基于机器学习的北京供暖季气温预报误差订正

doi:10.3969/j.issn.1673-503X.2025.01.007

摘要/Abstract

摘要： 基于2019年7月1日至2024年3月15日水平分辨率为0.1°×0.1°的ECMWF模式预报数据和北京20个国家级气象站观测数据,分析北京历史供暖季ECMWF模式对2 m气温预报的误差特征,利用极限随机森林、决策树、梯度提升树、线性回归、Lasso回归算法对ECMWF模式的2 m气温预报误差进行订正。结果表明:ECMWF模式对北京城区2019—2023年供暖季2 m气温预报整体偏低,最大偏差出现在下午,平均偏差为-2.3 ℃,郊区2 m气温预报早晨偏低,下午偏高,最大正偏差和负偏差出现在07:00和16:00,分别为1.7 ℃和-2.2 ℃。利用机器学习方法订正后,2023年供暖季(2023年11月7日至2024年3月15日)北京城区和郊区的平均偏差和均方根误差均有明显降低,其中极限随机森林算法的订正效果最优,城区和郊区均方根误差分别改善了24.2%和35.4%;2023年供暖季北京城区9个站日平均气温预报偏差在±0.5、±1、±2 ℃内的准确率均显著提升,最大分别提升31%、44%和40%,极限随机森林和决策树算法表现最佳。

关键词: 机器学习, 供暖季气温, ECMWF模式, 订正

Abstract: Based on the European Centre for meaium-Range Weather forecasts(ECMWF) model with a horizontal resolution of 0.1°×0.1° and the observation data from 20 national automatic weather sites in Beijing from July 1,2019 to March 15,2024,the characteristics of the model for 2 m temperature bias forecasted by ECMWF model during the historical heating season were analyzed.Extreme random forest,decision tree,gradient boosting tree,linear regression,and Lasso regression methods were used to correct the 2 m temperature forecasts from ECMWF model.The results show that the overall 2 m temperature forecast during the historical heating season in 2019-2023 in the urban area of Beijing by ECMWF is low,with the largest bias occurring in the afternoon and with the average bias of -2.3 ℃.While the 2 m temperature forecast in the suburban area is low in the morning and high in the afternoon,with the largest positive and negative bias occurring at 07:00 and 16:00,being 1.7 ℃ and -2.2 ℃,respectively.After the correction by machine learning method,the mean bias and root mean square error of urban and suburban sites in Beijing in the 2023 heating season (from November 7,2023 to March 15,2024) are significantly decreased,in which the correction effect of the extreme random forest is the best,and the improvement rates of root mean square error in the urban and suburban areas are 24.2% and 35.4%.After the correction by machine learning method,the accuracy of daily mean temperature forecast bias within ±0.5 ℃,±1.0 ℃ and ±2.0 ℃ at 9 sites in urban area of Beijing in the 2023 heating season is significantly improved,with the maximum improvement rates of 31%,44% and 40%,respectively,and the extreme random forest and decision tree have the best performance.

Key words: Machine learning, Heating season temperatures, ECMWF model, Correction

中图分类号:

P457.3

张艳晴, 金晨曦, 闵晶晶, 韩超, 董颜, 齐晨. 基于机器学习的北京供暖季气温预报误差订正[J]. 气象与环境学报, 2025, 41(1): 58-65.

ZHANG Yanqing, JIN Chenxi, MIN Jingjing, HAN Chao, DONG Yan, QI Chen. Bias correction of heating season temperature forecasts based on Machine Learning in Beijing[J]. Journal of Meteorology and Environment, 2025, 41(1): 58-65.

