Learning Traffic as Images: A Deep Convolutional Neural Network for Large-Scale Transportation Network Speed Prediction

TL;DR

This paper introduces a CNN-based approach that transforms traffic data into images to accurately predict large-scale transportation network speeds, outperforming existing methods with significant accuracy improvements.

Contribution

The study presents a novel image-based traffic modeling method using CNNs for large-scale networks, demonstrating superior accuracy over traditional and deep learning models.

Findings

Outperforms four traditional algorithms with 42.91% accuracy improvement.

Effective for large-scale transportation networks with reasonable training time.

CNN-based method achieves high accuracy in real-world network speed prediction.

Abstract

This paper proposes a convolutional neural network (CNN)-based method that learns traffic as images and predicts large-scale, network-wide traffic speed with a high accuracy. Spatiotemporal traffic dynamics are converted to images describing the time and space relations of traffic flow via a two-dimensional time-space matrix. A CNN is applied to the image following two consecutive steps: abstract traffic feature extraction and network-wide traffic speed prediction. The effectiveness of the proposed method is evaluated by taking two real-world transportation networks, the second ring road and north-east transportation network in Beijing, as examples, and comparing the method with four prevailing algorithms, namely, ordinary least squares, k-nearest neighbors, artificial neural network, and random forest, and three deep learning architectures, namely, stacked autoencoder, recurrent neural network, and long-short-term memory network. The results show that the proposed method outperforms other algorithms by an average accuracy improvement of 42.91% within an acceptable execution time. The CNN can train the model in a reasonable time and, thus, is suitable for large-scale transportation networks.