ISSN 1000-0526
CN 11-2282/P
CN 11-2282/P
A METHOD FOR DETECTING ABNORMAL WIND DIRECTION OF AUTOMATIC WEATHER STATIONS BASED ON MACHINE LEARNING
- Article
- Figures
- Metrics
- Preview PDF
- Reference
- Related
- Cited by
- Materials
Abstract:
To address the issue of high-concealed abnormal wind directions in automatic weather station (AWS) data，this study establish an abnormal wind direction identification method based on the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering algorithm. Historical wind direction data from 16 weather events affecting Guangzhou between 2016 and 2022, including cold waves, cold air masses, and typhoons, as well as real-time wind direction data from AWSs during the impact of Typhoon Sura (No. 2309), were used to detect abnormal wind directions. The analysis results reveal that the proportion of AWSs with suspicious wind directions in historical cases ranges from 0.46% to 5.56%, while the proportion of AWSs with erroneous wind directions ranges from 0.25% to 2.05%.During the real-time case of Typhoon Sura,the method identified 13 AWSs with significantly deviating wind directions from the dominant ground wind direction, primarily due to wind direction sensor malfunctions and environmental impacts on AWS observations. Compared to the traditional method, the accuracy of wind direction error identification has improved by 20.32%.The new method provides a novel approach for the quality control of historical wind direction data from AWSs and offers an effective reference for the operational monitoring and on-site verification of AWS equipment.
Keywords:
Project Supported:
Clc Number:
Mobile website
