基于極端梯度提升算法的重慶市暴雨災(zāi)害風(fēng)險(xiǎn)評(píng)估

doi:10.12306/2024jms.0020

首頁 > 過刊瀏覽>2024年第44卷第6期 >1140-1153. DOI:10.12306/2024jms.0020

基于極端梯度提升算法的重慶市暴雨災(zāi)害風(fēng)險(xiǎn)評(píng)估
DOI:
                        10.12306/2024jms.0020
                    
CSTR:
                        
                    
作者:
                        
                        
                    
作者單位:
作者簡(jiǎn)介:
通訊作者:
中圖分類號(hào):P426.616;TP181
基金項(xiàng)目:基于機(jī)器學(xué)習(xí)方法的重慶暴雨災(zāi)害風(fēng)險(xiǎn)評(píng)估技術(shù)研究(YWJSGG-202413);高分專項(xiàng)航空觀測(cè)系統(tǒng)科研項(xiàng)目外協(xié)子課題

Risk assessment of rainstorm disaster in Chongqing based on eXtreme Gradient Boosting algorithm

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(píng)論

摘要:

因其獨(dú)特的地理位置與氣候,重慶市暴雨災(zāi)害頻發(fā),對(duì)其開展暴雨災(zāi)害風(fēng)險(xiǎn)評(píng)估與區(qū)劃十分必要。本文利用暴雨過程強(qiáng)度影響因素、孕災(zāi)環(huán)境影響因素與承災(zāi)體暴露度等數(shù)據(jù),結(jié)合專家打分得到的指標(biāo)權(quán)重獲得致災(zāi)危險(xiǎn)性與承災(zāi)體受災(zāi)風(fēng)險(xiǎn)性指數(shù),以此構(gòu)建樣本集?；陔S機(jī)森林(Random Forest, RF)、自適應(yīng)提升(Adaptive Boosting, AdaBoost)、極端梯度提升(eXtreme Gradient Boosting, XGBoost)、梯度提升回歸(Gradient Boosting Regression, GBR)、支持向量回歸(Support Vector Regression, SVR)、線性回歸(Linear Regression, LR)算法分別進(jìn)行預(yù)測(cè)。結(jié)果顯示,XGBoost算法以最低的平均相對(duì)誤差值(Mean Relative Error,MRE)1.950%、均方根誤差值(Root Mean Square Error,RMSE)0.028,以及最高的相關(guān)性值(R-squared,R²)0.896,成為最優(yōu)算法(以暴雨致災(zāi)危險(xiǎn)性預(yù)測(cè)結(jié)果為例)。在單場(chǎng)暴雨災(zāi)害風(fēng)險(xiǎn)評(píng)估中,在缺少暴雨過程持續(xù)天數(shù)數(shù)據(jù)的情況下,XGBoost算法仍為最優(yōu)算法,其預(yù)測(cè)的MRE值與RMSE值分別為2.066%、0.030,R²值為0.885,利用XGBoost算法在評(píng)估區(qū)劃中劃分的各等級(jí)受災(zāi)風(fēng)險(xiǎn)區(qū)域與實(shí)際受災(zāi)區(qū)域基本保持一致,表明XGBoost算法在缺少部分?jǐn)?shù)據(jù)的情況下,仍能高效準(zhǔn)確地進(jìn)行評(píng)估。

Abstract:

Rainstorm disaster is one of the frequent natural disasters in China. Chongqing has suffered heavy losses due to its unique geographical location and climate. Risk assessment and zoning of rainstorm disaster can effectively prevent and control it. This paper uses the data of rainstorm process intensity influencing factors, disaster-inducing environmental influencing factors and exposure degree of disaster-affected bodies, combines the index weights obtained by expert scoring to obtain the disaster-causing risk and disaster-affected risk index of disaster-affected bodies, so as to construct the sample set. Random Forest (RF), Adaptive Boosting (AdaBoost), eXtreme Gradient Boosting (XGBoost), Gradient Boosting Regression (GBR), Support Vector Regression (SVR) and Linear Regression (LR) are used to predict respectively. Finally, the XGBoost algorithm with the lowest mean relative error (MRE) 1.950%,root mean square error (RMSE) 0.028, and the highest correlation(R-squared, R²) 0.896 becomes the optimal algorithm (taking the prediction results of rainstorm disaster risk as an example). In the risk assessment of single rainstorm disaster, the XGBoost algorithm is still the optimal algorithm in the absence of continuous days data of rainstorm process. The MRE and RMSE of the prediction results are 2.066% and 0.030, and the R² is 0.885. The disaster risk areas of each grade divided by XGBoost algorithm in the evaluation zoning are basically consistent with the actual disaster areas, indicating that the XGBoost algorithm can still be evaluated efficiently and accurately in the absence of some data.

參考文獻(xiàn)

相似文獻(xiàn)

引證文獻(xiàn)

引用本文

謝濤,余亮,周浩,秦文思.基于極端梯度提升算法的重慶市暴雨災(zāi)害風(fēng)險(xiǎn)評(píng)估.氣象科學(xué),2024,44(6):1140-1153 XIE Tao, YU Liang, ZHOU Hao, QIN Wensi. Risk assessment of rainstorm disaster in Chongqing based on eXtreme Gradient Boosting algorithm. Journal of the Meteorological Sciences,2024,44(6):1140-1153

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:2024-01-17
最后修改日期:2024-02-18
錄用日期:
在線發(fā)布日期: 2025-01-08
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