3D-CLoST: A CNN-LSTM Approach for Mobility Dynamics Prediction in Smart Cities

The problem of reliably predicting vehicle flows is paramount for traffic management, risk assessment, and public safety. It is a challenging problem as it is influenced by multiple factors, such as spatio-temporal dependencies with external factors (as events and weather conditions). In recent years, with the exponential data growth and technological advancement, deep learning has been adopted to approach urban mobility problems by addressing spatial dependency with convolutional neural networks and the temporal one with recurrent neural networks. We propose a spatio-temporal flow prediction framework, called 3D-CLoST, that exploits the synergy between 3D convolution and long short-term memory (LSTM) networks to jointly learn the characteristics of the space-time correlation from low to high levels. To the best of our knowledge, no method currently proposes such a structure for this problem. The results achieved on the two real-world datasets show that 3D-CLoST can learn behaviors from the data effectively.