摘要
选取国家气象信息中心多源融合降水产品、四川省智能网格气象预报产品、德阳市实况降水观测资料以及欧洲中心数值预报资料,应用前馈式神经网络及最优逼近方法对德阳市降雨预报系统进行训练,并利用多源融合降水资料对预报结果进行检验。结果表明:改进后的系统不仅能对输入层因子的降水及其落区预报进行有效的智能优化,还使得暴雨天气过程中强降水中心分布和极端降水量的预报结果更加接近实况,总之可为预报员开展本地降水预报业务提供有益的参考。
Based on the feedforward neural network(FNN)and the method of optimal approximation,the forecasting system for rainfall in Deyang City is trained with refinement intelligent grid forecasting,real-time rainfall monitoring data,ECMWF numerical forecasting data and CMPA Precipitation data.The forecasting results are verified and assessed with CMPA Precipitation data.The results show that the improved system can not only effectively intelligently optimize the precipitation of input layer factors and the forecast of its falling area,but also make the forecast results of the distribution of heavy precipitation centers and extreme precipitation in the process of rainstorm weather more close to the reality.Therefore,it can provide useful reference for local precipitation forecast.
作者
雍星
陈佳
赖维肖
陈丹妮
YONG Xing;CHEN Jia;LAI Weixiao;CHEN Danni(Deyang Meteorological Service,Deyang 618000,China)
出处
《高原山地气象研究》
2022年第2期69-74,共6页
Plateau and Mountain Meteorology Research
基金
德阳市科技计划项目(2019SZ065)。
关键词
前馈式神经网络
智能网格预报
多源融合
精细化降水预报
Feedforward neural network
Intelligent grid forecasting
Integration
Refinement rainfall forecast
作者简介
雍星,工程师,主要从事中短期天气预报研究。E-mail:418902072@qq.com;通讯作者:陈佳,工程师,主要从事中短期天气预报研究。E-mail:467427504@qq.com。
