气象与环境学报2026，Vol.42Issue(1)：95-102,8.DOI:10.3969/j.issn.1673-503X.2026.01.010
一种堆叠OCF算法在气温订正中的应用研究
A study on the application of a stacked OCF ensemble method for temperature correction
摘要
Abstract
This study proposes an improved stacked optimal screening machine learning model(REGOCF)to en-hance the accuracy and stability of temperature prediction.The model integrates multiple factors within the study region,including terrain characteristics,underlying surface types,and forecaster experience,thereby reducing uncer-tainties arising from multi-model discrepancies.A comparative verification was conducted using nearly one year of forecast data from REGOCF,the China Meteorological Administration′s Urban Guidance Forecast,ECMWF Thin,the National Intelligent Grid,and the Inner Mongolia Autonomous Region′s RAP(Rapid Refresh)regional numer-ical model.The verification results demonstrate that the REGOCF algorithm exhibits superior performance in fore-casting both maximum and minimum temperatures.Compared with single-model forecasts,the average accuracy improved by 5%-10%,with a marked reduction in forecast errors and a significant decrease in number of outliers,which is highly practical.Additionally,this study assessed the performance of the REGOCF algorithm across differ-ent seasons and climatic conditions,further corroborating its robustness and adaptability.This research not only pro-vides an innovative approach to temperature correction but also provides a reference for the forecasting of other meteorological elements.关键词
REGOCF/气温集成预报/内蒙古/订正/检验Key words
REGOCF/Ensemble temperature forecast/Inner Mongolia/Correction/Verification分类
天文与地球科学引用本文复制引用
哈斯塔木嘎,格日乐,孙岳飞,范嘉承,楚健坤..一种堆叠OCF算法在气温订正中的应用研究[J].气象与环境学报,2026,42(1):95-102,8.基金项目
内蒙古自治区气象局科技创新重点项目(nmqxkjcx202525)、中国气象局复盘总结专项(FPZJ2025－023)、内蒙古自治区2023年度草原英才创新人才基金、内蒙古自治区气象局"揭榜挂帅"科技项目(nmqxjbgs202307)、中国气象局创新发展专项(CXFZ2021Z034)和锡林郭勒盟气象局科研项目(xmqxjkyxm202002)共同资助. （nmqxkjcx202525）
