LibCity/Bigscity-LibCity

Health v2 · maintenance only

Adoption not part of the score

1157 stars · 193 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

LibCity is an open-source PyTorch library for urban spatial-temporal data mining, providing a unified pipeline for traffic prediction research. It reproduces 74 models across 9 tasks (traffic flow/speed prediction, ETA, map matching, etc.) with 52 datasets and standardized evaluation.

Use cases

• predict traffic flow on road networks
• forecast traffic speed from sensor data
• estimate travel time between origin and destination
• predict next location from trajectory data
• map matching GPS points to road networks
• learn road network representations
• benchmark spatio-temporal prediction models
• predict on-demand service demand

When to choose

• you need a unified framework to reproduce and compare traffic prediction models
• you want standardized datasets and evaluation metrics for spatio-temporal research
• you are a researcher prototyping new traffic prediction models in PyTorch

When to avoid

• you need production traffic forecasting at scale rather than research experiments
• your task is general time-series forecasting unrelated to urban/spatial data
• you prefer TensorFlow or non-PyTorch ecosystems

Facets

library · maturity active

deep-learning machine-learning data-science benchmarking data-visualization machine-learning deep-learning data-science python cross-platform traffic-prediction spatio-temporal trajectory-prediction eta map-matching pytorch urban-computing research-toolkit algorithms gpu

Member repositories

For agents

markdown · JSON · MCP: product_card(name="LibCity/Bigscity-LibCity")