参考文献

[1] Cheng W Y Y,Steenburgh W J.Strengths and weaknesses of MOS,running-mean bias removal,and Kalman filter techniques for improving model forecasts over the western United States[J].Weather and Forecasting,2007,22(6):1304-1318.
[2] Rudack D E,Ghirardelli J E.A comparative verification of localized aviation model output statistics program (LAMP) and numerical weather prediction (NWP) model forecasts of ceiling height and visibility[J].Weather and Forecasting,2010,25(4):1161-1178.
[3] 王佳津,王彬雁,肖递祥,等.基于目标对象检验法的四川省两种数值模式暴雨预报对比分析[J].气象与环境学报,2023,39(6):44-50.
[4] 吴迪,田宏强,刘辉,等.基于相似卡尔曼滤波的安徽省WRF模式风速预报订正[J].气象与环境学报,2023,39(4):31-37.
[5] 金巍,刘卫华,高凌峰,等.辽宁地区ECMWF模式气温预报检验及误差订正研究[J].气象与环境学报,2020,36(6):50-57.
[6] 王涛,王乙舒,赵春雨,等.基于机器学习方法的辽宁省初霜冻日期预测模型研究[J].气象与环境学报,2022,38(4):47-56.
[7] Marzban C.Neural networks for postprocessing model output:ARPS[J].Monthly Weather Review,2003,131(6):1103-1111.
[8] Zjavka L.Numerical weather prediction revisions using the locally trained differential polynomial network[J].Expert Systems with Applications,2016,44:265-274.
[9] Yi C,Shin Y,Roh J W.Development of an urban high-resolution air temperature forecast system for local weather information services based on statistical downscaling[J].Atmosphere,2018,9(5):164.
[10] Shin Y,Yi C.Statistical downscaling of urban-scale air temperatures using an analog model output statistics technique[J].Atmosphere,2019,10(8):427.
[11] 谭江红,陈伟亮,王珊珊.一种机器学习方法在湖北定时气温预报中的应用试验[J].气象科技进展,2018,8(5):46-50.
[12] 门晓磊,焦瑞莉,王鼎,等.基于机器学习的华北气温多模式集合预报的订正方法[J].气候与环境研究,2019,24(1):116-124.
[13] 陈昱文,黄小猛,李熠,等.基于ECMWF产品的站点气温预报集成学习误差订正[J].应用气象学报,2020,31(4):494-503.
[14] 韩念霏,杨璐,陈明轩,等.京津冀站点风温湿要素的机器学习订正方法[J].应用气象学报,2022,33(4):489-500.
[15] Chen K R,Wang P,Yang X J,et al.A model output deep learning method for grid temperature forecasts in Tianjin area[J].Applied Sciences,2020,10(17):5808.
[16] 王莹,杨晓君,王迪,等.利用卷积神经网络提高天气短期气温预报效果[J].气象科学,2024,44(4):793-800.
[17] David Kreuzer,Michael Munz,Stephan Schlüter.Short-term temperature forecasts using a convolutional neural network:An application to different weather stations in Germany[J].Machine Learning with Applications,2020,2:100007.
[18] 潘留杰,薛春芳,王建鹏,等.一个简单的格点温度预报订正方法[J].气象,2017,43(12):1584-1593.
[19] 雷彦森,蔡晓军,王文,等.遗传算法优化的BP神经网络在地面温度多模式集成预报的应用研究[J].气象科学,2018,38(6):806-814.
[20] 郝翠,张迎新,王在文,等.最优集合预报订正方法在客观温度预报中的应用[J].气象,2019,45(8):1085-1092.
[21] 任萍,陈明轩,曹伟华,等.基于机器学习的复杂地形下短期数值天气预报误差分析与订正[J].气象学报,2020,78(6):1002-1020.
[22] Rodriguez-Galiano V,Sanchez-Castillo M,Chica-Olmo M,et al.Machine learning predictive models for mineral prospectivity:an evaluation of neural networks,random forest,regression trees and support vector machines[J].Ore Geology Reviews,2015,71:804-818.
[23] Geurts P,Ernst D,Wehenkel L.Extremely randomized trees[J].Machine Learning,2006,63(1):3-42.
[24] Nie P,Roccotelli M,Fanti M P,et al.Prediction of home energy consumption based on gradient boosting regression tree[J].Energy Reports,2021,7:1246-1255.
[25] Schneider A,Hommel G,Blettner M.Linear regression analysis:Part 14 of a series on evaluation of scientific publications[J].Deutsches Ärzteblatt International,2010,107(44):776-782.
[26] Tibshirani R.Regression shrinkage and selection via the lasso[J].Journal of the Royal Statistical Society.Series B (Methodological),1996,58(1):267-288.