edouardelasalles/stnn

Code for the paper "Spatio-Temporal Neural Networks for Space-Time Series Modeling and Relations Discovery"

47
/ 100
Emerging

This project helps researchers and scientists forecast complex changes across many interacting locations over time, such as temperature variations or environmental pollutants. It takes in historical measurements from different spatial points over time, along with information on how these points are physically connected. The output is a prediction of future values and an understanding of the underlying relationships driving these changes. This tool is ideal for scientists, environmental modelers, or urban planners dealing with interconnected sensor data.

121 stars. No commits in the last 6 months.

Use this if you need to predict future values for interconnected spatial locations and also want to uncover the hidden influences between these locations.

Not ideal if your data points are completely independent of each other, or if you only need simple time series forecasting without considering spatial interactions.

environmental-modeling climate-forecasting sensor-network-analysis geospatial-prediction complex-system-dynamics
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

121

Forks

43

Language

Jupyter Notebook

License

BSD-2-Clause

Last pushed

Aug 31, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/edouardelasalles/stnn"

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