Tae-Soo Chon, Young-Seuk Park, Ja-Myung Kim, Buom-Young Lee, Yeong-Jin Chung, YooShin Kim
Environmental Entomology 29 (6), 1208-1215, (1 December 2000) https://doi.org/10.1603/0046-225X-29.6.1208
KEYWORDS: Thecodiplosis japonensis, pine needle gall midge, population dynamics, prediction, artificial neural network, backpropagation algorithm
The backpropagation algorithm in artificial neural networks was used to forecast dynamic data of a forest pest population of the pine needle gall midge, 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. When new input data were given to the trained network, recognition was possible and population density at the subsequent sampling time could be predicted.