Official code from the paper that you can find in the following link: https://arxiv.org/pdf/2011.03303.pdf
Some animation of the actual vs prediction of the AsymmInceptionRes-3DDR-UNet model, using a 48h ahead prediction:
| Variable | Actual Vs Prediction |
|---|---|
| Sea Surface Height | 
|
| Sea Water Salinity | 
|
| Eastward Current Velocity | 
|
| Northward Current Velocity | 
|
Note: the dark area is made of pixels that correspond to the land.
The required modules can be installed via:
pip install -r requirements.txtTo launch the training, please run:
python train_selected_model.py- The scripts contain the models, the data preprocessing, as well as the training files.
We show here the schema related to the AsymmInceptionRes-3DDR-UNet model.
In order to download the data, please email to the following addresses:
j.garciafernandez@student.maastrichtuniversity.nl
i.alaouiabdellaoui@student.maastrichtuniversity.nl
siamak.mehrkanoon@maastrichtuniversity.nl
The data must be downloaded and unzipped inside the 'Data/' directory.
If you use our data and code, please cite the paper using the following bibtex reference:
@article{Fernández2020coastal,
title={Coastal sea elements prediction using U-Net based models},
author={García Fernández, Jesús and Alaoui Abdellaoui, Ismail and Mehrkanoon, Siamak},
journal={arXiv preprint arXiv:2011.03303},
year={2020}
}