Prediction of CO2 absorption by physical solvents using a chemoinformatics-based machine learning model

Abstract

The rising atmospheric CO2 level is partly responsible for global warming. Despite numerous warnings from scientists during the past years, nations are reacting too slowly, and thus, we will probably reach a situation needing rapid and effective techniques to reduce atmospheric CO2. Therefore, advanced engineering methods are particularly important to decrease the greenhouse effect, for instance, by capturing CO2 using solvents. Experimental testing of many solvents under different conditions is necessary but time-consuming. Alternatively, modeling CO2 capture by solvents using a nonlinear fitting machine learning is a rapid way to select potential solvents, prior to experimentation. Previous predictive machine learning models were mainly designed for blended solutions in water using the solution concentration as the main input of the model, which was not able to predict CO2 solubility in different types of physical solvents. To address this issue, here, we developed a new descriptor-based chemoinformatics model for predicting CO2 solubility in physical solvents in the form of mole fraction. The input factors include organic structural and bond information, thermodynamic properties, and experimental conditions. We studied the solvents from 823 data, including methanol (165 data), ethanol (138), n-propanol (98), n-butanol (64), n-pentanol (59), ethylene glycol (52), propylene glycol (54), acetone (51), 2-butanone (49), ethylene glycol monomethyl ether (46 data), and ethylene glycol monoethyl ether (47), using artificial neural networks as the machine learning model. Results show that our descriptor-based model predicts the CO2 absorption in physical solvents with generally higher accuracy and low root-mean-squared errors. Our findings show that using a set of simple but effective chemoinformatics-based descriptors, intrinsic relationships between the general properties of physical solvents and their CO2 solubility can be precisely fitted with machine learning.

This is a preview of subscription content, log in to check access.

Fig. 1
Fig. 2
Fig. 3

References

  1. Aaron D, Tsouris C (2005) Separation of CO2 from flue gas: a review. Sep Sci Technol 40:321–348. https://doi.org/10.1081/SS-200042244

    Article  CAS  Google Scholar 

  2. Adzic RR, Zhang J, Sasaki K et al (2007) Platinum monolayer fuel cell electrocatalysts. Top Catal 46:249–262. https://doi.org/10.1007/s11244-007-9003-x

    Article  CAS  Google Scholar 

  3. Aeshala LM, Uppaluri RG, Verma A (2013) Effect of cationic and anionic solid polymer electrolyte on direct electrochemical reduction of gaseous CO2 to fuel. J CO2 Util 3(4):49–55. https://doi.org/10.1016/j.jcou.2013.09.004

    Article  CAS  Google Scholar 

  4. Behler J, Parrinello M (2007) Generalized neural-network representation of high-dimensional potential-energy surfaces. Phys Rev Lett. https://doi.org/10.1103/physrevlett.98.146401

    Article  Google Scholar 

  5. Bezanehtak K, Combes GB, Dehghani F et al (2002) Vapor-liquid equilibrium for binary systems of carbon dioxide + methanol, hydrogen + methanol, and hydrogen + carbon dioxide at high pressures. J Chem Eng Data 47:161–168. https://doi.org/10.1021/je010122m

    Article  CAS  Google Scholar 

  6. Böttcher T (2016) An additive definition of molecular complexity. J Chem Inf Model. https://doi.org/10.1021/acs.jcim.5b00723

    Article  Google Scholar 

  7. Browne MW (2000) Cross-validation methods. J Math Psychol 44:108–132. https://doi.org/10.1006/jmps.1999.1279

    Article  CAS  Google Scholar 

  8. Dai C, Wei W, Lei Z, Li C, Chen B (2015) Absorption of CO2 with methanol and ionic liquid mixture at low temperatures. Fluid Phase Equilib 391:9–17. https://doi.org/10.1016/j.fluid.2015.02.002

