Neural Computing and Applications

, Volume 28, Issue 3, pp 505–519 | Cite as

Machine learning use in predicting interior spruce wood density utilizing progeny test information

  • Kostantinos Demertzis
  • Lazaros Iliadis
  • Stavros Avramidis
  • Yousry A. El-Kassaby
Original Article


Several machine learning models were used to predict interior spruce wood density using data from open-pollinated progeny testing trial. The data set consists of growth (height and diameter which were used to estimate individual tree volume) and wood quality (wood density determined by X-ray densitometry, resistance to drilling, and acoustic velocity) attributes for a total of 1146 trees growing on comparable sites in interior British Columbia. Various machine learning models were developed for estimating wood density. The multilayer feed-forward artificial neural networks and gene expression programming provided the highest predictability as compared to the other methods tested, including those based on classical multiple regression which was considered as the comparisons benchmark. The utilization of machine learning models as a credible method for estimating wood density using available growth data as an indirect method for determining trees wood density is expected to become increasingly helpful to forest managers and tree breeders.


Machine learning Artificial neutral networks (ANNs) Interior spruce Progeny test Wood density 



Thanks to Irena Fundova and Tomas Funda for data collection and Barry Jaquish for access to progeny test sites. Funds from the Natural Sciences and Engineering Research Council of Canada’s Discovery and IRC grants, FPInnovations, and the Johnson’s Family Forest Biotechnology Endowment to YAE are highly appreciated.


