###
DOI:
本文二维码信息
随机森林回归法在冬季路面温度预报中的应用
王可心1, 包云轩2, 朱承瑛3, 陈粲1, 袁成松3
(1.南京信息工程大学气象灾害预报预警与评估协同创新中心;2.南京信息工程大学 气象灾害预报预警与评估协同创新中心;3.中国气象局交通气象重点开放实验室)
Forecasts of Road Surface Temperature in Winter Based on Random Forests Regression
摘要
相似文献
本文已被:浏览 79次   下载 28
投稿时间:2019-12-26    修订日期:2020-11-26
中文摘要: 基于宁宿徐高速公路三个交通气象站2015-2018年冬季逐十分钟实时观测资料,使用随机森林回归模型预报这三个站的未来1小时冬季路面温度,分析了该模型在冬季路面温度预报中的可行性和适用性。研究结果表明:(1)随机森林回归法可以被用来预报高速公路冬季路面温度,不同类型的交通气象站点的特征输入方案和参数调试标准存在差异;(2)与简单特征相比,引入的复合特征能更好的补充解释交通气象站所处的环境和气象要素,且其对普通路面交通气象站和靠近桥梁、水体的交通气象站的区分度更高,故引入复合特征的随机森林回归模型可以被用来预报高速公路冬季路面温度,且其在对普通路面交通气象站和靠近水体、桥梁的交通气象站的预报效果较好,而对服务区交通气象站的预报效果略差;(3)袋外误差率的降低并不代表预报精度的提高;(4)引入复合特征的随机森林回归模型不论在何种天气状况下,均可用于各不同类型交通气象站冬季路面温度的预报,雨雪天时的预报效果最佳,阴天其次,晴天略差。
Abstract:Based on the data of three traffic meteorological stations set on Nanjing-Suqian-Xuzhou expressway observed every ten minutes during 2015 to 2018, the Random Forests Regression was used to forecast the road surface temperature in the next hour in winter and the feasibility and applicability of the models were analyzed. The results were showed as follow: (1) The Random Forests Regression models could be used to predict the road surface temperature of the expressway in winter, and the feature input and parameter debugging are different in types of traffic meteorological stations. (2) Compared with the simple features, the complex features could replenish and explain the environment and meteorological elements of the traffic meteorological stations better, and they had a higher degree of differentiation between the ordinary road traffic meteorological stations and the traffic meteorological stations near the bridge and water. As a result, the model has a good forecast effect on the general road traffic meteorological stations and the traffic meteorological stations near the water and bridges, but a little poor forecast effect on the traffic meteorological stations in the service areas. (3) The reduction of the average error rate out of bag did not mean the improvement of the prediction accuracy. (4) The random forest regression models simulated from the complex features could be used to predict the road surface temperature of different types of traffic weather stations in winter no matter what weather conditions. Their forecast effect was the best in rainy and snowy days, followed by cloudy days and slightly worse in sunny days.
文章编号:201912260454     中图分类号:    文献标志码:
基金项目:2018年度交通运输行业重点科技项目(2018-MS4-102)、2018年度云交设计公司自立科技项目( ZL-2018-04)
引用文本:
王可心,包云轩,朱承瑛,陈粲,袁成松,0.[en_title][J].Meteor Mon,():-.
wangkexin,baoyunxuan,zhuchengying,chencan,yuanchengsong,0.Forecasts of Road Surface Temperature in Winter Based on Random Forests Regression[J].Meteor Mon,():-.