    Article  CAS  Google Scholar 

  9. Duan Z, Sun R (2003) An improved model calculating CO2 solubility in pure water and aqueous NaCl solutions from 273 to 533 K and from 0 to 2000 bar. Chem Geol 193:257–271. https://doi.org/10.1016/S0009-2541(02)00263-2

    Article  CAS  Google Scholar 

  10. Gui X, Tang Z, Fei W (2011) Solubility of CO2 in alcohols, glycols, ethers, and ketones at high pressures from (288.15 to 318.15) K. J Chem Eng Data 56:2420–2429. https://doi.org/10.1021/je101344v

    Article  CAS  Google Scholar 

  11. Hornik K, Stinchcombe M, White H (1989) Multilayer feedforward networks are universal approximators. Neural Netw 2:359–366. https://doi.org/10.1016/0893-6080(89)90020-8

    Article  Google Scholar 

  12. Koytsoumpa EI, Bergins C, Kakaras E (2018) The CO2 economy: review of CO2 capture and reuse technologies. J Supercrit Fluids 132:3–16. https://doi.org/10.1016/j.supflu.2017.07.029

    Article  CAS  Google Scholar 

  13. Krupa SV, Kickert RN (1993) The greenhouse effect: the impacts of carbon dioxide (CO2), ultraviolet-B (UV-B) radiation and ozone (O3) on vegetation (crops). Vegetatio 104–105:223–238. https://doi.org/10.1007/BF00048155

    Article  Google Scholar 

  14. Li H, Henkelman GA (2017) Dehydrogenation selectivity of ethanol on close-packed transition metal surfaces: a computational study of monometallic, Pd/Au, and Rh/Au catalysts. J Phys Chem C 121:27504–27510. https://doi.org/10.1021/acs.jpcc.7b09953

    Article  CAS  Google Scholar 

  15. Li H, Zhang Z (2018) Mining the intrinsic trends of CO2 solubility in blended solutions. J CO2 Util 26:496–502. https://doi.org/10.1016/j.jcou.2018.06.008

    Article  CAS  Google Scholar 

  16. Li B, Duan Y, Luebke D, Morreale B (2013) Advances in CO2 capture technology: a patent review. Appl Energy 102:1439–1447. https://doi.org/10.1016/j.apenergy.2012.09.009

    Article  CAS  Google Scholar 

  17. Li H, Chen F, Cheng K et al (2015) Prediction of zeta potential of decomposed peat via machine learning: comparative study of support vector machine and artificial neural networks. Int J Electrochem Sci 10:6044–6056

    CAS  Google Scholar 

  18. Li H, Liu Z, Liu K, Zhang Z (2017a) Predictive power of machine learning for optimizing solar water heater performance: the potential application of high-throughput screening. Int J Photoenergy 1:2. https://doi.org/10.1155/2017/4194251

    Article  Google Scholar 

  19. Li H, Zhang Z, Liu Z (2017b) Application of artificial neural networks for catalysis: a review. Catalysts 7:306. https://doi.org/10.3390/catal7100306

    Article  CAS  Google Scholar 

  20. Li H, Evans EJ, Mullins CB, Henkelman G (2018a) Ethanol decomposition on Pd-Au alloy catalysts. J Phys Chem C 122:22024–22032. https://doi.org/10.1021/acs.jpcc.8b08150

    Article  CAS  Google Scholar 

  21. Li H, Luo L, Kunal P et al (2018b) Oxygen reduction reaction on classically immiscible bimetallics: a case study of RhAu. J Phys Chem C 122:2712–2716. https://doi.org/10.1021/acs.jpcc.7b10974

    Article  CAS  Google Scholar 

  22. Li H, Shin K, Henkelman G (2018c) Effects of ensembles, ligand, and strain on adsorbate binding to alloy surfaces. J Chem Phys 149:174705. https://doi.org/10.1063/1.5053894

