Advertisement

Variables Selection for Ecotoxicity and Human Toxicity Characterization Using Gamma Test

  • Antonino Marvuglia
  • Mikhail Kanevski
  • Michael Leuenberger
  • Enrico Benetto
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8581)

Abstract

Toxicity characterization of chemicals’ emissions is a complex task which proceeds via multimedia fate and exposure models attached to models of dose–response relationships. Several different environmental multimedia models exist, but in any case a vast amount of data on the properties of the chemical compounds being assessed is required. This paper deals with the selection of informative variables in the problem of deriving characterization factors for eco-toxicology and human toxicology of chemical compounds starting from molecular-based properties. The Gamma Test algorithm has been applied to single out the most informative variables. The set of variables retained varies with the subset of the original dataset used to carry out the analysis. In particular, 16 different subsets have been used. They have been created selecting each time only those entries in the data set where one chosen input variable was available only from measurements/estimations, respectively.

Keywords

Toxicity characterization Life Cycle Assessment USEtox® Gamma Test features selection 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    Rosenbaum, R.K., et al.: USEtox®—the UNEP-SETAC toxicity model: recommended characterisation factors for human toxicity and freshwater ecotoxicity in life cycle impact assessment. Int. J. Life Cycle Assess. 13(7), 532–546 (2008)CrossRefGoogle Scholar
  2. 2.
    Birkved, M., Heijungs, R.: Simplified fate modelling in respect to ecotoxicological and human toxicological characterisation of emissions of chemical compounds. Int. J. Life Cycle Assess. 16(8), 739–747 (2011)CrossRefGoogle Scholar
  3. 3.
    Stefánsson, A., Končar, N., Jones, A.J.: A note on the Gamma Test. Neural Comput. Appl. 5, 131–133 (1997)CrossRefGoogle Scholar
  4. 4.
    Huijbregts, M., Hauschild, M., Jolliet, O., Margni, M., McKone, T., Rosenbaum, R.K., et al.: USEtox® User manual (2010)Google Scholar
  5. 5.
    Jones, A.J.: New tools in non-linear modelling and prediction. Comput. Manag. Science 1(2), 109–149 (2004)CrossRefzbMATHGoogle Scholar
  6. 6.
    Evans, D., Jones, A.J.: Asymptotic moments of near neighbour distance distributions. Proc. of R. Soc. Ser. A 458(2028), 2839–2849 (2002a)Google Scholar
  7. 7.
    Evans, D., Jones, A.J.: A proof of the Gamma Test. Proc. of R. Soc. Ser. A 458(2027), 2759 (2002b)Google Scholar
  8. 8.
    Monte, R.A.: A random walk for dummies. MIT Undergrad. J. Math. 1, 143–148 (1999)Google Scholar
  9. 9.
  10. 10.
    Durrant, P.: winGammaTM: A non-linear data analysis and modelling tool with applications to flood prediction system. Ph.D. thesis, University of Wales, Cardiff, Wales U.K (2001), http://www.cs.cf.ac.uk/user/Antonia.J.Jones

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  • Antonino Marvuglia
    • 1
  • Mikhail Kanevski
    • 2
  • Michael Leuenberger
    • 2
  • Enrico Benetto
    • 1
  1. 1.Resource Centre for Environmental Technologies (CRTE)Public Research Centre Henri TudorEsch-sur-AlzetteLuxembourg
  2. 2.Faculty of Geosciences and Environment, Institute of Earth Surface DynamicsUniversity of LausanneLausanneSwitzerland

Personalised recommendations