Journal of Molecular Modeling

, Volume 11, Issue 1, pp 55–60 | Cite as

Prediction of lower critical solution temperature of N-isopropylacrylamide–acrylic acid copolymer by an artificial neural network model

  • Hakan Kayı
  • S. Ali Tuncel
  • Ali Elkamel
  • Erdoğan Alper
Original Paper


In this paper, we have investigated the lower critical solution temperature (LCST) of N-isopropylacrylamide–acrylic acid (NIPAAm-AAc) copolymer as a function of chain-transfer agent/initiator mole ratio, acrylic acid content of copolymer, concentration, pH and ionic strength of aqueous copolymer solution. Aqueous solutions with the desired properties were prepared from previously purified polymers, synthesized at 65 °C by solution polymerization using ethanol. The effects of each parameter on the LCST were examined experimentally.In addition, an artificial neural network model that is able to predict the lower cretical solution temperature was develeped. The predictions from this model compare well against both training and test data sets with an average error less than 2.53%.

Figure Cross plot of predicted and experimental LCST values for the testing data set.


Lower critical solution temperature neural networks N-isopropylacrylamide–acrylic acid copolymer 



This work was supported by The Scientific and Technical Research Council of Turkey (TÜB İ TAK, MISAG-242).


  1. 1.
    Heskins M, Guillet JE (1968) J Macromol Sci Chem 2:1441–1455Google Scholar
  2. 2.
    Chiklis CK, Grasshoff JM (1970) J Polym Sci A; Polym Chem 8:1617–1626Google Scholar
  3. 3.
    Kujawa P, Winnik FM (2001) Macromolecules 43:4130–4135CrossRefGoogle Scholar
  4. 4.
    Elkamel A, Abdul-Wahab S, Bouhamra W, Alper E (2001) Adv Environ Res 5:47–59CrossRefGoogle Scholar
  5. 5.
    Baughman DR, Liu YA (1990) Neural networks in bioprocessing and chemical engineering. Academic, New YorkGoogle Scholar
  6. 6.
    Agatonovic-Kustrin S, Beresford R (2000) J Pharm Biomed Anal 22:717–727CrossRefPubMedGoogle Scholar
  7. 7.
    Pollard JF, Broussard MR, Garrison DB, San KY (1992) Comput Chem Eng 16:253–270CrossRefGoogle Scholar
  8. 8.
    Churchland PS, Sejnowski TJ (1992) The computational brain. MIT Press, CambridgeGoogle Scholar
  9. 9.
    Schalkoff RJ (1997) Artificial neural networks. McGraw-Hill, New YorkGoogle Scholar
  10. 10.
    Basheer IA, Hajmeer M (2000) J Microbiol Methods 43:3–31CrossRefPubMedGoogle Scholar
  11. 11.
    Elkamel A, Kargoub M, Gharbi R (1996) Comp Chem Eng 20:515–520CrossRefGoogle Scholar
  12. 12.
    Quantrille TE, Liu YA (1991) Artificial intelligence in chemical engineering. Academic, New YorkGoogle Scholar
  13. 13.
    Haykin S (1999) Neural networks: a comprehensive foundation. Prentice Hall, EnglewoodcliffsGoogle Scholar
  14. 14.
    Swingler K (1996) Applying neural networks: a practical guide. Academic, New YorkGoogle Scholar
  15. 15.
    Kratz K, Hellweg T, Eimer W (2000) Colloids Surf, A 170:137–149Google Scholar
  16. 16.
    Hagan MT, Menhaj M (1994) IEEE Trans Neural Netw 5:989–993CrossRefGoogle Scholar
  17. 17.
    Demuth H, Beale M (2003) Neural network toolbox for use with matlab. The Mathworks IncGoogle Scholar

Copyright information

© Springer-Verlag 2004

Authors and Affiliations

  • Hakan Kayı
    • 1
    • 3
  • S. Ali Tuncel
    • 1
  • Ali Elkamel
    • 2
  • Erdoğan Alper
    • 1
  1. 1.Chemical Engineering DepartmentHacettepe UniversityBeytepe, AnkaraTurkey
  2. 2.Chemical Engineering DepartmentUniversity of WaterlooOntarioCanada
  3. 3.Computer-Chemie-CentrumErlangen-Nürnberg UniversityErlangenGermany

Personalised recommendations