Estimating travel speed distributions of paths in road networks using dual-input LSTMs

Thanks to recent advances in sensor technologies, detailed travel speed information is becoming increasingly available. Such data provide a solid data foundation to capture traffic uncertainty, e.g., in the form of travel speed distributions. We study the problem of estimating travel speed distributions of paths in a road network using vehicle trajectory data. Given a path and a departure time, we aim at estimating the travel speed distribution of the path. To this end, we propose a dual-input long-short term memory (DI-LSTM) model. We introduce two new gates with the purpose of combining two input distributions in every iteration, where one distribution is an edge' distribution, and the other is the distribution of the pre-path until the edge, which is obtained from the previous DI-LSTM unit. Empirical studies on a large trajectory dataset offer insight into the design properties of the DI-LSTM and demonstrate that DI-LSTM out-performs classic LSTM, especially for long paths.