基于雷达组网拼图和XGBoost的雷达定量降水估测  

Radar Quantitative Precipitation Estimation Based on Radar Mosaic and XGBoost Algorithm

作　　者：赵华生 李晓静[2] ZHAO Huasheng;LI Xiaojing(Guangxi Institute of Meteorological Sciences,Nanning 530006;Guangxi College for Preschool Education,Nanning 530006)

机构地区：[1]广西气象科学研究所,南宁530006 [2]广西幼儿师范高等专科学校,南宁530006

出　　处：《气象科技》2023年第3期338-345,共8页Meteorological Science and Technology

基　　金：广西高校中青年教师科研基础能力提升项目(2022KY0963);广西科技厅重点研发计划项目(桂科AB21196041);广西职业教育教学改革研究重点项目(GXGZJG2022A001)资助。

摘　　要：针对传统方法采用天气雷达进行强降水的定量估测存在较大偏差问题,论文以1 h累计雨量为估测对象,基于雷达组网拼图资料,采用XGBoost(eXtreme Gradient Boosting)算法,建立新的雷达估测降水模型。该模型设计以前1 h的雷达组合反射率因子作为输入,进一步采用若干个剔除异常样本的策略有效清除建模样本中的部分噪声,更好地构建了雷达组合反射率与估测对象之间的非线性映射关系。在32万个独立检验样本的估测结果中,其均方根误差(RMSE)为6.04 mm、平均绝对误差(MAE)为3.50 mm、预报偏差(BIAS)为1.05;与目前业务系统上使用的ZR(300,1.4)关系方法相比,前者的RMSE和MAE分别下降了20.6%和10.3%,而BIAS指标则显示后者对降水量级的估测明显低估。进一步对小时雨强大于10 mm样本的统计结果表明,新方案的RMSE、MAE以及TS评分均大幅优于ZR(300,1.4)关系方法,可进行实际业务应用。To address the problem of large bias in the quantitative estimation of heavy precipitation by traditional methods using weather radar,the thesis uses the 1-hour cumulative rainfall as the estimation object,a new model for radar precipitation estimation based on radar mosaic data and XGBoost(eXtreme Gradient Boosting)algorithm.The model is designed with the radar combined reflectance factor of the previous hour as the input factor,and further employs several rejection strategies of anomalous samples to effectively remove some of the noise from the modelling samples,thus better constructing a non-linear mapping relationship between the radar combined reflectance and the estimated object.The root mean square error(RMSE)is 6.04 mm,the mean absolute error(MAE)is 3.50 mm,and the forecast bias(BIAS)is 1.05 for the 320,000 independently tested samples;compared to the ZR(300,1.4)relational method currently used on operational systems,the RMSE and MAE of the former decrease by 20.6%and 10.3%respectively,while the BIAS indicators show a significant underestimation of precipitation magnitude by the latter.For samples with hourly rainfall intensity greater than 10 mm,further statistical results show that the new scheme's RMSE,MAE and TS scores are substantially better than the ZR(300,1.4)relational method for practical operational applications.

关 键 词：雷达降水估测 XGBoost 组合反射率 雷达拼图 

分 类 号：P415.2[天文地球—大气科学及气象学]