  1. 1.
    Allard RW (1960) Principles of plant breeding. Wiley, New YorkGoogle Scholar
  2. 2.
    American Society for Testing and Materials (ASTM) (1985) Standard test methods for specific gravity of wood and wood-based materials. American Society for Testing and Materials, Philadelphia. ASTM D 2395-02Google Scholar
  3. 3.
    Anastasakis L, Mort N (2009) Exchange rate forecasting using a combined parametric and nonparametric self-organising modelling approach. Expert Syst Appl 36:12001–12011CrossRefGoogle Scholar
  4. 4.
    Andrews M (2002) Wood quality measurement-son et lumière. N Z J For Sci 47:19–21Google Scholar
  5. 5.
    Bouffier L, Raffin A, Rozenberg P, Meredieu C, Kremer A (2008) What are the consequences of growth selection on wood density in the French maritime pine breeding programme? Tree Genet Genomes 5:11–25CrossRefGoogle Scholar
  6. 6.
    Carter P, Briggs D, Ross RJ, Wang X (2005) Acoustic testing to enhance western forest values and meet customer wood quality needs. In: Harrington CA, Schoenholtz SH (eds) Productivity of western forests: a forest products focus. Gen. Tech. Rep. PNW-GTR-642. U.S. Department of Agriculture, Forest Service, Pacific Northwest Research Station, Portland, pp 121–129Google Scholar
  7. 7.
    Chantre G, Rozenberg P (1997) Can drill resistance profiles (Resistograph) lead to within-profile and within-ring density parameters in Douglas fir wood? In: Zhang SY, Gosselin R, Chauret G (eds) Proceedings of CTIA-IUFRO international wood quality workshop: timber management toward wood quality and end-product values. Forintek Canada, Sainte-Foy, Quebec, Canada, pp 41–47Google Scholar
  8. 8.
    Cown DJ (1978) Comparison of the pilodyn and torsiometer methods for the rapid assessment of wood density in living trees. N Z J For Sci 8:384–391Google Scholar
  9. 9.
    Cown DJ, Clement BC (1983) A wood densitometer using direct scanning with X-rays. Wood Sci Technol 17:91–99CrossRefGoogle Scholar
  10. 10.
    Deng N, Tian Y, Zhang C (2012) Support vector machines: optimization based theory, algorithms, and extensions. Chapman & Hall/CRC press data mining and knowledge discovery series. ISBN 9781439857922Google Scholar
  11. 11.
    El-Kassaby YA, Mansfield SD, Isik F, Stoehr M (2011) In situ wood quality assessment in Douglas-fir. Tree Genet Genomes 7:553–561CrossRefGoogle Scholar
  12. 12.
    Falconer DS, Mackay TFC (1996) Introduction to quantitative genetics. Longman, New YorkGoogle Scholar
  13. 13.
    Farlow SJ (1984) Self-organizing methods in modelling: GMDH type algorithms. Marcel Decker Inc., New YorkMATHGoogle Scholar
  14. 14.
    Ferreira C (2006) Gene expression programming: mathematical modeling by an artificial intelligence, 2nd edn. Springer, Berlin. ISBN 3540327967MATHGoogle Scholar
  15. 15.
    Freedman DA (2005) Statistical models: theory and practice. Cambridge University Press, CambridgeCrossRefMATHGoogle Scholar
  16. 16.
    Gianola D, Okut H, Weigel K, Rosa G (2011) Predicting complex quantitative traits with Bayesian neural networks: a case study with Jersey cows and wheat. BMC Genet 12:87CrossRefGoogle Scholar
  17. 17.
    Goyal S, Goyal GK (2011) Cascade and feed forward back propagation artificial neural network models for prediction of sensory quality of instant coffee flavoured sterilized drink. Can J Artif Intell Mach Learn Pattern Recognit 2:78–82Google Scholar
  18. 18.
    Gurney K (1997) An introduction to neural networks. Taylor and Francis Group Inc., LondonCrossRefGoogle Scholar
  19. 19.
    Hagan MT, Demuth HB, Beale M (1996) Neural network design. PWS Publishing Company, BostonGoogle Scholar
  20. 20.
    Hanrahan G (2011) Artificial neural networks in biological and environmental analysis. CRC Press Inc., Boca RatonCrossRefMATHGoogle Scholar
  21. 21.
    Haykin S (1994) Neural networks: a comprehensive foundation. Macmillan Publishing Company, New YorkMATHGoogle Scholar
  22. 22.
    Holmes G, Donkin A, Witten IH (1994) Weka: a machine learning workbench. In: Proceedings of 2nd Australia an New Zealand conference on intelligent information systems, Brisbane, AustraliaGoogle Scholar
  23. 23.
    Huang G-B (2014) An insight into extreme learning machines: random neurons, random features and kernels. Cognit Comput 6:376–390CrossRefGoogle Scholar
  24. 24.
    Huang L, Song Q, Kasabov N (2008) Evolving connectionist system based role allocation for robotic soccer. Int J Adv Rob Syst 5:59–62Google Scholar
  25. 25.
    Iliadis L (2008) Intelligent information systems and applications in risk estimation. Stamoulis publication, ThessalonikiGoogle Scholar
  26. 26.
    Iliadis L, Mansfield SD, Avramidis S, El-Kassaby YA (2013) Predicting Douglas-fir wood density by artificial neural networks (ANN) based on progeny testing information. Holzforschung 67:771–777CrossRefGoogle Scholar
  27. 27.
    Isik F, Li B (2003) Rapid assessment of wood density of live trees using the Resistograph for selection in tree improvement programs. Can J For Res 33:2426–2435CrossRefGoogle Scholar
  28. 28.
    Ivakhnenko AG (1971) Polynomial theory of complex systems. IEEE Trans Syst Man Cybern 1:364–378MathSciNetCrossRefGoogle Scholar
  29. 29.
    Kasabov N (2001) Evolving fuzzy neural networks for on-line supervised/unsupervised, knowledge-based learning. IEEE Trans Cybern 31:902–918CrossRefGoogle Scholar
  30. 30.
