中国农业气象

• 论文 • 上一篇    下一篇

基于主分量的神经网络气温预报模型

孙鸿娉;闫世明;李培仁;王雁;   

  1. 南京信息工程大学,山西省气象科学研究所,山西省人工降雨防雹办公室,山西省气象科学研究所 南京210044,山西省人工降雨防雹办公室
  • 出版日期:2007-02-10 发布日期:2007-02-10
  • 基金资助:
    山西省气象局开放基金(SX041001)

Neural Network Prediction Model of the Lowest Temperature Based on Principal Component Analysis

SUN Hong-ping1, 2, YAN Shi-ming3, LI Pei-ren2, WANG Yan3(1.Nanjing University of Information Science & Technology, Nanjing 210044, China; 2.Weather Modification Office of Shanxi Province; 3. Shanxi Meteorological Institute)   

  • Online:2007-02-10 Published:2007-02-10

摘要: 根据山西省6个有代表性的气象观测站1951-2000年的气象资料,以降水量、气温为预报因子,以太原市最冷月平均气温为预报量,采用人工神经网络与主分量分析相结合的方法,建立了太原最冷月平均气温预报模型。该模型对1960-1990年的历史样本拟合的平均相对误差为3.6%,对1991-2000年独立样本的预报准确率达90%,说明该模型可使预报泛化能力显著提高,对农业防灾减灾有较大作用。

关键词: 最冷月平均气温, 神经网络, 主分量分析方法, 预报

Abstract: Based on observed climatic data of precipitation and temperature from 6 meteorological stations in Shanxi province during 1951-2000, the prediction model of the lowest average monthly temperature in Taiyuan city was established with neural network technology and principal component analysis (PCA) method. According to this prediction model, the average relative error to the data series of 1960-1990 was 3.6%, and the prediction accuracy to 1991-2000 was 90%. The results indicated that the prediction model could improve prediction scale and precision significantly, and could take positive effect in reducing and preventing agricultural disasters.

Key words: The lowest average monthly temperature, The lowest average monthly temperature, Neural network, Principal component analysis, Prediction