Forecasting Spatially-Distributed Urban Traffic Volumes via Multi-Target LSTM-Based Neural Network Regressor

Abstract

Monitoring the distribution of vehicles across the city is of great importance for urban traffic control. In particular, information on the number of vehicles entering and leaving a city, or moving between urban areas, gives a valuable estimate on potential bottlenecks and congestions. The possibility of predicting such flows in advance is even more beneficial, allowing for timely traffic management strategies and targeted congestion warnings. Our work is inserted in the context of short-term forecasting, aiming to predict rapid changes and sudden variations in the traffic volume, beyond the general trend. Moreover, it concurrently targets multiple locations in the city, providing an instant prediction outcome comprising the future distribution of vehicles across several urban locations. Specifically, we propose a multi-target deep learning regressor for simultaneous predictions of traffic volumes, in multiple entry and exit points among city neighborhoods. The experiment focuses on an hourly forecasting of the amount of vehicles accessing and moving between New York City neighborhoods through the Metropolitan Transportation Authority (MTA) bridges and tunnels. By leveraging a single training process for all location points, and an instant one-step volume inference for every location at each time update, our sequential modeling approach is able to grasp rapid variations in the time series and process the collective information of all entry and exit points, whose distinct predicted values are outputted at once. The multi-target model, based on long short-term memory (LSTM) recurrent neural network layers, was tested on a real-world dataset, achieving an average prediction error of 7% and demonstrating its feasibility for short-term spatially-distributed urban traffic forecasting.

Attention-Based Gated Recurrent Graph Convolutional Network for Short-Term Traffic Flow Forecasting

“…In order to capture the time dependencies in trafc fow more accurately, some scholars have used variants of recurrent neural networks (RNN) time series models and their variants (LSTM [8] and GRU [13]) for trafc fow prediction with good performance. Crivellari and Beinat [30] proposed a multiobjective LSTM-based neural network regulator to predict spatially distributed urban trafc. Zhao et al [31] built a cascaded LSTM network and integrated the origin destination correlation (ODC) matrix representing spatialtemporal correlations into the proposed network.…”

“…Although these models can reasonably consider the spatialtemporal correlations among trafc fows in various city regions and extract rich spatialtemporal features, they can only handle Euclidean structured data and are inadaptive to non-Euclidean structured data. Crivellari and Beinat [30] proposed an LSTM-based method so as to predict urban trafc fows distributed over multiple reference locations in the city. Bai et al [34] proposed a multitask convolutional recurrent neural network (MT-CRNN) framework that combines CNN and LSTM and mixes external features together, such as season, temperature, and air quality, to predict passengers' demand for multiple features from diferent domains.…”

Public Transport Congestion Detection Using Incremental Learning

“…The efficacy of machine learning for vehicle classification using roadside sensors has been rigorously examined in [42,43]. The mathematical landscape of methods used for traffic flow forecasting include Hidden Markov models [44], gradient boosting regression tree [45], artificial neural networks [46], decision trees [47], support vector machines [48], Long short-term memory (LSTM) [49,50], and Bayes networks [51]. Recent advances in traffic flow forecasting also include deep learning-based techniques [52][53][54][55][56] and ensemble approaches [57][58][59][60].…”

LSTM-Based Path Prediction for Effective Sensor Filtering in Sensor Registry System

“…Recurrent neural networks (RNN) are effective tools for processing sequential data and can be applied to path prediction as well [ 31 , 32 ]. Crivellari et al propose a series of methods to analyze call detail records related to tourists’ behavior in Italy, such as geo-embedding [ 33 , 34 ], predicting individual mobility traces [ 35 ], trajectory translation [ 36 ], and urban traffic forecasting [ 37 ]. Similar to natural language processing, these methods have three significant components [ 38 ]: 1.…”