基于因果分析和機(jī)器學(xué)習(xí)算法的站點(diǎn)氣溫短臨預(yù)報(bào)試驗(yàn)

doi:10.12306/2023jms.0059

首頁(yè) > 過(guò)刊瀏覽>2025年第45卷第4期 >535-548. DOI:10.12306/2023jms.0059

基于因果分析和機(jī)器學(xué)習(xí)算法的站點(diǎn)氣溫短臨預(yù)報(bào)試驗(yàn)
DOI:
                        10.12306/2023jms.0059
                    
CSTR:
                        
                    
作者:
                        
                        
                    
作者單位:
作者簡(jiǎn)介:
通訊作者:
中圖分類號(hào):P732
基金項(xiàng)目:國(guó)家自然科學(xué)基金資助項(xiàng)目(62073332)

Experiments on short-term station temperature forecast based on causality analysis and machine learning algorithms

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:

本文構(gòu)建了一種基于因果分析和機(jī)器學(xué)習(xí)的站點(diǎn)氣溫短臨預(yù)報(bào)模型，以臺(tái)灣省松山站為試驗(yàn)對(duì)象，利用歐洲中期天氣預(yù)報(bào)中心(European Centre for Medium-Range Weather Forecasts， ECMWF)再分析資料、松山站實(shí)測(cè)氣象資料和中國(guó)氣象局陸面數(shù)據(jù)同化系統(tǒng)(Chinese Land Data Assimilation System-v2.0， CLDAS-v2.0)近實(shí)時(shí)產(chǎn)品資料，引入因果信息流理論，采用四種機(jī)器學(xué)習(xí)算法：多層前饋神經(jīng)網(wǎng)絡(luò)(Back Propagation Neural Network， BPNN)、隨機(jī)森林(Random Forest，RF)、最小二乘支持向量機(jī)(Least Square Support Vector Machine， LSSVM)和貝葉斯網(wǎng)絡(luò)(Bayesian Network， BN)，開(kāi)展氣溫短臨預(yù)報(bào)試驗(yàn)。結(jié)論如下：(1)在選取的任一種數(shù)據(jù)資料驅(qū)動(dòng)下，對(duì)于BPNN、RF、BN，基于因果分析的預(yù)報(bào)結(jié)果優(yōu)于相關(guān)分析，均方根誤差的平均降幅在1%～2%之間。對(duì)于LSSVM，因果分析與相關(guān)分析差別較小，驗(yàn)證了因果分析具備更優(yōu)的關(guān)聯(lián)關(guān)系挖掘能力；(2)在預(yù)報(bào)模型中增加相鄰空間預(yù)報(bào)因子能夠顯著提高氣溫預(yù)報(bào)效果，改進(jìn)后氣溫預(yù)報(bào)模型均方根誤差的平均降幅在2%～8%之間；(3)在模型訓(xùn)練樣本較少情況下，基于CLDAS-v2.0近實(shí)時(shí)產(chǎn)品資料的預(yù)報(bào)效果優(yōu)于ECMWF再分析資料的預(yù)報(bào)效果，均方根誤差的平均降幅在4%～8%之間，從側(cè)面驗(yàn)證了CLDAS-v2.0近實(shí)時(shí)產(chǎn)品資料在中國(guó)區(qū)域質(zhì)量?jī)?yōu)于國(guó)際同類產(chǎn)品。

Abstract:

This paper constructed a model for short term forecasting of station temperature based on causal analysis of information flow and machine learning algorithms， taking Songshan Station in Taiwan as the test samples， using ECMWF reanalysis data， measured meteorological data of Songshan Station and CLDAS-v2.0 near-real-time product data， combined with causal analysis and correlation analysis， using four Machine Learning (ML) algorithms: BP neural network， Random Forest (RF)， Least Squares Support Vector Machine (LSSVM) and Bayesian Network (BN) to carry out temperature short-term forecasting experiments.The conclusions are as follows: (1)driven by any of the data selected in this paper， for BP neural network， RF， and BN， the prediction results based on causal analysis are better than those of correlation analysis， and the average reduction of RMSE is between 1%-2%. For LSSVM， the difference between causal analysis and correlation analysis is small， which verifies that causal analysis has better correlation mining capabilities; (2) adding adjacent spatial prediction factors in the forecast model can improve the temperature prediction effect， and the average reduction of the RMSE of the improved temperature prediction model is between 2%-8%; (3) in the case of small samples， the forecasting effect based on CLDAS-V2.0 data is better than that of ECMWF reanalysis data， and the average reduction of RMSE is between 4%-8%， which verifies that the quality of CLDAS-V2.0 data in China is indeed better than that of similar international products.

參考文獻(xiàn)

相似文獻(xiàn)

引證文獻(xiàn)

引用本文

李洪臣,李明,王鵬皓.基于因果分析和機(jī)器學(xué)習(xí)算法的站點(diǎn)氣溫短臨預(yù)報(bào)試驗(yàn).氣象科學(xué),2025,45(4):535-548 LI Hongchen, LI Ming, WANG Penghao. Experiments on short-term station temperature forecast based on causality analysis and machine learning algorithms. Journal of the Meteorological Sciences,2025,45(4):535-548

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:2023-05-30
最后修改日期:2023-07-31
錄用日期:
在線發(fā)布日期: 2025-11-29
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

<sub id="vuwze"></sub>

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