    Kasabov N (2002) Evolving connectionist systems: methods and applications in bioinformatics, brain study and intelligent machines. Springer, New YorkMATHGoogle Scholar
  31. 31.
    Kasabov N, Song Q (2002) DENFIS: dynamic evolving neural-fuzzy inference system and its application for time-series prediction. IEEE Trans Fuzzy Syst 10:144–154CrossRefGoogle Scholar
  32. 32.
    Kiss GK, Yanchuk AD (1991) Preliminary evaluation of genetic variation of weevil resistance in interior spruce in British Columbia. Can J For Res 21:230–234CrossRefGoogle Scholar
  33. 33.
    Koshulko OA, Koshulko GA (2011) Validation strategy selection in combinatorial and multilayered iterative GMDH algorithms. In: Proceedings of 4th international workshop on inductive modelling, Kyiv, Ukraine, pp 51–54Google Scholar
  34. 34.
    Kriesel D (2007) A brief introduction to neural networks.
  35. 35.
    Lehmann EL, Casella G (1998) Theory of point estimation, 2nd edn. Springer, New YorkMATHGoogle Scholar
  36. 36.
    Madala HR, Ivakhnenko AG (1994) Inductive learning algorithms for complex systems modeling. CRC Press, Boca RatonMATHGoogle Scholar
  37. 37.
    Marquardt D (1963) An algorithm for least-squares estimation of nonlinear parameters. SIAM J Appl Math 11:431–441MathSciNetCrossRefMATHGoogle Scholar
  38. 38.
    El-Dien OG, Ratcliffe B, Klápště J, Chen C, Porth I, El-Kassaby YA (2015) Prediction accuracies for growth and wood attributes of interior spruce in space using genotyping-by-sequencing. BMC Genomics 16:370. doi: 10.1186/s12864-015-1597-y CrossRefGoogle Scholar
  39. 39.
    Namkoong G, Kang HC, Brouard JS (1988) Tree breeding: principles and strategies. Monographs on theoretical and applied genetics 11. Springer, New York, p 11Google Scholar
  40. 40.
    Oh S-K, Pedrycz W (2002) The design of self-organizing polynomial neural networks. Inf Sci 141:237–258CrossRefMATHGoogle Scholar
  41. 41.
    Okut H, Wu X-L, Rosa GJM, Bauck S, Woodward BW, Schnabel RD, Taylor JF, Gianola D (2013) Predicting expected progeny difference for marbling score in 43 Angus cattle using artificial neural networks and Bayesian regression models. Genet Sel Evol 45:34CrossRefGoogle Scholar
  42. 42.
    Pereira BDB, Rao CR (2009) Data mining using neural networks: a guide for statisticians.
  43. 43.
    Ratcliffe B, Hart FJ, Klápšte J, Jaquish B, Mansfield SD, El-Kassaby YA (2014) Genetics of wood quality attributes in western larch. Ann For Sci 71:415–424CrossRefGoogle Scholar
  44. 44.
    Rinn F, Scheweingruber FH, Schar E (1996) Resistograph and X-ray density charts of wood comparative evaluation of drill resistance profiles and X-ray density charts of different wood species. Holzforschung 50:303–311CrossRefGoogle Scholar
  45. 45.
    Rodriguez JJ, Kuncheva L, Alonso CJ (2006) Rotation forest: a new classifier ensemble method. IEEE Trans Pattern Anal Mach Intell 28(10):1619–1630CrossRefGoogle Scholar
  46. 46.
    Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by backpropagating errors. Nature 323:533–536CrossRefGoogle Scholar
  47. 47.
    Song Q, Kasabov N (2003) Weighted data normalization and feature selection. In: Proceedings of 8th intelligence information systems conference. Australia & N.Z, pp 87–92Google Scholar
  48. 48.
    Sutton BCS, Flanagan DJ, Gawley JR, Newton CH, Lester DT, El-Kassaby YA (1991) Inheritance of chloroplast and mitochondrial-DNA in Picea and composition of hybrids from introgression zones. Theor Appl Genet 82:242–248CrossRefGoogle Scholar
  49. 49.
    The Mathworks Inc (2005) MATLAB: the language of technical computing, version (R14) service pack 3. The MathWorks Inc., NatickGoogle Scholar
  50. 50.
    Watts MJ (2009) A decade of Kasabov’s evolving connectionist systems: a review. IEEE Trans Syst Man Cybern Part C Appl Rev 39:253–269CrossRefGoogle Scholar
  51. 51.
    White TL, Adams WT, Neale DB (2007) Forest genetics. CABI, OxfordCrossRefGoogle Scholar
  52. 52.
    Winistorfer PM, Xli W, Wimmer R (1995) Application of drill resistance technique for density profile measurement in wood composite panels. For Prod J 45:50–53Google Scholar
  53. 53.
    Witten IH, Frank E (2011) Data mining: practical machine learning tools and techniques, 2nd edn. Morgan Kaufmann. ISBN 978-0-12-374856-0Google Scholar
  54. 54.
    Wu HX, Matheson AC (2004) General and specific combining ability from partial diallels of radiata pine: implications for utility of SCA in breeding and deployment populations. Theor Appl Genet 108:1503–1512CrossRefGoogle Scholar
  55. 55.
    Yanchuk AD (1996) General and specific combining ability from disconnected partial diallels of coastal Douglas-fir. Silvae Genet 45:37–45Google Scholar
  56. 56.
    Zwillinger D, Kokoska S (2000) CRC standard probability and statistics tables and formulae. CRC Press, Boca Raton. ISBN 1-58488-059-7MATHGoogle Scholar

Copyright information

© The Natural Computing Applications Forum 2015

Authors and Affiliations

  • Kostantinos Demertzis
    • 1
  • Lazaros Iliadis
    • 1
  • Stavros Avramidis
    • 2
  • Yousry A. El-Kassaby
    • 3
  1. 1.Department of Forestry and Management of the Environment and Natural ResourcesDemocritus University of ThraceNea OrestiasGreece
  2. 2.Department of Wood Science, Faculty of ForestryUniversity of British ColumbiaVancouverCanada
  3. 3.Department of Forest and Conservation Sciences, Faculty of ForestryUniversity of British ColumbiaVancouverCanada

Personalised recommendations