chengtan9907/OpenSTL
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
This project helps researchers and machine learning engineers evaluate and compare different methods for predicting how things change over time and space, like weather patterns or traffic flow. You input historical spatio-temporal data, and it outputs predictions for future states, along with metrics to assess various models. This is ideal for those developing or researching predictive models in dynamic fields.
1,075 stars.
Use this if you need a standardized platform to benchmark and experiment with different spatio-temporal predictive learning algorithms for tasks such as video prediction, weather forecasting, or traffic analysis.
Not ideal if you are looking for an out-of-the-box solution to directly apply to a business problem without delving into model development or research.
Stars
1,075
Forks
184
Language
Python
License
Apache-2.0
Category
Last pushed
Mar 01, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/chengtan9907/OpenSTL"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
NVIDIA/earth2studio
Open-source deep-learning framework for exploring, building and deploying AI weather/climate workflows.
mllam/neural-lam
Research Software for Neural Weather Prediction for Limited Area Modeling
NVIDIA/earth2mip
Earth-2 Model Intercomparison Project (MIP) is a python framework that enables climate...
aditya-grover/climate-learn
Source code for ClimateLearn
microsoft/aurora
Implementation of the Aurora model for Earth system forecasting