A Feasible Method for Categorizing Weather Patterns Using K-Means Clustering Based on Coherent Doppler Wind Lidar

This study presents a method for categorizing weather patterns using K-Means Clustering, utilizing signal-to-noise ratio (SNR) data obtained from Coherent Doppler Wind Lidar. By integrating atmospheric parameters from meteorological stations and wind radar, the weather patterns are classified into f...

Full description

Saved in:
Bibliographic Details
Published inInternational Conference on Systems and Informatics pp. 1 - 5
Main Authors Chen, Yehui, Jin, Xiaomei, Liu, Ying, Weng, Ningquan, Zhu, Wenyue, Liu, Qing
Format Conference Proceeding
LanguageEnglish
Published IEEE 14.12.2024
Subjects
Atmospheric Pollution
Clouds
Coherent Doppler Wind Lidar
Doppler effect
K-Means Clustering
Laser radar
Meteorological Data Analysis
Meteorological radar
Meteorology
Pattern recognition
Reliability
Signal to noise ratio
Weather forecasting
Weather Pattern Recognition
Wind
Online AccessGet full text
ISSN2689-7148
DOI10.1109/ICSAI65059.2024.10893755

Cover

More Information
Summary:This study presents a method for categorizing weather patterns using K-Means Clustering, utilizing signal-to-noise ratio (SNR) data obtained from Coherent Doppler Wind Lidar. By integrating atmospheric parameters from meteorological stations and wind radar, the weather patterns are classified into five categories: clear, rainy, few clouds, moderate clouds, and cloudy. The K-Means Clustering analysis showed a 93% consistency with meteorological data from the China Meteorological Information Center by using hourly SNR data from December 2019 to April 2020. This approach offers a simple, effective tool for weather pattern recognition, essential for climate change studies, weather forecasting, and air pollution assessment.
ISSN:2689-7148
DOI:10.1109/ICSAI65059.2024.10893755