EdWangLoDaSc/DSOVT

Sample codes for training of dynamical system prediction from sparse observations using deep neural networks with Voronoi tessellation and physics constraints (DSOVT) by Wang et al.

12
/ 100
Experimental

This project helps oceanographers, meteorologists, or climate scientists predict complex environmental phenomena like sea surface temperatures or shallow water dynamics. It takes sparse, real-world observation data and uses deep learning, enhanced with physics rules, to generate highly accurate and efficient spatio-temporal predictions and rolling forecasts. This is designed for researchers or practitioners needing precise forecasting of dynamic natural systems.

No commits in the last 6 months.

Use this if you need to accurately predict how environmental systems evolve over time, especially when your observational data is incomplete or limited to specific locations.

Not ideal if you are looking for a simple, off-the-shelf forecasting tool that doesn't require familiarity with advanced deep learning or geostatistical methods.

oceanography meteorology environmental-forecasting climate-modeling hydrodynamics
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 4 / 25
Maturity 8 / 25
Community 0 / 25

How are scores calculated?

Stars

6

Forks

Language

Jupyter Notebook

License

Last pushed

Jun 11, 2024

Commits (30d)

0

Get this data via API

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

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