基于Catboost和Stacking融合模型的 長江中下游短時臨近降水預(yù)報研究

doi:10.12306/2021jms.0067

首頁 > 過刊瀏覽>2022年第42卷第5期 >569-580. DOI:10.12306/2021jms.0067

基于Catboost和Stacking融合模型的 長江中下游短時臨近降水預(yù)報研究
DOI:
                        10.12306/2021jms.0067
                    
CSTR:
                        
                    
作者:
                        
                        
                    
作者單位:
作者簡介:
通訊作者:
中圖分類號:P456.7
基金項目:國家自然科學(xué)基金資助項目(42075148);江蘇省"六大人才高峰"計劃資助項目(RJFW-016);江蘇省大學(xué)生創(chuàng)新創(chuàng)業(yè)訓(xùn)練計劃項目(201910300024Z)

Short-range forecast of precipitation over the middle-lower reaches of the Yangtze River based on the Catboost and Stacking model

Author:

Affiliation:

Fund Project:

摘要

圖/表

訪問統(tǒng)計

參考文獻

相似文獻

引證文獻

資源附件

文章評論

摘要:

用中國自動站與CMORPH降水產(chǎn)品融合的逐小時降水量網(wǎng)格數(shù)據(jù)集、全球預(yù)報系統(tǒng)(Global Forecasting System, GFS)模式再分析資料,將機器學(xué)習(xí)特征算法篩選的特征變量作為模型輸入數(shù)據(jù),運用Catboost模型和以Catboost和隨機森林為初級模型、徑向基神經(jīng)網(wǎng)絡(luò)為次級模型的融合模型預(yù)測未來6 h累計降水等級,并應(yīng)用公平TS評分(Equal Threat Score,ETS)、真實技巧評分(True Skill Statistic,TSS)、混淆矩陣、預(yù)報偏差(Bias值)、擊中率(Probability of Detection,POD)對預(yù)報結(jié)果進行檢驗分析。結(jié)果表明:優(yōu)化變量的輸入有利于提高模型的準(zhǔn)確率;Catboost模型和融合模型都可以在一定程度上辨別晴雨狀況;僅非動力學(xué)變量參與的融合模型對雨區(qū)預(yù)報準(zhǔn)確率最高,但容易將暴雨雨區(qū)預(yù)報得更加廣泛?？傮w而言,融合模型具有更強、更穩(wěn)定的預(yù)報性能,中到暴雨量級預(yù)報準(zhǔn)確率還待進一步提高。

Abstract:

The Catboost model and the Stacking model which has Catboost and Random Forest(RF) as the primary predictive model, a secondary predictive model was developed using Radial Basis Function(RBF) to predict 6 h accumulated precipitation-grade over the middle-lower reaches of the Yangtze River based on data from the hourly precipitation data merged by China Automatic Weather Station(CAWS) and CMORPH precipitation products and the Global Forecasting System(GFS) reanalysis. Comprehensively considering ETS score, TSS score, confusion matrix, Bias and POD (Probability of Destection) were analyzed the precipitation-grade forecast ability of two models. The results showed that: optimized the input variables is beneficial to improve the accuracy of the models; both the Catboost model and the Stacking model can distinguish clear and rainy conditions to a certain extent; the Stacking model with only non-dynamic variables has the highest prediction accuracy for the rain areas, but it can overly predict the heavy rain areas more widely. Above all, the Stacking model has stronger and more stable forecasting performance, however the prediction accuracy of moderate to heavy rainfall needs to be further improved.

參考文獻

相似文獻

引證文獻

引用本文

宋慧娟,陳耀登,歐陽霖,陳海琴,高哲凡,孫濤.基于Catboost和Stacking融合模型的長江中下游短時臨近降水預(yù)報研究.氣象科學(xué),2022,42(5):569-580 SONG Huijuan, CHEN Yaodeng, OUYANG Lin, CHEN Haiqin, GAO Zhefan, SUN Tao. Short-range forecast of precipitation over the middle-lower reaches of the Yangtze River based on the Catboost and Stacking model. Journal of the Meteorological Sciences,2022,42(5):569-580

復(fù)制

文章指標(biāo)

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

歷史

收稿日期:2021-01-18
最后修改日期:2021-07-27
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

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