tsinghua-fib-lab/KSTDiff-Urban-flow-generation

Official implementation of "Towards Generative Modeling of Urban Flow through Knowledge-enhanced Denoising Diffusion"(SIGSPATIAL'23)

38
/ 100
Emerging

This project helps urban planners, transportation analysts, and city developers generate realistic urban traffic flow patterns. By using real-world city data as input, it can produce simulated future or hypothetical traffic movements within cities like NYC, Washington D.C., and Baltimore. This tool is for professionals who need to model and understand how people move through a city.

No commits in the last 6 months.

Use this if you need to create synthetic yet realistic urban traffic flow data for planning, simulation, or analysis purposes.

Not ideal if you need to analyze real-time traffic or predict specific short-term traffic congestion, as this focuses on generating general patterns.

urban-planning transportation-modeling city-development traffic-simulation geographic-information-systems
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

25

Forks

5

Language

Python

License

MIT

Last pushed

Jan 24, 2024

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/tsinghua-fib-lab/KSTDiff-Urban-flow-generation"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.