Skip to content

Mitigating loss of variance in ensemble data assimilation: machine learning-based and distance-free localization for better covariance estimation

License

Notifications You must be signed in to change notification settings

viluiz/ml_localization

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Machine Learning Localization

This repository is the official implementation of:

Mitigating loss of variance in ensemble data assimilation: machine learning-based and distance-free localization

Directories

  • data: data files to test the ML-localization.
  • ml_localization: ML-localization module folder.

Requirements

To install requirements:

 $ pip install -r requirements.txt

Usage

To run ML-localization (help):

 $ python -m ml_localization -h

or

 $ python ./run.py -h

To run ML-localization on data folder:

 $ python -m ml_localization -m 20 -d 1530 -M data/M.bin -D data/D.bin -Ms data/Msuper.bin -Ds data/Dsuper.bin -R data/R.bin -l data/ml_localization.log

or

 $ python ./run.py -m 20 -d 1530 -M data/M.bin -D data/D.bin -Ms data/Msuper.bin -Ds data/Dsuper.bin -R data/R.bin -l data/ml_localization.log

About

Mitigating loss of variance in ensemble data assimilation: machine learning-based and distance-free localization for better covariance estimation

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages