Table 1 Comparative analysis of spatiotemporal traffic forecasting models.

From: Research on traffic flow prediction of progressive graph convolutional networks based on spatio-temporal self-attention mechanism

Methods

Structure

Spatial

Temporal

Feature

Relationship type

STGCN32

In Series

S

I

I

P

DCRNN33

In Embedded

S

I

I

P

Graph WaveNet34

In Series

S

I

I

A

ASTGCN35

In Series

S & I

I

I

A & D

SSGCRTN24

In Embedded

S & I

IT

I

A & D

MSTDFGRN25

In Parallel

S & I

IT & S

I

A & D

PSTCGCN26

In Series

S

I

I

P & A

TIIDGCN27

In Series

S & I

IT & S & I

I

A & D

SDSINet28

In Parallel

S

IT

I

A

MTEGCRN29

In Parallel

S & I

IT & S

I

A & D

GDGCRN30

In Series

S

I

I

A & D

DMFGCRN31

In Parallel

IT & S

IT & S & I

IT & S & I

A & D

PGCN-STSA (Proposed)

In Series

IT & S & I

IT & S & I

IT & S & I

P & A & D