  Hybrid connectionist models to assess recovery performance of low salinity water injection , 2020 .

[18]  A. Mosavi,et al.  Comparative Analysis of Machine Learning Models for Nanofluids Viscosity Assessment , 2020, Nanomaterials.

[19]  Gonzalo Martínez-Muñoz,et al.  A comparative analysis of gradient boosting algorithms , 2020, Artificial Intelligence Review.

[20]  T. Coburn,et al.  Well predictive performance of play-wide and Subarea Random Forest models for Bakken productivity , 2020 .

[21]  I. Ahmadianfar,et al.  Prediction of nanofluids viscosity using random forest (RF) approach , 2020 .

[22]  Mohamed El Amine Ben Seghier,et al.  Experimental measurement and compositional modeling of crude oil viscosity at reservoir conditions , 2020 .

[23]  Jin Wang,et al.  Gradient boosting machine for predicting return temperature of district heating system: A case study for residential buildings in Tianjin , 2020 .

[24]  Hongqi Li,et al.  Identifying channel sand-body from multiple seismic attributes with an improved random forest algorithm , 2019, Journal of Petroleum Science and Engineering.

[25]  Chris Carpenter,et al.  Experimental Program Investigates Miscible CO2 WAG Injection in Carbonate Reservoirs , 2019, Journal of Petroleum Technology.

[26]  R. Span,et al.  Measurement and modeling of the viscosity of (nitrogen + carbon dioxide) mixtures at temperatures from (253.15 to 473.15) K with pressures up to 2 MPa , 2018 .

[27]  Afeez O. Gbadamosi,et al.  A comprehensive review of experimental studies of nanoparticles-stabilized foam for enhanced oil recovery , 2018 .

[28]  H. Sun,et al.  Thickening Supercritical CO2 with π-Stacked Co-Polymers: Molecular Insights into the Role of Intermolecular Interaction , 2018, Polymers.

[29]  B. Tohidi,et al.  Viscosity of CO2-rich mixtures from 243 K to 423 K at pressures up to 155 MPa: new experimental viscosity data and modelling , 2018 .

[30]  Huiqing Liu,et al.  3D Experimental Investigation on Enhanced Oil Recovery by Flue Gas Coupled with Steam in Thick Oil Reservoirs , 2018 .

[31]  Daoyong Yang,et al.  Scaling Criteria for Waterflooding and Immiscible CO2 Flooding in Heavy Oil Reservoirs , 2017 .

[32]  Shunxi Zhang,et al.  A new model for the accurate calculation of natural gas viscosity , 2017 .

[33]  Yuhe Wang,et al.  Nanoparticle-Stabilized Foam for Mobility Control in Enhanced Oil Recovery , 2016 .

[34]  Xiaohong Yang,et al.  A theoretical model for the density and temperature dependent viscosity of hydrocarbon gases , 2016 .

[35]  Katja Bachmeier,et al.  Volumetric And Phase Behavior Of Oil Field Hydrocarbon Systems , 2016 .

[36]  Roland Span,et al.  Measurements of the viscosity of carbon dioxide at temperatures from (253.15 to 473.15)K with pressures up to 1.2MPa , 2015 .

[37]  M. Khishvand,et al.  A Novel Correlation for Prediction of Gas Viscosity , 2015 .

[38]  Yanru Zhang,et al.  A gradient boosting method to improve travel time prediction , 2015 .

[39]  I. Tan,et al.  An experimental and numerical study of chemically enhanced water alternating gas injection , 2015, Petroleum Science.

[40]  M. Vossoughi,et al.  Experimental investigation of heavy oil recovery by continuous/WAG injection of CO2 saturated with silica nanoparticles , 2015 .

[41]  E. Khamehchi,et al.  Estimation of dynamic viscosity of natural gas based on genetic programming methodology , 2014 .

[42]  Ehsan Heidaryan,et al.  A simple correlation to estimate natural gas viscosity , 2014 .

[43]  N. Afshar,et al.  An Efficient Reliable Method for Calculation of Natural Gas Viscosity , 2014 .

