主办单位:中国气象局沈阳大气环境研究所
国际刊号:ISSN 1673-503X
国内刊号:CN 21-1531/P

气象与环境学报 ›› 2025, Vol. 41 ›› Issue (1): 104-112.doi: 10.3969/j.issn.1673-503X.2025.01.013

• 快报 • 上一篇    

基于全连接神经网络方法的冬季公路路面温度预报及检验

贾晓红1,2, 石岚1,2, 郝玉珠1   

  1. 1. 内蒙古自治区气象服务中心, 内蒙古呼和浩特 010051;
    2. 中国气象局交通气象重点实验室, 江苏南京 210008
  • 收稿日期:2023-09-13 修回日期:2023-12-27 出版日期:2025-02-28 发布日期:2025-02-28
  • 通讯作者: 石岚,女,正研级高级工程师,E-mail:lan_shi@sina.com。 E-mail:lan_shi@sina.com
  • 作者简介:贾晓红,女,1993年生,工程师,主要从事交通气象研究,E-mail:2570415607@qq.com。
  • 基金资助:
    中国气象局交通气象重点开放实验室开放研究基金(BJG202207)和内蒙古自治区自然科学基金(2023QN04008、2024MS04030)共同资助。

Forecast and verification of winter road surface temperature using the Fully Connected Neural Network method

JIA Xiaohong1,2, SHI Lan1,2, HAO Yuzhu1   

  1. 1. Inner Mongolia Service Center of Meteorology, Hohhot 010051, China;
    2. Key Laboratory of Transportation Meteorology, CMA, Nanjing 210008, China
  • Received:2023-09-13 Revised:2023-12-27 Online:2025-02-28 Published:2025-02-28

摘要: 基于SCMOC精细化格点预报产品及交通气象站观测数据,利用全连接神经网络模型(Fully Connected Neural Network,FCNN),对G6京藏高速内蒙古复杂路段进行冬季未来24 h逐小时路面温度预报。结果表明:构建的FCNN模型的最佳训练期为20 d,增加时间特征变量能有效减小模型路面温度预报误差,MAE减小0.3~0.8 ℃,AR提高4%~18%。最终建立FCNN路面温度预报模型,预报总体上具有较高的精度,其中ME、MAE、RMSE分别为-0.2~0.0 ℃、1.1~1.3 ℃和1.6~1.9 ℃,r大于0.94,AR超过90%,且0 ℃以下预报效果良好。从各项检验指标的日变化来看,除12:00—15:00预报效果较差外,其余时段预报能力较强,ME、MAE、RMSE、r和AR平均值分别为-0.07 ℃、1.20 ℃、1.58 ℃、0.94和93%。通过对2022年冬季平稳天气、寒潮天气和降雪天气进行检验,MAE均在2.0 ℃以内,证实FCNN模型对不同天气的路面温度都有一定的预报能力。

关键词: 路面温度, FCNN模型, 预报, 检验

Abstract: Based on SCMOC refined grid forecast products and observation data of traffic meteorological stations,using the Fully Connected Neural Network model (FCNN),the hourly road surface temperature was forecasted for the next 24 hours in winter along the complex section of the G6 Beijing-Xizang Highway in Inner Mongolia.The results show that according to the experiment,the optimal training period of FCNN model is 20 d.Increasing the time characteristic variable could reduce the forecasting error of the road surface temperature effectively,MAE decreases by 0.3~0.8 ℃,AR increases by 4%~18%.The final FCNN model of road surface temperature forecast is developed with high accuracy,in which ME,MAE and RMSE are -0.2~0.0 ℃,1.1~1.3 ℃,and 1.6~1.9 ℃,respectively,r exceeds 0.94,AR is above 90%,and better performance for temperature below 0 ℃.From the perspective of daily variation of each test index,except for the poor forecast performance from 12:00 to 15:00,the other time periods have good forecast performance,with the mean values of ME,MAE,RMSE,r,and AR are -0.07 ℃,1.20 ℃,1.58 ℃,0.94,and 93%,respectively.Case studies conducted for stable weather,cold wave weather,and snowfall weather during the winter of 2022 confirm that the FCNN model maintains a forecasting MAE within 2.0 ℃ across different weather scenarios,demonstrating its applicability for road surface temperature prediction under diverse meteorological conditions.

Key words: Road surface temperature, FCNN Model, Forecast, Verification

中图分类号: