摘要
提出了运用人工神经网络技术进行梨黑星病预测的新思路,并以梨黑星病发病的主要影响因素,即上年7月的降水量和上年8月的降水量作为训练样本模式提供给网络,按照误差逆传播网络的学习规则对网络进行训练,经过计算机2844次学习后,网络达到预先给定的收敛标准,使网络具备了预测梨树黑星病流行趋势和流行强度的功能.检验结果表明,该方法性能良好,预测准确率高,可望成为果树病虫害预测预报的有效辅助手段.
Based on the Artificial Neural Network(ANN),We put forword a new prediction method for pear scab Ventuna Nashicola. Taking the historial data of pear scab Venturia Nashicola in Jangsu province as sample pattern, the network was trained in the light of learning rule of F3P. After 2844 tries, the network reached the convergence standard given in advance, enabling it to possess the function for predict the pear scab vertura Nashicola.The result indicated that this method have good performance and have a satisfactory forecasting effect.This method have the hope to turn into a effective means for the prediction of plant disease and insect pests.
出处
《生物数学学报》
CSCD
2002年第4期440-443,共4页
Journal of Biomathematics
