首页|期刊导航|气象与环境学报|基于机器学习的CMA-MESO模式气温预报订正方法研究

基于机器学习的CMA-MESO模式气温预报订正方法研究

张会陈军明王亚强马凤莲周煜卢宇坤刘通张良玉

气象与环境学报2025，Vol.41Issue(3)：18-28,11.

气象与环境学报2025，Vol.41Issue(3)：18-28,11.DOI:10.3969/j.issn.1673-503X.2025.03.003

基于机器学习的CMA-MESO模式气温预报订正方法研究

A study on the temperature forecast correction method of the CMA-MESO model based on machine learning

张会 ¹陈军明 ²王亚强 ²马凤莲 ³周煜 ³卢宇坤 ⁴刘通 ⁴张良玉⁵

作者信息

1. 中国气象局雄安大气边界层重点开放实验室,河北雄安新区 071700||中国气象科学研究院灾害天气科学与技术全国重点实验室,北京 100081||河北省气象与生态环境重点实验室,河北石家庄 050021||保定市生态气象智能监测与服务重点实验室,河北保定 071000||保定市气象局,河北保定 071000
2. 中国气象科学研究院灾害天气科学与技术全国重点实验室,北京 100081||雄安气象人工智能创新研究院,河北雄安新区 070001
3. 中国气象局雄安大气边界层重点开放实验室,河北雄安新区 071700||雄安新区气象局,河北雄安新区 071700
4. 保定市生态气象智能监测与服务重点实验室,河北保定 071000||保定市气象局,河北保定 071000
5. 保定市气象局,河北保定 071000
折叠

摘要

Abstract

To improve the accuracy of temperature forecasts in Xiong'an New Area and the upstream Baoding re-gion,this study utilizes forecast products from the CMA-MESO mesoscale weather model and surface observation data.Three machine learning methods-Linear Regression,Long Short-Term Memory Fully Convolutional Network(LSTM-FCN),and Light Gradient Boosting Machine(LightGBM)are applied.Four forecast correction schemes are designed,focusing on station classification and feature selection.The results show that models using regionally divided stations outperform those using all stations collectively,and LightGBM delivers the best performance a-mong all schemes.Specifically,when composite feature factors are constructed by combining observed data from 48 hours prior to the forecast start time and forecast or observed variables from 4·k hours before the forecast time(within the 0-36 h lead time:for lead times 0-12 h,actual observations from the 0-12 h period before the forecast time are used,with k ranging from 0-12;for lead times 13-36 h,forecast data from 12 h before the forecast time are used,with k fixed at 12),the predictive performance of LightGBM is further improved.For all 37 forecast lead times,the accuracy is improved over the original CMA-MESO model forecasts.Particularly in plateau regions with elevations above 1000 meters,the RMSE improvement exceeds 30％.Moreover,these methods continue to demon-strate strong adaptability under transitional weather conditions.In terms of overall forecasting performance,LightG-BM proves to be the best,achieving a root mean square error(RMSE)of 1.86℃,a mean absolute error(MAE)of 1.42℃,and an accuracy of 75％,representing improvements of 36.5％,38.9％,and 44.4％respectively com-pared to the CMA-MESO forecast.

关键词

CMA-MESO/预报订正/机器学习/气温预报

Key words

CMA-MESO/Forecast correction/Machine Learning/Temperature forecast

分类

天文与地球科学

引用本文复制引用

张会,陈军明,王亚强,马凤莲,周煜,卢宇坤,刘通,张良玉..基于机器学习的CMA-MESO模式气温预报订正方法研究[J].气象与环境学报,2025,41(3):18-28,11.

基金项目

中国气象局能力提升联合研究专项(24NLTSZD01)和河北省保定市科技局(2211ZG001)共同资助. （24NLTSZD01）

气象与环境学报

ISSN：1673-503X

访问量0

下载量0

段落导航