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

doi:10.3969/j.issn.1673-503X.2025.01.013

Abstract

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

CLC Number:

P457.3

JIA Xiaohong, SHI Lan, HAO Yuzhu. Forecast and verification of winter road surface temperature using the Fully Connected Neural Network method[J]. Journal of Meteorology and Environment, 2025, 41(1): 104-112.

References

[1] 成丹,付晓辉.沪渝高速(湖北段)路面温度变化特征及预报研究[J].气象科技进展,2016,6(4):51-57.
[2] 胡继超,林子静,成添.道路结冰的温度预报方法研究进展[J].科学技术与工程,2020,20(1):1-6.
[3] 田华,吴昊,赵琳娜,等.沪宁高速公路路面温度变化特征及统计模型[J].应用气象学报,2009,20(6):737-744.
[4] 田华,张楠,张楷翊,等.国外公路交通气象研究进展[J].气象与环境学报,2019,35(3):79-86.
[5] 曲晓黎,齐宇超,尤琦,等.基于METRo模型的冬奥高速公路示范站路面温度临近预报方法[J].干旱气象,2020,38(3):497-503.
[6] 冯蕾,王晓峰,何晓凤,等.基于INCA和METRo的江苏省路面高温精细化预报[J].应用气象学报,2017,28(1):109-118.
[7] 赵文.基于METRo的高速公路路面低温预报模型研究[D].兰州:兰州大学,2022.
[8] Liu B,Yan S,You H L,et al.Road surface temperature forecast based on gradient extreme learning machine boosting[J].Computers in Industry,2018(99):294-302.
[9] 刘鑫达.基于深度学习的气象温度预测研究[D].银川:宁夏大学,2016.
[10] 罗小川,唐荣年,宁雨珂,等.基于CLDAS和ConvLSTM的海南岛区域网格温度短临预报[J].海南大学学报(自然科学版),2021,39(3):297-305.
[11] 赵琳娜,卢姝,齐丹,等.基于全连接神经网络方法的日最高气温预报[J].应用气象学报,2022,33(3):257-269.
[12] Tabrizi S E,Xiao K,Griensven J V,et al.Hourly road pavement surface temperature forecasting usingdeep learning models[J].Journal of Hydrology,2021,603(1):126877.
[13] 韦青,代刊,林建,等.2016—2018年全国智能网格降水及温度预报检验评估[J].气象,2020,46(10):1272-1285.
[14] 潘留杰,张宏芳,刘静,等.智能网格SCMOC及多模式降水预报对比[J].大气科学学报,2023,46(2):217-229.
[15] 韩伟,吴艳兰,任福.基于全连接和LSTM神经网络的空气污染物预测[J].地理信息世界,2018,25(3):34-40.
[16] 王佳,郭春燕,谷新波.包头市不同路面温度变化特征及预报模型研究[J].沙漠与绿洲气象,2021,15(1):91-96.
[17] 王可心,包云轩,朱承瑛,等.随机森林回归法在冬季路面温度预报中的应用[J].气象,2021,47(1):82-93.
[18] 邱金晶,陈锋,张珏,等.浙江省高速公路路面温度预报模型性能检验及应用[J].气象科技,2020,48(4):518-528.
[19] 张曦,浩宇,梁佳,等.陕西省高速公路路面温度特征及预报模型[J].干旱气象,2019,37(6):1028-1034.
[20] 武辉芹,马翠平,杨荣芳,等.河北省高速公路路面温度变化特征及预报模型[J].干旱气象,2014,32(4):665-670.
[21] 孙翠梅,马俊峰,孔启亮,等.镇江市道路结冰影响指数分级预报方法[J].气象与环境学报,2013,29(4):84-88.
[22] 王可心.宁宿徐高速公路北段冬季路面温度分布特征及预报研究[D].南京:南京信息工程大学,2020.
[23] 肖瑶,杜明哲,徐鹏.两种订正方法在河南高速公路沿线气温精细化预报中的应用[J].干旱气象,2020,38(6):1023-1030.

