Use of an artificial neural network to predict population dynamics of the forest-pest pine needle gall midge (Diptera : Cecidomyiida)

The backpropagation algorithm in artificial neural networks was used to for ecast dynamic data of a forest pest population of the pine needle gall midg e, Thecodiplosis japonensis Uchida et Inouye, a serious pest in pine trees in northeast Asia. Data for changes in population density were sequentially given as input, whereas densities of subsequent samplings were provided as matching target data for training of the network. Convergence was reached, generally after 20,000 iterations with learning coefficients of 0.5-0.8. W hen new input data were given to the trained network, recognition was possi ble and population density at the subsequent sampling time could be predict ed.