基于BP神经网络气象数据质量控制方法研究  

Research on Meteorological Data Quality ControlMethod based on BP Neural Network

作　　者：黄胃建 杨笔锋[1] 卢会国[1] 魏春梅 HUANG Weijian;YANG Bifeng;LU Huiguo;WEI Chunmei(College of Electronic Engineering,Chengdu University of InformationTechnology,Chengdu 610225,China)

机构地区：[1]成都信息工程大学电子工程学院,四川成都610225

出　　处：《成都信息工程大学学报》2023年第4期392-397,共6页Journal of Chengdu University of Information Technology

基　　金：国家自然科学基金资助项目(42075129)。

摘　　要：气象观测数据的准确与否与天气、气候等预报的准确性有直接联系。气象观测数据质量控制主要是为了确保数据能具有代表性、准确性和比较性。对中国传统的质量控制算法做综述,提出存在的一些问题。在传统质量控制算法基础上,提出基于BP神经网络一致性检查的新质量控制算法,对气象观测数据实现了更精确的质量控制。The accuracy of meteorological observation data is directly related to the accuracy of weather and climate pre-diction.Meteorological observation data quality control is mainly to ensure that the data can be representative,accurate and comparative.This paper summarizes the traditional quality control algorithms in China and summarizes some existing problems.Based on the traditional quality control algorithm,a new quality control algorithm based on BP neural network consistency check is proposed,which realizes more accurate quality control of meteorological observation data on the ba-sis of the traditional quality control.

关 键 词：质量控制 一致性检查 BP神经网络 

分 类 号：P468.0[天文地球—大气科学及气象学]