# lehaifeng/T-GCN

Temporal Graph Convolutional Network for Urban Traffic Flow Prediction Method

Repository: https://github.com/lehaifeng/T-GCN
Canonical: https://ross.abutalabs.com/products/t-gcn
Language: Jupyter Notebook
License Family: other
Last push: 2025-09-01T02:23:21+00:00

## Health v2 (maintenance only)
Score: 50/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 39, release rhythm 35, longevity 100
- inputs: {"age_days": 2851, "days_push": 367, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1781, forks 473 (observed 2026-08-28T04:05:35.514683+00:00)

## What it is
A collection of research source code implementing Temporal Graph Convolutional Networks (T-GCN) and related variants for urban traffic flow prediction. It accompanies multiple published papers on spatiotemporal graph neural networks and graph representation learning.

## Use cases
- predict urban traffic flow with graph neural networks
- implement temporal graph convolutional networks
- reproduce T-GCN paper results
- spatiotemporal traffic forecasting research
- learn graph representation learning for time series
- compare GNN traffic prediction models

## When to choose
- you need reference implementations of T-GCN and its variants for traffic prediction
- you are doing academic research on spatiotemporal GNNs
- you want paper-reproducible code for graph-based forecasting

## When to avoid
- you need a production-ready, maintained forecasting library
- you require a licensed package for commercial use (no license is provided)
- you need non-traffic graph learning tasks with polished APIs

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning, data-science
- domain: machine-learning, deep-learning, artificial-intelligence
- platform: python
- tags: graph-neural-networks, traffic-forecasting, spatiotemporal, time-series, research-code, jupyter-notebook

## Member repositories
- lehaifeng/T-GCN (main) score 50

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:35.514683+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T03:24:24.943792+00:00, confidence not recorded.
  - readme: https://github.com/lehaifeng/T-GCN (fetched 2026-08-28T04:05:35.514683+00:00, sha 246c8b2d32f2)
- Data as of 2026-08-30T08:39:29.467469+00:00.