EarthyScience/EasyHybrid.jl

EasyHybrid.jl provides a simple and flexible framework for hybrid modeling, enabling the integration of neural networks with process-based models.

47
/ 100
Emerging

This tool helps environmental scientists and ecological modelers improve predictions for complex systems like ecosystem respiration. It takes time-series data with environmental conditions and outputs more accurate forecasts by combining established scientific formulas with data-driven neural networks. Researchers studying natural processes can use this to build robust predictive models.

Use this if you need to build predictive models for environmental or biological systems and want to integrate both your scientific understanding (process-based models) and observed data (neural networks) for better accuracy.

Not ideal if your problem does not involve both a well-understood physical or biological process and available observational data for machine learning.

environmental-modeling ecological-prediction hydrology climate-science geoscience
No Package No Dependents
Maintenance 10 / 25
Adoption 6 / 25
Maturity 15 / 25
Community 16 / 25

How are scores calculated?

Stars

16

Forks

6

Language

Julia

License

MIT

Last pushed

Mar 13, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/EarthyScience/EasyHybrid.jl"

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