![]() |
OSnet is a python library to make T/S/MLD predictions in the Gulf Stream region using Neural Network |
---|---|
Methodology | Pauthenet et al, 2022 Method source code: https://github.com/euroargodev/OSnet |
OSnet gridded dataset | |
OSnet software to make your own predictions |
The folder docs
contains many advanced notebooks to get you started with making your OSnet predictions.
pip install git+http://github.com/euroargodev/OSnet-GulfStream.git
To create the OSnet
python development environment, you can:
conda env create -f ci/requirements/py3.8-dev.yml
Then, to make it available in Jupyter notebooks:
python -m ipykernel install --user --name=OSnet
Import library:
import osnet
import xarray as xr
Prepare inputs:
ds_in = xr.DataSet([...])
Load model and make prediction:
model = osnet.load('Gulf-Stream')
ds_out = model.predict(ds_in)
ds_out = model.predict(ds_in, adjust_mld=False) # Do not perform MLD adjustment
This repository has been developed at the Laboratory for Ocean Physics and Satellite remote sensing, Ifremer, within the framework of the Euro-ArgoRISE project. This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement no 824131. Call INFRADEV-03-2018-2019: Individual support to ESFRI and other world-class research infrastructures.