基于粒子群优化-BP神经网络-马尔科夫链的地面能见度观测资料质量控制

自动气象站能见度检测仪多采用光学装置采样,一些雨雪、粉尘等天气因素可能对部分仪器造成镜头污染,导致能见度要素的观测数据不准确。本文针对能见度数据出错率高的问题,通过粒子群算法、BP神经网络,结合马尔科夫链,对地面能见度观测资料进行质量控制。为检验该方法的适用性,本文首先将安徽省不同区域站点的历史能见度数据加入人工误差,然后运用该方法对处理后的数据进行检错率分析。实验结果表明,该方法可以有效地标记出地面能见度观测资料中的存疑数据,具有检错率高、地区和气候适应性强等优点。

PSO-BP-MC Neural Network Based Quality Control for Surface Visibility Data

Most automatic weather stations use optical devices to sample visibility. There are two problems with this. One problem is inaccurate sample date caused by weather factors such as rain, snow or dust due to which the lens of those optimal devices might be soiled, and thus the collected data are usually not accurate. Another problem is data missing due to aging equipment, equipment maintenance, etc. To get rid of those wrong sample and provide complete data for meteorological prediction, this paper proposes a PSO-BP-MC neural network based data quality control method for weather visibility according to those historical data collected from the Anhui Meteorological Bureau. In order to test the applicability of this method, the error detection rate of the ground visibility observation data is analyzed with artificial errors added at different sites in Anhui province. The experimental results show that this method can effectively mark the doubtful data in the ground visibility data, and has the advantages of high detection rate and strong regional and climate adaptability.