计算机与现代化 ›› 2023, Vol. 0 ›› Issue (09): 38-43.doi: 10.3969/j.issn.1006-2475.2023.09.006

• 数据库与数据挖掘 • 上一篇    下一篇

基于集成学习的巢湖面雨量计算方法

  

  1. (1.安徽省农村综合经济信息中心,安徽 合肥 230031; 2.广东省清远市气象局,广东 清远 511515;
    3.安徽省公共气象服务中心,安徽 合肥 230031)
  • 出版日期:2023-09-28 发布日期:2023-10-10
  • 作者简介:王杰(1986—),男,安徽临泉人,工程师,硕士,研究方向:机器学习,农业气象新技术应用,E-mail: wangjie629_308@126.com; 徐祥(1989—),男,安徽安庆人,工程师,硕士,研究方向:大数据处理,E-mail: 337967650@qq.com; 罗晓丹(1978—),女,广东英德人,工程师,学士,研究方向:专业气象服务,E-mail: tender-april@126.com; 张萌(1993—),男,安徽肥西人,助理工程师,硕士,研究方向:气象数据处理,E-mail: 3103387872@qq.com; 黄澈(1992—),男,安徽怀宁人,助理工程师,硕士,研究方向:气象产品开发,E-mail: 274210008@qq.com; 洪冠中(1978—),男,广东清远人,工程师,学士,研究方向:专业气象服务,E-mail: honggz@126.com; 通信作者:汪翔(1985—),男,江苏宿迁人,高级工程师,硕士,研究方向:公共气象服务,E-mail: wxpc007@163.com。
  • 基金资助:
    安徽省自然科学基金资助项目(2208085UQ06); 科技助力经济2020重点专项(KJZLJJ202002)

Calculation Method of Chaohu Lake Surface Rainfall Based on Ensemble Learning

  1. (1. Anhui Rural Comprehensive Economic Information Center, Hefei 230031, China; 2. Qingyuan Meteorological Bureau of Guangdong Province, Qingyuan 511515, China; 3. Anhui Public Meteorological Service Center, Hefei 230031, China)
  • Online:2023-09-28 Published:2023-10-10

摘要: 针对湖面气象观测站部署困难导致降水观测资料不足以及传统数值模式面雨量计算复杂等问题,本文以巢湖为研究对象,利用巢湖流域内雷达三维拼图数据和气象观测站降水数据,制作模型数据集。构建基于集成学习的雷达降水估测(Quantitative Precipitation Estimation, QPE)模型,利用自制数据集对模型进行训练,并结合地理信息系统(GIS),将巢湖区域按经纬度网格划分并与雷达拼图在空间上进行叠加,根据QPE模型计算各网格点降雨量,对网格点降雨量求算术平均得到湖面面雨量。实验分析基于随机森林(Random Forest, RF)、XGBoost、LightGBM这3种集成学习的QPE模型性能,选取性能较优QPE模型并进行超参数调优;对比分析利用网格点平均法和气象陆面数据同化系统(CMA Land Data Assimilation System, CLDAS)得到的湖面面雨量结果。结果表明,使用RF算法的QPE模型性能较优,采用网格点平均法和CLDAS计算结果数值虽有差异,但总体趋势一致。该方法可用于巢湖面雨量的计算,为巢湖及其流域防汛抗洪提供重要参考。

关键词: 集成学习, 定量降水估测, 地理信息系统, 面雨量, 巢湖

Abstract: In view of the problems such as insufficient precipitation data due to the difficulties in deployment of the lake meteorological observation station and the complexity of rainfall calculation under the traditional numerical model, this paper takes Chaoahu Lake as the research object, and creates a model dataset using radar 3D mosaic data and precipitation data from meteorological observation station in the Chaohu Lake basin. Then a quantitative precipitation estimation (QPE) model based on ensemble learning is constructed, and the self-made data set is used to train the model. Combined with geographic information system (GIS), the Chaohu Lake basin is divided by latitude and longitude grid and superimposed on the radar mosaic spatially. The arithmetic mean of the rainfall at each grid point which is calculated by the QPE model is calculated to obtain the rainfall on the lake surface. In the study, the performance of the QPE model based on ensemble learning of random forest (RF), XGBoost and LightGBM algorithms is compared and analyzed, and the QPE model with better performance is selected to conduct hyperparameter tuning. And the results of lake surface rainfall obtained by grid averaging method and CMA land data assimilation system (CLDAS) are comparatively analyzed. The results show that the QPE model using RF algorithm has better performance, and the overall trend is consistent although there are differences in the results values calculated by the grid average method and CLDAS. In conclusion, this method could be used to calculate the surface rainfall of Chaohu Lake, and provides an important reference for flood prevention and control of Chaohu Lake and its watershed.

Key words: ensemble learning, quantitative precipitation estimation, GIS, areal rainfall, Chaohu Lake

中图分类号: