---
id: ai-wq-package
version: "3.29"
license: unclear
license_treatment: permissive
maintenance: active
---

# AI-WQ-package — A python package to support forecast submission, visualisation and evaluation for S2S ML/AI prediction project

License: permissive · Maintenance: active · Downloads: 122.3K/mo

## What it is and what it does

AI-WQ-package is a research-focused Python library for the ECMWF AI Weather Quest competition. It provides tools to download training data, develop and evaluate sub-seasonal forecast models, and submit forecasts to the competition platform. The package wraps xarray for efficient NetCDF-based data handling and integrates dask for parallel computation, numpy for numerical operations, scipy for scientific algorithms, pandas for tabular data, matplotlib and cartopy for visualization, and requests for API communication.

The package is explicitly marked as sandbox-level software under active development and not suitable for operational use. It is intended for research, testing, and competition participation only. Support is best-effort through community channels rather than official ECMWF support.

Use it for:

- Download and prepare sub-seasonal weather training datasets for developing machine learning forecast models.
- Evaluate AI-based forecast predictions against ground truth using the competition's evaluation framework.
- Submit forecast results to the ECMWF AI Weather Quest competition platform.
- Visualize sub-seasonal forecast data and model outputs using integrated matplotlib and cartopy tools.
- Prototype and iterate on forecast models in a research environment with built-in data pipeline support.

## Worth the install?

AI-flagged interpretation of the facts above — verify before relying.

Supports participation in the ECMWF AI Weather Quest competition by enabling forecast submission, evaluation of sub-seasonal forecasts, and training data download for AI-based weather prediction models.

Yes, if you are actively participating in the ECMWF AI Weather Quest competition or conducting research on sub-seasonal forecasting. The low install friction, active maintenance, and permissive license support research use. No, if you need production-grade weather forecasting tools or operational deployment—the package explicitly disclaims such use and is sandbox-level software.

## Install

pip install ai-wq-package
uv add ai-wq-package
poetry add ai-wq-package

## Installing AI-WQ-package

Before you install: Low friction installation with a pure Python wheel. Active maintenance as of the latest release. Requires 9 runtime dependencies; consider a virtual environment if these conflict with your existing setup.

License in practice: Licensed under Apache License 2.0 (permissive). Suitable for research and competition use; explicitly not intended for operational or production deployment.

Quickstart:

python3 -m pip install AI-WQ-package

import ai_wq_package
# Download training data, develop forecasts, submit to competition

Requires Python 3.8 or higher; installation guidance specifies Linux.

Verify before relying:

- Whether the package's data download and submission features remain functional outside the competition window or require active competition registration.
- Performance characteristics when working with large multi-year training datasets via dask.
- Compatibility of cartopy visualization with non-Linux systems.

## Package facts

- License: not declared (permissive)
- Python support: supports_current
- Install friction: low
- Maintenance: active
- Downloads: 122.3K/month (top 15,000 on PyPI)
- Known vulnerabilities: none known

## Tags

weather forecast submission, sub-seasonal prediction tools, AI weather competition, forecast evaluation framework, weather model training data, ECMWF AI Weather Quest, NetCDF weather data handling, weather-forecasting, competition-framework, research-sandbox

[View on SkillFed](https://skillfed.io/packages/ai-wq-package) · [View on PyPI](https://pypi.org/project/ai-wq-package/)