    Article  CAS  Google Scholar 

  23. Liu P, Lin H, Yang Y et al (2014) New insights into thermal decomposition of polycyclic aromatic hydrocarbon oxyradicals. J Phys Chem A 118:11337–11345. https://doi.org/10.1021/jp510498j

    Article  CAS  Google Scholar 

  24. Liu P, Li Z, Roberts WL (2018a) The growth of PAHs and soot in the post-flame region. Proc Combust Inst 000:1–8. https://doi.org/10.1016/j.proci.2018.05.047

    CAS  Article  Google Scholar 

  25. Liu P, Zhang Y, Wang L et al (2018b) Chemical mechanism of exhaust gas recirculation on polycyclic aromatic hydrocarbons formation based on laser-induced fluorescence measurement. Energy Fuels 32:7112–7124. https://doi.org/10.1021/acs.energyfuels.8b00422

    Article  CAS  Google Scholar 

  26. Maeda T (2018) Technical note: how to rationally compare the performances of different machine learning models? PeerJ Preprints 6:e26714v1. https://doi.org/10.7287/peerj.preprints.26714v1

    Article  Google Scholar 

  27. Murad S, Gupta S (2000) A simple molecular dynamics simulation for calculating Henry’s constant and solubility of gases in liquids. Chem Phys Lett 319:60–64. https://doi.org/10.1016/S0009-2614(00)00085-3

    Article  CAS  Google Scholar 

  28. Nawi NM, Khan A, Rehman MZ (2013) A new back-propagation neural network optimized. Iccsa 2013:413–426. https://doi.org/10.1007/978-3-642-39637-3

    Article  Google Scholar 

  29. Padilla M, Baturina O, Gordon JP, Artyushkova K, Atanassov P, Serov A (2017) Selective CO2 electroreduction to C2H4 on porous Cu films synthesized by sacrificial support method. J CO2 Util 19:137–145. https://doi.org/10.1016/j.jcou.2017.03.006

    Article  CAS  Google Scholar 

  30. Park J-H, Jun C-H (2013) Multivariate process control chart for controlling the false discovery rate. Ind Eng Manag Syst 11:385–389. https://doi.org/10.7232/iems.2012.11.4.385

    Article  Google Scholar 

  31. Park J, Jun CH (2015) A new multivariate EWMA control chart via multiple testing. J Process Control. https://doi.org/10.1016/j.jprocont.2015.01.007

    Article  Google Scholar 

  32. Paul S, Ghoshal AK, Mandal B (2008) Theoretical studies on separation of CO2 by single and blended aqueous alkanolamine solvents in flat sheet membrane contactor (FSMC). Chem Eng J 144:352–360. https://doi.org/10.1016/j.cej.2008.01.036

    Article  CAS  Google Scholar 

  33. Secuianu C, Feroiu V, Geană D (2008) Phase behavior for carbon dioxide + ethanol system: experimental measurements and modeling with a cubic equation of state. J Supercrit Fluids 47:109–116. https://doi.org/10.1016/j.supflu.2008.08.004

    Article  CAS  Google Scholar 

  34. Secuianu C, Feroiu V, Geanǎ D (2009) Phase equilibria experiments and calculations for carbon dioxide + methanol binary system. Cent Eur J Chem 7:1–7. https://doi.org/10.2478/s11532-008-0085-5

    Article  CAS  Google Scholar 

  35. Singh S, Gautam RK, Malik K, Verma A (2017) Ag-Co bimetallic catalyst for electrochemical reduction of CO2 to value added products. J CO2 Util 18:139–146. https://doi.org/10.1016/j.jcou.2017.01.022

    Article  CAS  Google Scholar 

  36. Specht DF (1991) A general regression neural network. IEEE Trans Neural Netw 2:568–576. https://doi.org/10.1109/72.97934

    Article  CAS  Google Scholar 

  37. Svozil D, Kvasnicka V, Pospichal J (1997) Introduction to multi-layer feed-forward neural networks. Chemom Intell Lab Syst 39:43–62. https://doi.org/10.1016/S0169-7439(97)00061-0

