论文部分内容阅读
综合HP滤波、Elman神经网络、马尔科夫链的优点建立HP-ENN-MC模型对某地区10年内降雨量进行预测.以某地区1990-2015年植物生育期(6-10月)的降雨量数据作为实验训练样本,以2010-2015年(6-10月)的降雨量数据为实验的测试样本,证明HP-ENN-MC模型的实用性.由最后实验结果得到,预测平均相对误差为3.83%.所建模型能够对降雨量准确预测,与Elman、ENN-MC模型相比,HP-ENN-MC模型对降雨量预测更有效.
The HP-ENN-MC model is established based on the advantages of HP filter, Elman neural network and Markov chain to forecast the rainfall in a certain area in 10 years. Taking the rainfall during the period of plant growth (June-October) in a certain area from 1990 to 2015 Data were used as experimental training samples to test the HP-ENN-MC model with the rainfall data from 2010 to 2015 (June-October) as experimental samples. The final experimental results show that the average relative error of prediction is 3.83 The model can predict the rainfall accurately, and the HP-ENN-MC model is more effective in predicting rainfall than the Elman and ENN-MC models.