Open access
Jul 2026
A Hybrid Spatiotemporal Framework with Memory and Diffusion Convolution for Traffic Flow Prediction
A novel spatiotemporal forecasting framework, termed Memory-augmented Diffusion Convolutional LSTM network (MDC-LSTM), which integrates a MemBART-inspired memory mechanism, diffusion convolution, regional attention, and LSTM-based temporal modeling and effectively captures both localized spatial patterns and deep inter-temporal relationships.
Xi Chen, Jiajia Chen
· Applied Artificial Intellige... · 0 citations