遗传算法优化神经网络的汛期降水模型  

Flood Season Precipitation Forecasting Model Based on Neural Network By Genetic Algorithms

作　　者：农吉夫[1] 黄文宁[2] 

机构地区：[1]广西民族大学数学与计算机科学学院,广西南宁530006 [2]河池学院数学系,广西宜州546300

出　　处：《数学的实践与认识》2010年第20期54-58,共5页Mathematics in Practice and Theory

摘　　要：针对目前神经网络在实际应用中,网络结构难以确定以及网络极易陷入局部解问题,用遗传算法优化神经网络的连接权和网络结构,并在遗传进化过程中采取保留最佳个体的方法,建立基于遗传算法的神经网络模型,实例研究结果表明该方法可以取得较高的预测精度.For overcoming difficulties in application of the method of BP neural network,this paper proposed to optimize the neural network structure and connection weights by means of genetic algorithm whilst to reserve the best individual in evolution process,so that to build up a genetic algorithms Neural Networks model.The result of study indicates that this method can gain a higher forecasting precision.

关 键 词：短期气候预测 神经网络 遗传算法 

分 类 号：P426.61[天文地球—大气科学及气象学]