基于機(jī)器學(xué)習(xí)的冰雹天氣識別研究

doi:10.12306/2021jms.0106

首頁 > 過刊瀏覽>2022年第42卷第5期 >581-590. DOI:10.12306/2021jms.0106

基于機(jī)器學(xué)習(xí)的冰雹天氣識別研究
DOI:
                        10.12306/2021jms.0106
                    
CSTR:
                        
                    
作者:
                        
                        
                    
作者單位:
作者簡介:
通訊作者:
中圖分類號:S427;P412.25
基金項(xiàng)目:國家重點(diǎn)研發(fā)計(jì)劃資助項(xiàng)目(2018YFC1506103);成都信息工程大學(xué)大學(xué)生創(chuàng)新創(chuàng)業(yè)訓(xùn)練計(jì)劃項(xiàng)目(202010621032)

Hail identification based on machine learning methods

Author:

Affiliation:

Fund Project:

摘要

圖/表

訪問統(tǒng)計(jì)

參考文獻(xiàn)

相似文獻(xiàn)

引證文獻(xiàn)

資源附件

文章評論

摘要:

利用2017—2019年貴州省威寧彝族回族苗族自治縣的C波段天氣雷達(dá)數(shù)據(jù),提取了多種與冰雹相關(guān)的雷達(dá)特征參量,并結(jié)合地面降雹記錄建立了客觀的冰雹樣本標(biāo)記方法。通過支持向量機(jī)、決策樹和樸素貝葉斯三種機(jī)器學(xué)習(xí)方法,對冰雹高發(fā)區(qū)貴州省威寧的冰雹天氣過程進(jìn)行建模與評估。評估結(jié)果表明,采用機(jī)器學(xué)習(xí)方法可以有效地識別冰雹天氣過程。支持向量機(jī)和決策樹方法的命中率(Probability of Detection, POD)均較高,分別為88.9%和90.5%;臨界成功指數(shù)(Critical Success Index, CSI)分別為73.1%和70.3%;誤報(bào)率(False Alarm Rate, FAR)分別為19.6%和24.1%。樸素貝葉斯方法的POD和CSI相對偏低,分別為67.8%、62.8%,但FAR最低,為10.6%。

Abstract:

Three machine learning methods, namely support vector machine, decision tree and Naive Bayesian, were applied to model and predict hail events occurred in Weining, Guizhou Province from 2017 to 2019. A variety of hail-related features were extracted from the C-band weather radar and an improved objective hail sample labelling procedure was proposed. The verification results showed that the machine learning methods were able to effectively identify the hail events. Both the support vector machine and decision tree methods had a high POD of 88.9% and 90.5% respectively, CSI of 73.1% and 70.3%, and FAR of 19.6% and 24.1% respectively. The POD and CSI of Naive Bayesian method were lower than the other two methods at 67.8% and 62.8% respectively, but its FAR was the lowest at 10.6%.

參考文獻(xiàn)

相似文獻(xiàn)

引證文獻(xiàn)

引用本文

李冰村,唐曉文,何建新,唐佳佳,李星澤,申楓.基于機(jī)器學(xué)習(xí)的冰雹天氣識別研究.氣象科學(xué),2022,42(5):581-590 LI Bingcun, TANG Xiaowen, HE Jianxin, TANG Jiajia, LI Xingze, SHEN Feng. Hail identification based on machine learning methods. Journal of the Meteorological Sciences,2022,42(5):581-590

復(fù)制

文章指標(biāo)

點(diǎn)擊次數(shù):
下載次數(shù):
HTML閱讀次數(shù):
引用次數(shù):

歷史

收稿日期:2021-09-28
最后修改日期:2021-12-14
錄用日期:
在線發(fā)布日期: 2022-11-03
出版日期:

文章二維碼

您是第位訪問者
氣象科學(xué) ® 2026 版權(quán)所有
技術(shù)支持：北京勤云科技發(fā)展有限公司

<dfn id="cko0u"></dfn>

<small id="cko0u"></small>

<abbr id="cko0u"></abbr>

抽查舔水白紧大视频,冲喜娘子超甜哒激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说

引用本文

分享

相關(guān)視頻

文章指標(biāo)

歷史

文章二維碼

抽查舔水白紧大视频,冲喜娘子超甜哒 激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说

引用本文

分享

相關(guān)視頻

文章指標(biāo)

歷史

文章二維碼

抽查舔水白紧大视频,冲喜娘子超甜哒激情五月,亚洲黄色图片偷拍网站,亚洲三级黄片免费播放,91在线观看喷潮红桃,日韩精品在线观看一区二区,久久久久久久久久久久黄色片子,日产精品99久久久久久久久,欧洲亚洲另类图片小说