基于可解释机器学习的大型活动场馆周边路网运行状态影响研究  

Research on impact of short-term large-scale events on nearby traffic flow via interpretable machine learning

作　　者：吴明珠 冯楷 翁剑成[1] 魏瑞聪 王晶晶 钱慧敏 WU Mingzhu;FENG Kai;WENG Jiancheng;WEI Ruicong;WANG Jingjing;QIAN Huimin(Beijing Key Laboratory of Traffic Engineering,Beijing University of Technology,Beijing 100124,China;Fujian Expressway Group Co.,Ltd.,Fuzhou 350001,China;Beijing Municipal Transportation Operations Coordination Center,Beijing 100161,China)

机构地区：[1]北京工业大学交通工程北京市重点实验室,北京100124 [2]福建省高速公路联网运营有限公司,福州350001 [3]北京市交通运行监测调度中心,北京100161

出　　处：《南京信息工程大学学报》2024年第2期221-230,共10页Journal of Nanjing University of Information Science & Technology（Natural Science Edition）

基　　金：国家自然科学基金(52072011)。

摘　　要：举办大型活动会导致周边受影响区域在短时间内集中大量人群和车辆,场馆周边路网与常态交通具有差异化特征.为探究大型活动对场馆周边路网运行状态的影响机理,解析活动规模、路段与活动场馆的空间距离等因素的影响特征,构建融合XGBoost算法与部分依赖图的可解释机器学习模型,以捕捉不同因素的非线性效应与协同影响.以北京市为例开展了实证研究,单因素的异质性影响表明:路段与活动场馆的空间距离及活动规模对场馆周边路网运行状态的影响较大,其相对重要度分别达到27.1%和25.4%,距离活动开始/结束的时间对场馆周边路网运行状态存在明显非线性特征,在活动开始前30~60 min,以及活动结束后30 min内,场馆周边3 km以内的路段将受到显著影响.二维因素的协同影响表明:当活动规模大于3万人时,节假日和不利天气对场馆周边路网运行状态呈负面影响,而在降雨和雾霾天气下,场馆周边路网运行状态受时空影响较大,影响范围为活动开始前60 min与结束后40 min内距离活动场馆2.5 km内的路段.相关研究结论可为大型活动期间道路拥堵致因辨别及制定科学有效的路网管控策略提供定量化的决策依据.The large number of people and vehicles gathered in a short period of time around large-scale events will lead to a differentiated traffic flow.Here,an interpretable machine learning model integrating XGBoost algorithm and partial dependence plots is proposed to capture the nonlinear effects and synergistic influences of large-scale events and their characteristics on the operation of nearby road network,and an empirical study has been conducted in Beijing.The heterogeneity of single factors shows that the distance of road section away from event venue and the event scale have great impact on nearby traffic flow,with relative importance of 27.1%and 25.4%,respectively;time before start and after end of the event has obvious nonlinear characteristics,and the road sections within 3 km from the venue will be significantly affected within 30-60 minutes before the event and 30 minutes after the event.The synergistic effect of two-dimensional factors shows that,if an event attracted more than 30,000 people,holidays and adverse weather have a negative impact on the nearby traffic flow;in rain or haze weather,the road section within 2.5 km from the venue will be affected within 60 minutes before the event and 40 minutes after the event.The findings can provide quantitative data support for identifying the causes of road congestion and formulating reasonable and effective road network control strategies during large events.

关 键 词：城市交通 短时大型活动 路网运行状态 影响关系 XGBoost模型 部分依赖图 

分 类 号：U491.1[交通运输工程—交通运输规划与管理] TP183[交通运输工程—道路与铁道工程]