U-Net模型在京津冀臨近降水預(yù)報(bào)中的應(yīng)用和檢驗(yàn)評(píng)估

doi:10.12306/2022jms.0078

首頁(yè) > 過(guò)刊瀏覽>2022年第42卷第6期 >781-792. DOI:10.12306/2022jms.0078

U-Net模型在京津冀臨近降水預(yù)報(bào)中的應(yīng)用和檢驗(yàn)評(píng)估
DOI:
                        10.12306/2022jms.0078
                    
CSTR:
                        
                    
作者:
                        
                        
                    
作者單位:
作者簡(jiǎn)介:
通訊作者:
中圖分類(lèi)號(hào):P456
基金項(xiàng)目:國(guó)家重點(diǎn)研發(fā)計(jì)劃項(xiàng)目(2021YFC3000903);風(fēng)云衛(wèi)星應(yīng)用先行計(jì)劃(2022)FY-APP-2022.0113

Application and test evaluation of U-Net model in Beijing-Tianjin-Hebei precipitation nowcasting

Author:

Affiliation:

Fund Project:

摘要

圖/表

訪問(wèn)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(píng)論

摘要:

利用2018—2019年期間10 min定量降水估計(jì)(Quantitative Precipitation Estimation, QPE)實(shí)況觀測(cè),構(gòu)建基于U-Net的分鐘級(jí)臨近降水預(yù)報(bào)模型,實(shí)現(xiàn)了京津冀地區(qū)未來(lái)0~2 h逐10 min降水量滾動(dòng)預(yù)報(bào)。以TS、BIAS、POD、SR、FAR作為評(píng)價(jià)指標(biāo),通過(guò)檢驗(yàn)2020和2021年6—9月長(zhǎng)序列以及分析2020年8月12日和2021年7月1日兩次強(qiáng)降水個(gè)例,表明U-Net模型預(yù)報(bào)接近實(shí)況,局部伴隨著一定程度的空?qǐng)?bào),相較光流法、持續(xù)性預(yù)報(bào)及CMA-MESO模式預(yù)報(bào)效果有明顯提升。具體表現(xiàn)為:當(dāng)分鐘級(jí)降水預(yù)報(bào)不超過(guò)10 mm/(10 min)時(shí),U-Net模型明顯優(yōu)于光流法和持續(xù)性預(yù)報(bào);當(dāng)小時(shí)預(yù)報(bào)不超過(guò)25 mm·h^-1,U-Net模型優(yōu)于CMA-MESO模式和光流法。然而,當(dāng)降水強(qiáng)度超過(guò)10 mm/(10 min)或 25 mm·h^-1時(shí),U-Net模型存在預(yù)報(bào)偏弱的情況,可能與強(qiáng)降水樣本較少有關(guān)。

Abstract:

In order to strengthen the application of deep learning in precipitation nowcasting over the Beijing-Tianjin-Hebei region, the 10-minute QPE observation during 2018-2019 was used to construct a minute-level precipitation nowcasting model based on U-Net,which realizes 10-minute rolling precipitation forecast in the future 0-2 hours. By verifying the long series from June to September in 2020 and 2021 and analyzing two cases of heavy precipitation on both August 12, 2020 and July 1, 2021 based on evaluation indicators such as TS, BIAS, POD, SR and FAR, results show that the prediction of U-Net model is close to observation accompanied by false alarms to some extent and its forecasting effect is significantly improved compared with the optical flow method, persistent forecast and CMA-MESO model. Specific performance as follows: when the minute-level precipitation forecast does not exceed 10 mm/(10 min), the U-Net model is significantly better than the optical flow method and persistence forecast; when the hourly forecast does not exceed 25 mm·h^-1, the U-Net model is significantly better than the CMA-MESO model and the optical flow method. However, when the precipitation intensity exceeds 10 mm/(10 min) or 25 mm·h^-1, U-Net has a weak forecast, which may be related to fewer samples of heavy precipitation.

參考文獻(xiàn)

相似文獻(xiàn)

引證文獻(xiàn)

引用本文

徐成鵬,曹勇,張恒德,劉海知,梅雙麗. U-Net模型在京津冀臨近降水預(yù)報(bào)中的應(yīng)用和檢驗(yàn)評(píng)估.氣象科學(xué),2022,42(6):781-792 XU Chengpeng, CAO Yong, ZHANG Hengde, LIU Haizhi, MEI Shuangli. Application and test evaluation of U-Net model in Beijing-Tianjin-Hebei precipitation nowcasting. Journal of the Meteorological Sciences,2022,42(6):781-792

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:2022-06-02
最后修改日期:2022-06-27
錄用日期:
在線發(fā)布日期: 2023-03-03
出版日期:

文章二維碼

您是第位訪問(wèn)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

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