The problem of traffic flow forecasting has multi-source heterogeneity.The traffic flow in the future is not only related to the flow at the previous moment, but also affected by heterogeneous spatio-temporal data such as the relationship between urban regions, weather conditions and POI (point of interest).To solve this problem, a traffic flow prediction model based on multi-source heterogeneous spatio-temporal data fusion was proposed, which was called MHFSTNet (multi-source heterogeneous fusion spatio-temporal network).Firstly, this model used clustering methods to obtain different traffic patterns in urban areas, and utilized various methods such as concatenation, weight addition, and attention mechanism to integrate spatio-temporal data of multiple modalities, including traffic flow, location relationships between urban areas, weather, POI and the time of day.Deep learning methods were used to uniformly model heterogeneous data and predict traffic flow in the future.Experiments were conducted on three real-world traffic datasets, TaxiBJ, TaxiNYC and BikeNYC datasets.The results showed that MHF-STNet achieved the best performance compared with some classic traffic flow prediction models, which verified the effectiveness of MHF-STNet for unified modeling of heterogeneous spatio-temporal data.
