Neural-Network Classifier for the Prediction of Occurrence of Helicoverpa armigera (Hiibner) and its Natural Enemies

Abstract

The cotton bollworm, Helicoverpa armigera (Hiibner) is an important pest in India damaging cotton crop and resulting in economic loss. Accurate and timely prediction of the pest, considering biotic and abiotic factors is essential to reduce the crop loss. In this paper, we present a neural-network classifier for predicting the pest incidence on cotton by considering the season, crop phenology, biotic factors (spiders and Chrysoperla zastrowi sillemi) and abiotic factors such as maximum temperature, minimum temperature, rainfall and relative humidity. Single layer perceptron neural-network with back-propagation algorithm was utilized for the design of the presented intelligent system. Decision tree is presented from the proposed trained neural-network. The results showed that the supervised neural network system could classify or predict the pest incidence as either 'high' or 'low' based upon economic threshold level with high degree of accuracy. Extracting rules from the decision tree helps the user to understand the role of biotic and abiotic factors on H. armigera incidence.