Improving Traffic Flow Predictions with SGCN-LSTM: A Hybrid Model for Spatial and Temporal Dependencies

TL;DR

This paper introduces SGCN-LSTM, a hybrid model that captures complex spatial and temporal dependencies in traffic data, significantly improving traffic speed prediction accuracy over existing models.

Contribution

The paper presents a novel SGCN-LSTM model that dynamically models intricate spatial relationships and temporal patterns in traffic data, advancing traffic prediction methods.

Findings

SGCN-LSTM outperforms benchmark models in MAE, RMSE, and MAPE on PEMS-BAY dataset.

Extensive experiments validate the effectiveness of the proposed hybrid model.

Dynamic spatial dependency modeling improves traffic prediction accuracy.

Abstract

Large amounts of traffic can lead to negative effects such as increased car accidents, air pollution, and significant time wasted. Understanding traffic speeds on any given road segment can be highly beneficial for traffic management strategists seeking to reduce congestion. While recent studies have primarily focused on modeling spatial dependencies by using graph convolutional networks (GCNs) over fixed weighted graphs, the relationships between nodes are often more complex, with edges that interact dynamically. This paper addresses both the temporal patterns in traffic data and the intricate spatial dependencies by introducing the Signal-Enhanced Graph Convolutional Network Long Short Term Memory (SGCN-LSTM) model for predicting traffic speeds across road networks. Extensive experiments on the PEMS-BAY road network traffic dataset demonstrate the SGCN-LSTM model's effectiveness, yielding significant improvements in Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) compared to benchmark models on the same dataset.