[44]  Hari S. Viswanathan,et al.  An Integrated Framework for Optimizing CO2 Sequestration and Enhanced Oil Recovery , 2014 .

[45]  Alois Knoll,et al.  Gradient boosting machines, a tutorial , 2013, Front. Neurorobot..

[46]  F. Esmaeilzadeh,et al.  Natural gas viscosity estimation through corresponding states based models , 2013 .

[47]  Guohua Luan,et al.  A New Model for the Accurate Prediction of Liquid Loading in Low-Pressure Gas Wells , 2012 .

[48]  Anne-Laure Boulesteix,et al.  Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics , 2012, WIREs Data Mining Knowl. Discov..

[49]  Farhad Gharagheizi,et al.  A novel method for evaluation of asphaltene precipitation titration data , 2012 .

[50]  E. Nemati Lay,et al.  Prediction of Natural Gas Viscosity using Artificial Neural Network Approach , 2012 .

[51]  M. Ghazanfari,et al.  An Experimental Study of Secondary WAG Injection in a Low-Temperature Carbonate Reservoir in Different Miscibility Conditions , 2012 .

[52]  Ehsan Sanjari,et al.  An accurate empirical correlation for predicting natural gas viscosity , 2011 .

[53]  E. M. El-M. Shokir,et al.  Artificial neural networks modeling for hydrocarbon gas viscosity and density estimation , 2011 .

[54]  Yongan Gu,et al.  Oil Recovery and Permeability Reduction of a Tight Sandstone Reservoir in Immiscible and Miscible CO2 Flooding Processes , 2011 .

[55]  Ehsan Heidaryan,et al.  A new and reliable model for predicting methane viscosity at high pressures and high temperatures , 2010 .

[56]  E. Hassel,et al.  Simultaneous Measurements on Helium and Nitrogen with a Newly Designed Viscometer−Densimeter over a Wide Range of Temperature and Pressure† , 2009 .

[57]  A. Pádua,et al.  Viscosity and density measurements for carbon dioxide + pentaerythritol ester lubricant mixtures at low lubricant concentration , 2008 .

[58]  Paola Gramatica,et al.  Principles of QSAR models validation: internal and external , 2007 .

[59]  Joao P. Hespanha,et al.  from Relative Measurements , 2007 .

[60]  Clarence A. Miller,et al.  Foam sweep in fractures for enhanced oil recovery , 2006 .

[61]  Pierre Geurts,et al.  Extremely randomized trees , 2006, Machine Learning.

[62]  E. Hassel,et al.  Viscosity Measurements on Nitrogen , 2006 .

[63]  Rosalind Archer,et al.  Correlations for Hydrocarbon Gas Viscosity and Gas Density - Validation and Correlation of Behavior Using a Large-Scale Database , 2005 .

[64]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[65]  Chunshan Song,et al.  Tri-reforming of Methane over Ni Catalysts for CO2 Conversion to Syngas With Desired H2/CO Ratios Using Flue Gas of Power Plants Without CO2 Separation , 2004 .

[66]  M. Dong,et al.  Flue Gas Injection for Heavy Oil Recovery , 2002 .

[67]  C. H. Whitson,et al.  Phase Behavior , 2000 .

[68]  P. S. van der Gulik,et al.  Viscosity of carbon dioxide in the liquid phase , 1997 .

[69]  Y. Xiong,et al.  Miscibility, density and viscosity of poly(dimethylsiloxane) in supercritical carbon dioxide , 1995 .

[70]  G. P. Matthews,et al.  Argon+carbon dioxide gaseous mixture viscosities and anisotropic pair potential energy functions , 1993 .

[71]  J. Bae,et al.  A Laboratory Investigation of Viscosified CO2 Process , 1993 .

[72]  Z. A. Chen,et al.  On Viscosity Correlations Of Natural Gas , 1993 .

[73]  H. R. Johnson,et al.  A Flue Gas Huff 'n' Puff Process for Oil Recovery From Shallow Formations , 1990 .

[74]  L. Schramm,et al.  Micro-visualization of foam interactions with a crude oil , 1990 .

[75]  P. Rousseeuw,et al.  Unmasking Multivariate Outliers and Leverage Points , 1990 .

