高速公路能见度的时空特征及预测

Study on Spatiotemporal Features and Prediction of Expressway Visibility

利用开源的历史气象数据,分析湖南省高速公路网能见度的时空变化特征,探究影响地区能见度的气象要素相关性,并构建基于BP神经网络和广义线性混合模型(GLMM)的能见度预测模型,结果表明BP神经网络模型能够更好地利用当前时刻的气象要素数据预测3 h后的高速公路能见度数值。

This paper used open-source historical meteorological data to analyze the temporal and spatial variation characteristics of expressway visibility in Hunan Province,explore the correlation of meteorological elements that affect regional visibility,and build a visibility prediction model based on BP neural network and Generalized Linear Mixed Model(GLMM).The results show that the BP neural network model can better predict the expressway visibility value after 3 hours by using the current meteorological data.