Multi-scale Wavelet-Mamba framework for spatiotemporal traffic forecasting

Nature·Nov 28

✦ NabkaNews BriefAuto-summarized from multiple outlets · verify with the source

Researchers have developed various frameworks for spatiotemporal forecasting, including traffic and flight trajectory prediction. These frameworks incorporate techniques such as wavelet transforms, graph convolutions, and neural operators to improve prediction accuracy. The specific details and applications of these frameworks appear to vary, with different models and approaches being proposed for different types of forecasting tasks.

Full coverage

DSTGA-Mamba: a disentangled spatio-temporal graph attention Mamba model for traffic flow prediction

Nature·Dec 10

Integrated spatio-temporal modeling with hybrid graph convolutions and the graph fourier neural operator for traffic prediction

Nature·Mar 10

Multi-horizon flight trajectory prediction enabled by time-frequency wavelet transform

Nature·Dec 11

Pre-trained multi-scale RWKV-GCN for multivariate time series forecasting

Nature·Feb 23