[76]  W. Wakeham,et al.  The prediction of the viscosity of dense gas mixtures , 1989 .

[77]  N. F. Djabbarah,et al.  Sweep Improvement in CO2 Flooding by Use of Foaming Agents , 1988 .

[78]  Peter J. Rousseeuw,et al.  Robust Regression and Outlier Detection , 2005, Wiley Series in Probability and Statistics.

[79]  M. R. Islam,et al.  A Mathematical Representation Of The Carr, Kobayashi And Burrows Natural Gas Viscosity Correlations , 1986 .

[80]  J. Heller,et al.  Direct Thickeners for Mobility Control of CO2 Floods , 1985 .

[81]  Mitsuo Takahashi,et al.  Viscosity of carbon dioxide and ethane , 1981 .

[82]  Klaus Lucas,et al.  Die Druckabhängigkeit der Viskosität von Flüssigkeiten – eine einfache Abschätzung , 1981 .

[83]  William A. Wakeham,et al.  The viscosity and diffusion coefficients of eighteen binary gaseous systems , 1977 .

[84]  H. Haepp Messung der Viskosität von Kohlendioxid und Propylen , 1976 .

[85]  J. Kestin,et al.  The Viscosity of Nine Binary and Two Ternary Mixtures of Gases at Low Density , 1974, Berichte der Bunsengesellschaft für physikalische Chemie.

[86]  M. W. Saunders On the Measurement of the Absolute Viscosity of Nitrogen and Air Over the Temperature Range of 100 to 400°K and at Pressures of 1 to 150 Atmospheres , 1972 .

[87]  J. Kestin,et al.  Viscosity of the Binary Gaseous Mixtures He–Ne and Ne–N2 in the Temperature Range 25–700°C , 1972 .

[88]  J. Kestin,et al.  On the density expansion for viscosity in gases , 1971 .

[89]  B. J. Bailey,et al.  The viscosity of carbon dioxide and acetylene at atmospheric pressure , 1970 .

[90]  I. Golubev Viscosity of gases and gas mixtures : a handbook : (Vyazkost' gazov i gazovykh smesei(spravochnoe rukovodstvo)) , 1970 .

[91]  Joseph Kestin,et al.  Viscosity and Diffusion Coefficient of Six Binary Mixtures , 1968 .

[92]  A. Ramachandran,et al.  Dynamic viscosity of gas mixtures , 1967 .

[93]  R. Dipippo,et al.  Viscosity of Three Binary Gaseous Mixtures , 1967 .

[94]  R. Dipippo,et al.  Viscosity and Binary Diffusion Coefficient of Neon—Carbon Dioxide Mixtures at 20° and 30°C , 1966 .

[95]  J. Kestin,et al.  The viscosity of four binary, gaseous mixtures at 20° and 30°C , 1966 .

[96]  L. I. Stiel,et al.  The viscosity of nonpolar gas mixtures at moderate and high pressures , 1965 .

[97]  John Lohrenz,et al.  Calculating Viscosities of Reservoir Fluids From Their Compositions , 1964 .

[98]  K. Goldman Viscosity of nitrogen at low temperatures and high pressures , 1963 .

[99]  J. Kestin,et al.  On relative measurements of the viscosity of gases by the oscillating-disk method , 1959 .

[100]  G. Brown,et al.  Viscosities of Gases at High Pressures , 1957 .

[101]  A. Michels,et al.  The viscosity of carbon dioxide between 0°C and 75°C and at pressures up to 2000 atmospheres , 1957 .

[102]  D. B. Burrows,et al.  Viscosity of Hydrocarbon Gases Under Pressure , 1954 .

[103]  M. B. Standing,et al.  Volumetric and phase behavior of oil field hydrocarbon systems , 1952 .

[104]  K. Walters,et al.  Measurement of Viscosity , 1946, Nature.

[105]  Donald L. Katz,et al.  Viscosity of Natural Gases , 1944 .

[106]  A. Michels,et al.  The Measurement of the Viscosity of Gases at High Pressures. The Viscosity of Nitrogen to 1000 Atms , 1931 .