The invention discloses a road visibility short-term and temporary prediction method based on ensemble learning. The method comprises the following steps: constructing a sample meteorological data set; training a random forest by utilizing the sample data set to obtain a random forest model; training a gradient boosting tree by using the sample data set, and training by using an extreme gradient boosting algorithm to obtain an extreme gradient boosting model; according to prediction time requirements, inputting to-be-predicted data into the trained random forest model and the extreme gradientlifting model to obtain visibility grade prediction data; and comparing the performance of the two models on different prediction performance indexes, and comprehensively selecting a prediction resultas final visibility prediction data. According to the method, refined and short-term prediction of visibility is realized, and the method has certain guiding significance for developing low-visibility early warning and forecasting in the fields of road traffic and the like.

    本发明公开了一种基于集成学习的道路能见度短临预测方法,该方法包括:构建样本气象数据集;利用样本数据集训练随机森林,得到随机森林模型;利用样本数据集训练梯度提升树,并利用极限梯度提升算法进行训练,得到极限梯度提升模型;根据预测时间要求,将待预测数据输入训练过后的随机森林模型和极限梯度提升模型中,得到能见度等级预测数据;对比两个模型在不同预测性能指标上的表现,综合选择预测结果作为最终的能见度预测数据。本发明实现了能见度的精细化、短临化预测,对于开展道路交通等领域的低能见度预警预报具有一定的指导意义。


    Zugriff

    Download


    Exportieren, teilen und zitieren



    Titel :

    Road visibility short-term and temporary prediction method based on ensemble learning


    Weitere Titelangaben:

    一种基于集成学习的道路能见度短临预测方法


    Beteiligte:
    WU BING (Autor:in) / ZHAI BEN (Autor:in) / WANG YANLI (Autor:in)

    Erscheinungsdatum :

    2020-11-10


    Medientyp :

    Patent


    Format :

    Elektronische Ressource


    Sprache :

    Chinesisch


    Klassifikation :

    IPC:    G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G01W METEOROLOGY , Meteorologie / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G06K Erkennen von Daten , RECOGNITION OF DATA / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Time sequence short-term and temporary prediction method

    MENG XIANWEI / JIA LIN | Europäisches Patentamt | 2023

    Freier Zugriff

    An ensemble learning method for low visibility prediction on freeway using meteorological data

    Zhai, Ben / Wang, Yanli / Wu, Bing | Wiley | 2023

    Freier Zugriff



    Short-term traffic flow prediction of road network based on deep learning

    Han, Lei / Huang, Yi-Shao | IET | 2020

    Freier Zugriff