    Article  CAS  Google Scholar 

  38. Tetko IV, Livingstone DJ, Luik AI (1995) Neural network studies. 1. Comparison of overfitting and overtraining. J Chem Inf Comput Sci 35:826–833. https://doi.org/10.1021/ci00027a006

    Article  CAS  Google Scholar 

  39. Tontiwachwuthikul P, Meisen A, Lim CJ (1992) CO2 absorption by NaOH, monoethanolamine and 2-amino-2-methyl-1-propanol solutions in a packed column. Chem Eng Sci 47:381–390. https://doi.org/10.1016/0009-2509(92)80028-B

    Article  CAS  Google Scholar 

  40. Tsivintzelis I, Missopolinou D, Kalogiannis K, Panayiotou C (2004) Phase compositions and saturated densities for the binary systems of carbon dioxide with ethanol and dichloromethane. Fluid Phase Equilib 224:89–96. https://doi.org/10.1016/j.fluid.2004.06.046

    Article  CAS  Google Scholar 

  41. Wang Y, Xiao J, Suzek TO, Zhang J, Wang J, Bryant SH (2009) PubChem: a public information system for analyzing bioactivities of small molecules. Nucleic Acids Res 37:W623–W633. https://doi.org/10.1093/nar/gkp456

    Article  CAS  Google Scholar 

  42. Wei CC, Puxty G, Feron P (2014) Amino acid salts for CO2 capture at flue gas temperatures. Chem Eng Sci 107:218–226. https://doi.org/10.1016/j.ces.2013.11.034

    Article  CAS  Google Scholar 

  43. Yim JH, Jung YG, Lim JS (2010) Vapor-liquid equilibria of carbon dioxide + n-propanol at elevated pressure. Korean J Chem Eng 27:284–288. https://doi.org/10.1007/s11814-009-0342-0

    Article  CAS  Google Scholar 

  44. Yu CH, Huang CH, Tan CS (2012) A review of CO2 capture by absorption and adsorption. Aerosol Air Qual Res 12:745–769. https://doi.org/10.4209/aaqr.2012.05.0132

    Article  CAS  Google Scholar 

  45. Zhang G, Eddy Patuwo B, Hu MY (1998) Forecasting with artificial neural networks. Int J Forecast 14:35–62. https://doi.org/10.1016/s0169-2070(97)00044-7

    Article  CAS  Google Scholar 

  46. Zhang Z, Chen F, Rezakazemi M, Zhang W, Lu C, Chang H, Quan X (2018a) Modeling of a CO2-piperazine-membrane absorption system. Chem Eng Res Des 131:375–384. https://doi.org/10.1016/j.cherd.2017.11.024

    Article  CAS  Google Scholar 

  47. Zhang Z, Li H, Chang H, Pan Z, Luo X (2018b) Machine learning predictive framework for CO2 thermodynamic properties in solution. J CO2 Util 26:152–159. https://doi.org/10.1016/j.jcou.2018.04.025

    Article  CAS  Google Scholar 

  48. Zhang Z, Li Y, Zhang W, Wang J, Soltanian MR, Olabi AG (2018c) Effectiveness of amino acid salt solutions in capturing CO2: a review. Renew Sustain Energy Rev 98:179–188. https://doi.org/10.1016/j.rser.2018.09.019

    Article  CAS  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Zhien Zhang.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (DOCX 121 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Li, H., Yan, D., Zhang, Z. et al. Prediction of CO2 absorption by physical solvents using a chemoinformatics-based machine learning model. Environ Chem Lett 17, 1397–1404 (2019). https://doi.org/10.1007/s10311-019-00874-0

Download citation

Keywords

  • Chemoinformatics
  • Greenhouse gas
  • CO2
  • Absorption
  • Solubility
  • Physical solvent
  • Chemical descriptors
  • Prediction
  • Machine learning
  • Artificial neural network (ANN)