摘要
根据2003年11月—2005年10月西藏自治区32个站点的气象资料,采用动态学习率BP算法的人工神经网络建模,在ECWMF、T213等模式数值预报产品释用基础上,进行1-7天逐日最高、最低温度模拟预测。模型业务试用结果表明,该神经网络模型具有较强的自适应学习和非线性映射能力,其预报结果能够满足实时预报的精度要求,对西藏中、短期极端温度的实时业务预报具有较好的参考价值。
According to the meteorological data of 32 stations in Tibet from November 2003 to October 2005,based on the interpretation of numerical forecasting products of ECWMF,T213 and so on,an artificial neural network model is constructed with dynamic learning rate BP algorithm to forecast daily maximum/minimum temperature from one day to seven days.The results show that the neural network model has preferable adaptive learning and non-linear mapping abilities and its forecast results can satisfy the precision requirement for real-time forecast,which has good referenced value in short and mid-range real-time operational forecast of extreme temperature.
出处
《高原气象》
CSCD
北大核心
2007年第3期491-495,共5页
Plateau Meteorology
基金
中国气象局2005年气象新技术推广项目"精细化大气要素中短期客观预报业务系统开发"(CMATG2005M07)资助
关键词
神经网络
BP算法
最高温度
最低温度
数值预报产品释用
Neural network
BP algorithm
Maximum temperature
Minimum temperature
Interpretation of numerical forecasting products
