城市轨道交通车站短时客流机器学习预测方法

1.深圳大学土木与交通工程学院,广东深圳518060;2.深圳大学滨海城市韧性基础设施教育部重点实验室,广东深圳518060;3.深圳大学未来地下城市研究院,广东深圳518060;4.深圳大学深圳市地铁地下车站绿色高效智能建造重点实验室,广东深圳518060

交通运输工程;城市轨道交通;短时客流预测;数据处理;特征工程;机器学习

Machine learning based method for forecasting short-term passenger flow in urban rail stations
HU Mingwei1,2,3,4,SHI Xiaolong1,WU Wenlin1,and HE Guoqing1

1.College of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, Guangdong Province, P. R. China;2.Key Laboratory of Coastal Urban Resilient Infrastructures of Ministry of Education, Shenzhen University, Shenzhen 518060, Guangdong Province, P. R. China;3.Underground Polis Academy, Shenzhen University, Shenzhen 518060, Guangdong Province, P. R. China;4.Shenzhen Key Laboratory of Green, Efficient and Intelligent Construction of Underground Metro Station, Shenzhen University, Shenzhen 518060, Guangdong Province, P. R. China

traffic and transportation engineering; urban rail transit; short-term passenger flow prediction; data processing; feature engineering; machine learning

DOI: 10.3724/SP.J.1249.2022.05593

备注

轨道交通具有载客量大、安全及环保等优点,已成为多数乘客的优先出行方式,是缓解城市交通压力的有效途径之一.为提高轨道系统的运行效率,实现轨道交通智慧化运营,基于机器学习算法理论,结合轨道交通车站的时间、空间及外部影响因素等客流特征,建立轻量的梯度提升机(lightgradientboostingmachine,LightGBM)、长短期记忆(longshort-termmemory,LSTM)及LightGBM-LSTM融合模型的车站短时客流预测模型,同时构建差分自回归移动平均(autoregressiveintegratedmovingaverage,ARIMA)和极限梯度提升(extremegradientboosting,XGBoost)模型作为预测实验的对照模型.以中国杭州地铁自动售票系统刷卡数据为例,选取了5种地铁车站(居住类型、工作类型、居住工作混合类型、购物类型及交通枢纽类型)和3个准确性评价指标(平均绝对误差、均方根误差及平均绝对百分误差),量化评价不同模型的预测准确性.结果表明,基于多特征的机器学习模型可以较好预测地铁车站短时客流,弥补了传统时间序列模型的不足.但单一模型在不同类型车站的预测效果波动性较大.基于多模型融合的LightGBM-LSTM模型可以综合单一模型的优点,预测性能更佳,对于不同类型车站的适应性更好.
Urban rail transit features much strength, such as large capacity, safety and environment-friendliness, and it becomes a preferred choice for most passengers. It also plays a prominent part in solving urban traffic problems. In order to improve the operation efficiency of the urban rail transit system and achieve the goal of smart operations, this paper applies machine learning algorithms and completes the feature engineering of urban rail transit passenger flow data in terms of time, space and external factors. Based on passenger flow characteristics as collected, we build the short-term passenger flow forecast models, which include light gradient boosting machine (LightGBM) model, long short-term memory (LSTM) model, and LightGBM-LSTM fusion model. Besides, we construct the autoregressive integrated moving average (ARIMA) model and extreme gradient boosting (XGBoost) model for experiment comparison. Finally, we conduct the passenger flow forecasting experiments on the Hangzhou subway dataset based on the five prediction-models mentioned above. Then, five types of subway stations are selected (residential type, occupation type, residential-occupation type, business type, and transportation hubs type) and three accuracy evaluation indicators are chosen (mean absolute error, root mean square error and mean absolute percentage error) to evaluate the prediction accuracy of the five prediction models. The experimental results show that, the multi-feature machine learning model can effectively forecast urban rail transit short-term passenger flow which is difficult for the traditional time series model. However, the single model has poor adaptability to different types of subway stations. Compared with a single model, LightGBM-LSTM model equipped with merits of multiple models, fulfills a better function in forecasting and a better adaptability to different types of urban rail transit stations.
·