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

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 10

[1]	YAO Kai, ZHU Xiaotong, CHEN Changsheng, QIN Yulin, ZHOU Dongxue, PIAO Meihua. Spatial verification of CMA models on precipitation forecast for typhoon “Meihua” in Northeast China [J]. Journal of Meteorology and Environment, 2025, 41(1): 35-42.
[2]	Wenguang DUAN,Yiyang JIA,Yan LIU,Yongwei SHI,Lifu CHEN. Calculation and classification of meteorological index for Marathon races [J]. Journal of Meteorology and Environment, 2024, 40(5): 99-105.
[3]	Liman CUI,Xiujie GU,Le XI,Yachun ZHANG,Ziyue XUE. Causes analysis of extreme snowstorm and lightning in He'nan province in March of 2023 [J]. Journal of Meteorology and Environment, 2024, 40(4): 10-18.
[4]	Sijia XUE,Pengpeng WANG,Ruijiang WEI,Yunxiu WANG,Mei YANG,Yuanyuan LIU. Comparative analysis of potato yield forecasting for different methods in Hebei province [J]. Journal of Meteorology and Environment, 2024, 40(4): 123-130.
[5]	Lei WEI,Binghong CHEN,Lan ZHANG,Huaiyu LI,Zhiyan LIANG,Huan XU. Evaluation of ECMWF model forecasting performance for front and warm-area rainfall in South China based on the sliding centroid method [J]. Journal of Meteorology and Environment, 2024, 40(2): 9-16.
[6]	Xiaoxuan SU,Xiaowei SUN,Chenhe ZHANG,Jia-qi LI,Zengxin LU,Xu YANG. Application and verification of the spatiotemporal projection model in the extended-range forecast of summer precipitation in Northeast China [J]. Journal of Meteorology and Environment, 2024, 40(1): 27-36.
[7]	Yong WANG, Yuying CHEN, Ting LI, Yang SU. Characteristics of wet potential vortex in two rainstorms at the eastern foothills of Helan Mountains [J]. Journal of Meteorology and Environment, 2023, 39(6): 1-9.
[8]	Yue WANG,Chenghan LIU,Yunxia DUAN,Hongyu SUN,Jinglin CUI,Yumeng SU,Peiyu CHEN,Weilong BAN. Verification technology of multi-model precipitation forecast in Liaoning province in summer 2020 [J]. Journal of Meteorology and Environment, 2023, 39(6): 37-43.
[9]	Jiajin WANG, Binyan WANG, Dixiang XIAO, Ke-ji LONG. Comparative analysis of heavy rain forecast in Sichuan province from two numerical models based on the object recognition method [J]. Journal of Meteorology and Environment, 2023, 39(6): 44-50.
[10]	Weihua LIU, Wei JIN, Huipin WANG, Chunxiang SHI, Shulin QU, Guojing HAN, Miao YU. Analysis of the applicability of CLDAS wind field data in Liaoning province in 2020 [J]. Journal of Meteorology and Environment, 2023, 39(6): 61-68.
[11]	Aizhong ZHANG,Qi YAN,Lei GAO,Jinglong LU,Fangda TENG,Dan WU,Hongjie SHI. Preliminary study on the causes of deviation of the northeast wind backflow snowstorm forecast in Liaoning region [J]. Journal of Meteorology and Environment, 2023, 39(5): 28-33.
[12]	Yunchen LIAO,Bingui WU,Tingting JU,Meng TIAN,Yinghua LI,Shupeng SUN,Jialin ZHANG,Jianbo YANG. Research on the applicability of high vertical resolution on radiation fog simulation around the Bohai Sea based on the WRF model [J]. Journal of Meteorology and Environment, 2023, 39(5): 34-43.
[13]	Weidong JIANG,Rongzhi ZHANG,Bo CHEN,Tianqi ZHANG,Hailing HUANG,Lin ZHOU. Experimental study on thunderstorm forecast of ground-based microwave radiometer based on BP neural network [J]. Journal of Meteorology and Environment, 2023, 39(5): 106-112.
[14]	Zhenghua TAN, Aizhong ZHANG, Qi YAN, Ruiwen YANG, Yushan GUAN. Analysis of the synoptic causes and forecast deviation of a snowstorm process in Liaoning province in February 2020 [J]. Journal of Meteorology and Environment, 2023, 39(4): 1-8.
[15]	Wei YANG,Xun LI,Jian-xing LIN,You-long CHEN,Bin-yu YANG. Numerical simulation of a strong convective lightning process in Hainan island with different lightning parameterization schemes [J]. Journal of Meteorology and Environment, 2023, 39(3): 20-30.