wass2s: A python-based tool for seasonal climate forecast

wass2s is a comprehensive tool developed to enhance the accuracy and reproducibility of seasonal forecasts in West Africa and the Sahel. This initiative aligns with the World Meteorological Organization's (WMO) guidelines for objective, operational, and scientifically rigorous seasonal forecasting methods.

Overview

The wass2s tool is designed to facilitate the generation of seasonal forecasts using various statistical and machine learning methods including the Exploration of AI methods. It helps forecaster to download data, build models, verify the models, and forecast. A user-friendly jupyter-lab notebook streaming the process of prevision.

🚀 Features

✅ Automated Forecasting: Streamlines the seasonal forecasting process, reducing manual interventions.
🔄 Reproducibility: Ensures that forecasts can be consistently reproduced and evaluated.
📊 Modularity: Highly modular tool. Users can easily customize and extend the tool to meet their specific needs.
🤖 Exploration of AI and Machine Learning: Investigates the use of advanced technologies to further improve forecasting accuracy.

📥 Installation

Download and Install miniconda

For Windows, download the executable here

For Linux (Ubuntu), in the terminal run:

sudo apt-get update
sudo apt-get upgrade
sudo apt-get install wget
wget -c -r https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh --no-check-certificate
bash Miniconda3-latest-Linux-x86_64.sh

Create an environment and activate

For Windows: download yaml here and run

conda env create -f WAS_S2S_windows.yml
conda activate WASS2S

For Linux: download yaml here and run

conda env create -f WAS_S2S_linux.yml
conda activate WASS2S

Install wass2s

pip install wass2s

Download notebooks for simulation

git clone https://github.com/hmandela/WASS2S_notebooks.git

Create CDS API key and use it to download NMME and C3S models data from the Climate Data Store (CDS) and IRI Data Library.

Create an account with Copernicus by signing up here
Once you successfully create an account, kindly log in to your Copernicus account and click on your name at the top right corner of the page. Note your "UID" and "Personal Access Token key".
Configure .cdsapirc file.

In your activated terminal, kindly initiate the Python interpreter by entering the command python3. Subsequently, carefully copy and paste the below code, ensuring to replace "Personal Access Token" with yours.

import os

config_data = '''url: https://cds.climate.copernicus.eu/api
key: Personal Access Token
verify: 0
'''

path_to_home = "/".join([os.path.expanduser('~'),".cdsapirc"])

if not os.path.exists(path_to_home):
    with open(path_to_home, 'w') as file:
        file.write(config_data)
        
print("Configuration file created successfully!")

Upgrade wass2s

If you want to upgrade wass2s to a newer version, use the following command:

pip install --upgrade wass2s

Potential Issues

If you encounter matplotlib errors, try the following steps:

Install this version of matplotlib:
```
pip install matplotlib==3.7.3
```

Install the latest version of cartopy:

conda install -c conda-forge -c hallkjc01 xcast

If you encounter other issues during installation or usage, please refer to the Troubleshooting Guide.

⚙️ Usage

Comprehensive usage guidelines, including data preparation, model configuration, and execution steps, are available in the wass2s documentation, wass2S Training Documentation.

🤝 Contributing

We welcome contributions from the community to enhance the WAS_S2S tool. Please refer to our contribution guidelines for more information.

📜 License

This project is licensed under the GPL-3 License.

Contact

For questions or support, please open a Github issue.

Credits

scikit-learn: scikit-learn
EOF analysis: xeofs
xcast: xcast
xskillscore: xskillscore
... and many more!

🙌 Acknowledgments

I would like to express my sincere gratitude to all the participants of the job-training on the new generation of seasonal forecasts in West Africa and the Sahel.
Your valuable feedback has significantly contributed to the improvement of this tool. I look forward to continuing to receive your insights and, where possible, your contributions.
A seed has been planted within you—now, let’s grow it together.

We also extend our heartfelt thanks to the AICCRA project for supporting this development, and to Dr. Abdou ALI, Head of the Climate-Water-Meteorology Department at AGRHYMET RCC-WAS, for his guidance and support.

📖 For more detailed information, tutorials, and support, please visit the

Metadata

Release files for wass2s 0.4.10.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for wass2s 0.4.10.5
File	Size	Uploaded	Provenance
wass2s-0.4.10.5.tar.gz	541.9 kB	Aug 18, 2026	Without provenance	Details

Built distribution (wheel)

Table of built distributions (wheels) for wass2s 0.4.10.5
File	Interpreter	ABI	Platform	Reset
wass2s-0.4.10.5-py3-none-any.whl 552.7 kB Aug 18, 2026 Without provenance	Python 3	none	any	Details

Total release size: 1.1 MB

Release files / wass2s-0.4.10.5.tar.gz

Download URL	wass2s-0.4.10.5.tar.gz
Size	541.9 kB
Tags	Source
SHA-256 checksum How to use checksums	`bb72d881f3affc0cf6e330c1e754905a4be36d1ef50f41db6dca696f3b04ab6c`
BLAKE2b-256 checksum How to use checksums	`220bd8b71076db09dcddc655fd13074929b631b50b99f6c0dd21ecd5f26d9b0f`
Upload date	Aug 18, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.12.5`

Release files / wass2s-0.4.10.5-py3-none-any.whl

Download URL	wass2s-0.4.10.5-py3-none-any.whl
Size	552.7 kB
Tags	Python 3
SHA-256 checksum How to use checksums	`b14630977c4d9480ebcf65bca12ec18805dbef5bb601b707b56ff1ed8a401746`
BLAKE2b-256 checksum How to use checksums	`4d115eea55cc79827cadfe9e8d7a0044de8a467a4ffa0850c4f9684a8eeb46a0`
Upload date	Aug 18, 2026
Uploaded using Trusted Publishing? What is trusted publishing?	No
Uploaded via	`twine/6.2.0 CPython/3.12.5`

Security for wass2s 0.4.10.5

Report project as malware

Provenance

Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.

No provenance found

None of the files in this release were uploaded with provenance metadata.

A note on package security

PyPI is a repository for distributing packages, not a service for auditing them. While third-party security researchers and our staff do their best to detect and remove malicious packages, PyPI cannot guarantee the quality, security or suitability of any given package.