A quality control method for real-time data of automatic weather stations based on psr-fastica-os_elm

Abstract

The invention discloses a real-time data quality control method of an automatic weather station based on PSR-FastICA-OS_ELM. In the method, firstly, a single-station real-time temperature and a fixed-length historical temperature sequence are collected to form a collection signal; Quality control; then phase space reconstruction; and fast independent component analysis of the reconstructed high-dimensional vector space signal to achieve the purpose of denoising and de-redundancy, and obtain the unbiased signal of the source signal in the high-dimensional vector space; Finally, the reconstruction model of the time series acquisition signal is constructed by the online sequential extreme learning machine to obtain the reconstruction value of the temperature after denoising; and the conditions are corrected according to the comparison between the denoising reconstruction value and the actual observation value, and the quality of the temperature at this time is completed. control. This method meets the requirements of real-time data collection and improves the quality of real-time automatic weather station observation data.

Description

technical field [0001] The invention relates to the field of quality control of observation data of automatic weather stations, and in particular invents a quality control method for real-time collection of temperature data by automatic weather stations. Background technique [0002] Since the late 1990s, my country has deployed ground automatic meteorological observation systems at some stations. By 2011, more than 2,500 ground automatic weather stations across the country have been applied to meteorological observation services. Automatic weather stations have the characteristics of dense station distribution, large terrain differences, harsh station environment, high degree of automation in data collection and transmission, strong real-time data, and obvious small and medium-scale weather phenomena. The data appear to be more complex and serious, so it is necessary to carry out quality control on the observation data of automatic weather stations. my country conducts two...

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a kind of automatic weather station real-time data quality control method based on PSR-FastICA-OS_ELM, has solved the problem that current quality control method can't eliminate random noise, system noise, micrometeorological noise, has improved automatic weather station real-time data quality control method. Quality of Observational Data

Images