IPSL-AID v0.1.0
This is the initial release of IPSL-AID (AI-based Climate Downscaling).
Features
- U-Net architecture for precipitation downscaling
- ERA5 data loader with CDS integration
- Complete training and inference pipelines
- Diffusion models support
- Comprehensive test suite
- Pre-commit hooks for code quality
Documentation
Full documentation is available at: https://kardaneh.github.io/IPSL-AID/
Installation
# Clone the repository
git clone https://github.com/kardaneh/IPSL-AID.git
cd IPSL-AID
# Create and activate a virtual environment with Python 3.11
uv venv --python=python3.11
source .venv/bin/activate # On Windows: .venv\Scripts\activate
# Install dependencies
uv sync
# Install pre-commit hooks (optional, for development)
pre-commit install