Meteorlogical outliers detection based on artificial intelligence

Abstract

To precisely evaluate the effect of artificial precipitation of Project Tianshui, anomaly data within the large dataset collected is supposed to be detected and dealt with reasonably, to enhance the analysis and prediction of the data. Using the data accumulated from 2008 to 2017 from Wushaoling Meteorological Station, and the data from May 2019 to October 2019 from the dedicated supervising network built for the project, taking temperature(0.1°C) and other meteorological data as example, anomaly dectection is conducted by the arithmetics Local Outlier Factor and Isolation Forest respectively. Consistency check is also conducted via the two arithmetics. The main outliers of the accumulated data for ten years are isolated outliers. LOF works pretty well, while Isolation Forest performs unsatisfying. The main outliers of the dedicated supervising network data are of a continuous outlier sequence. LOF can hardly detect the anomaly, while Isolation Forest precisely find out the outliers. Both arithmetics perform well on consistency check in space. The differences of LOF and Isolation Forest are compared. New ideas of using artificial intelligence arithmetics to detect meteorological outliers and pre-process the data are provided.