南京信息工程大学学报2026，Vol.18Issue(3)：331-339,9.DOI:10.13878/j.cnki.jnuist.20220915004
基于ConvLSTM及双重注意力机制的2m气温预报订正方法
A 2m temperature forecast correction method based on ConvLSTM and dual attention mechanism
摘要
Abstract
In order to reduce the large deviations between predicted and observed values in the traditional numeri-cal weather prediction model(GRAPES_GFS)for 2 m temperature and to improve forecast accuracy,this paper proposes a correction model based on a Convolution Long Short-Term Memory(ConvLSTM)network and attention mechanism,utilizing GRAPES_GFS grid data and corresponding observational data.The model consists of three main steps.First,shallow local features are extracted from the input data through a local feature extraction module.Second,the extracted feature maps are fed into a dual attention module,which assigns different weights to different channel and spatial dimensions of the data,suppresses the influence of meteorological elements weakly correlated with 2 m temperature,and enhances local features in high-temperature regions.Finally,a ConvLSTM network cap-tures temporal dependencies in the data and outputs the corrected forecast.Experimental results show that,compared with the original GRAPES_GFS forecasts,the proposed model improves all evaluation metrics for 12-to 36-hour lead times in 2 m temperature prediction.The Pearson correlation coefficient increases from about 0.55 to approximately 0.87,the root mean squared error decreases from 1.74-2.06 ℃ to 0.90-1.10 ℃,and the mean absolute error de-creases from 1.36-1.64 ℃ to 0.69-0.84 ℃.Moreover,the model outperforms other mainstream correction approa-ches.关键词
通道注意力/空间注意力/ConvL-STM/预报订正/多气象要素Key words
channel attention/spatial attention/ConvLSTM/forecast correction/multiple meteorological elements分类
信息技术与安全科学引用本文复制引用
房善普,邱雨楠,陆振宇..基于ConvLSTM及双重注意力机制的2m气温预报订正方法[J].南京信息工程大学学报,2026,18(3):331-339,9.基金项目
国家自然科学基金联合重点项目(U20B2061) （U20B2061）
国家自然科学基金(61773220) （61773220）
江苏省自然科学基金(BK20150523) （BK20150523）
国家重点研发计划(2016YFC0203301) （2016YFC0203301）
