Multiobjective genetic programming approach for a smooth modeling of the release kinetics of a pheromone dispenser

ABSTRACT

The accurate modeling of the release kinetics of pheromone dispensers is a matter or great importance for ensuring that the dispenser field-life covers the flight period of the pest and for optimizing the layout of dispensers in the treated area. A new experimental dispenser has been recently designed by researchers at the Instituto Agroforestal del Mediterraneo - Centro de Ecologia Quimica Agricola (CEQA) of the Universidad Politecnica de Valencia (Spain). The most challenging problem for the modeling of the release kinetics of this dispensers is the difficulty in obtaining experimental measurements for building the model. The procedure for obtaining these data is very costly, both time and money wise, therefore the available data across the whole season are scarce. In prior work we demonstrated the utility of using Genetic Programming (GP) for this particular problem. However, the models evolved by the GP algorithm tend to have discontinuities in those time ranges where there are not available measurements. In this work we propose the use of a multiobjective Genetic Programming for modeling the performance of the CEQA dispenser. We take two approaches, involving two and nine objectives respectively. In the first one, one of the objectives of the GP algorithm deals with how well the model fits the experimental data, while the second objective measures how "smooth" the model behaviour is. In the second approach we have as many objectives as data points and the aim is to predict each point separately using the remaining ones. The results obtained endorse the utility of this approach for those modeling problems characterized by the lack of experimental data.

REFERENCES

• 1: Eva Alfaro-Cid , Anna I. Esparcia-Alcázar , Pilar Moya , Beatriu Femenia-Ferrer , Ken Sharman , J. J. Merelo, Modeling Pheromone Dispensers Using Genetic Programming, Proceedings of the EvoWorkshops 2009 on Applications of Evolutionary Computing: EvoCOMNET, EvoENVIRONMENT, EvoFIN, EvoGAMES, EvoHOT, EvoIASP, EvoINTERACTION, EvoMUSART, EvoNUM, EvoSTOC, EvoTRANSLOG, April 15-17, 2009, Tübingen, Germany [doi>10.1007/978-3-642-01129-0_73]
• 2: E. Alfaro-Cid, A. Esparcia-Alcazar, P. Moya, J. Merelo, B. Femenia-Ferrer, K. Sharman, and J. Primo. Learning and variable selection in the modeling of pheromone release using genetic programming. Submitted to Computers and Electronics in Agriculture.
• 3: R. Carde and A. Minks. Control of moth pest by mating disruption: successes and constraints. Annual Review of Entomology, 40:559--585, 1995.
• 4: P. Charmillot, T. Degen, D. Pasquier, and F. Briand. Nouveaux procedes a base de pheromones pour lutter contre les vers de la grappe. Rev. Suisse Viticult. Arboricult. Horticult., 37:283--288, 2005.
• 5: P. Charmillot, D. Pasquier, E. Zuerey, and A. Bovard. Essai de lutte par confusion contre les vers de la grappe dans le vignoble du Dezaley en 1999 et 2000. Rev. Suisse Viticult. Arboricult. Horticult., 33:247--251, 2001.
• 6: C. A. C. Coello. Evolutionary multi-objective optimization: A historical view of the field. IEEE Computational Intelligence Magazine, 1(1):28--36, 2006.
• 7: S. Gustafson, E. Burke, and N. Krasnogor. On improving genetic programming for symbolic regression. In Proceedings of the 2005 IEEE Congress on Evolutionary Computation, volume 1, pages 912--919. IEEE Press, September 2005.
• 8: W. Karst. Twelve years of practical experience using matind disruption against Eupoecilia ambiguella and Lobesia botrana in vineyards of the Wuertemberg region, Germany. IOBC/WPRS Bull., 24:71--73, 2001.
• 9: Maarten Keijzer, Scaled Symbolic Regression, Genetic Programming and Evolvable Machines, v.5 n.3, p.259-269, September 2004 [doi>10.1023/B:GENP.0000030195.77571.f9]
• 10: M. Kotanchek, G. Smits, and A. Kordon. Genetic Programming Theory and Practice, chapter Industrial strength genetic programming, pages 239--255. Kluwer Academics, 2003.
• 11: John R. Koza, Genetic programming: on the programming of computers by means of natural selection, MIT Press, Cambridge, MA, 1992
• 12: Foundations of genetic programming, Springer-Verlag New York, Inc., New York, NY, 2002
• 13: F. Louis, A. Schmidt-Tiedemann, and K. Schirra. Control of Sparganothis pilleriana Schiff. and Lobesia botrana Den. & Schiff. in German vineyards using sex pheromone-mediated mating disruption. Bull OILB/SROP, 25:51--58, 2002.
• 14: T. Moschos. Yield loss quantification and assessment of economic injury level for the anthophagous generation of the European grapevine moth Lobesia botrana Den. & Schiff. (Lepidoptera: Tortricidae). Int. J. Pest Manag., 51:81--89, 2005.
• 15: T. Moschos. Yield loss quantification and economic injury level estimation for the carpophagous generation of the European grapevine moth Lobesia botrana Den. & Schiff. (Lepidoptera: Tortricidae). Int. J. Pest Manag., 52:141--147, 2006.
• 16: T. Moschos, C. Souliotis, T. Broumas, and V. Kapothanassi. Control of the European grapevine moth Lobesia botrana in Greece by the mating disruption technique: a three year survey. Phytoparasitica, 32:83--96, 2004.
• 17: R. Poli, W. Langdon, and N. McPhee. A Field Guide to Genetic Programming. Published via http://lulu.com and freely available at http://www.gp-field-guide.org.uk, 2008.
• 18: R. Roehrich and E. Boller. Tortricid pests: their biology, natural enemies and control, chapter Tortricids in vineyards, pages 507--514. Elsevier, 1991.
• 19: A. Sauer and G. Karg. Variables affecting pheromone concentration in vineyards treated for mating disruption of grape vine moth, Lobesia botrana. J. Chem. Ecol., 24:289--302, 1998.
• 20: S. Welter, C. Pickel, J. Millar, F. Cave, R. Van Steenwyk, and J. Dunley. Pheromone mating disruption offer selective management options for key pest. California Agriculture, 59(1):16--22, 2005.
• 21: E. Zitzler, M. Laumanns, and L. Thiele. SPEA2: Improving the Strength pareto evolutionary algorithm. Technical Report 103, Swiss Federal Institute of Technology, 2001.
• 22: N. Zong and X. Hong. Nonlinear channel equalizer design using directional evolutionary multi-objective optimization. International Journal of Systems Science, 36(12):737--755, 2005.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.8 Problem Solving, Control Methods, and Search
          Subjects: Heuristic methods

Additional Classification:
  I. Computing Methodologies
  I.6 SIMULATION AND MODELING
      I.6.5 Model Development
          Subjects: Modeling methodologies

General Terms:
Algorithms

Keywords:
agricultural application, genetic programming, modeling, multiobjective optimization