Bidirectional Spatial–Temporal Graph Convolutional Model: Traffic Flow Forecasting With Enhanced Extended Capabilities
Bibliographic record
Abstract
Traffic flow forecasting, as a crucial component of intelligent transportation systems (ITS), enables the prediction of future traffic conditions based on historical traffic data, thereby optimizing travel strategies and achieving the goal of reducing traffic congestion. Considering the limited nature of specific road network spatial structures, specific road network datasets often overlook the influence of surrounding networks on the network itself, motivating the need for a framework that captures boundary interactions. This paper introduces the bidirectional spatial–temporal expanded graph convolutional model (Bi‐STEGCM) to traffic flow forecasting. This addresses the limitations of conventional models, particularly in capturing spatial features and managing missing or anomalous data. The Bi‐STEGCM reconstructs and aggregates traffic data while preserving the temporal dynamics of traffic flow. This offers a more nuanced representation of the spatiotemporal dynamics within road networks. The model utilizes causal convolution for temporal feature extraction and an auto‐regressive moving average (ARMA) filter for spatial feature extraction. It integrates these with bidirectional graph convolution to aggregate spatial features across various layers. Validation using real‐world traffic datasets PEMS03, PEMS04, PEMS07, and PEMS08 demonstrates that the Bi‐STEGCM outperforms state‐of‐the‐art models, including spatial–temporal synchronous graph convolutional networks (STSGCN) and spatial–temporal fusion graph neural networks (STFGNN), across three key evaluation metrics. Notably, the Bi‐STEGCM requires significantly fewer parameters and less training time than its counterparts, rendering it a more efficient and effective solution for traffic flow forecasting tasks.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".