Sensitivity analysis and stability patterns of two-species pest models using artificial neural networks

Sensitivity analysis is a critical step in mathematical modelling of ecological processes and it provides an idea of the response of the model dynamics to a variation in the values of some parameters. In analytic models, there are standard mathematical techniques for carrying out sensitivity analyses, but this is not so with simulation models, mainly due to the fact that their behaviour usually depends upon the interaction among different parameters, and so sensitivity analysis has to be carried out for all combinations of all parameters of interest. In this study, we explored the use of artificial neural networks (ANN) for sensitivity analysis of simulation models, as applied to simulations models of two-species pest populations: the parasitoid-host system Nezara viridula-Trichopoda giacomellii, N. viridula being a pest of soybean and the Sirex noctilio-Pinus radiata system, S. noctilio being a pest of pine plantations. We compare the ANN sensitivity analysis results with the ones of the Classification Trees (CT), Sobol and the stepwise multiple regression with standardized partial regression coefficients (SMR). The sensitivity analyses were carried out evaluating the simulations models' parameters effect on the stability behaviour of the simulation models. The ANN sensitivity analysis produced the same (or superior) results as the other two techniques (CT, Sobol and SMR), but showed additional advantages similar to those offered by sensitivity analyses of analytic models: partial derivatives were calculated to determine the contribution of each parameter of the simulation models to their stability behaviour. We conclude that ANN is adequate for simulation modelling sensitivity analysis with the additional advantage of evaluating the contribution of model parameters to the model's behaviour. Although, we used only two-species pest systems as an example, this approach may be applied in wide areas of pest management and population dynamics studies.