ClimateLearn is a Python library for accessing state-of-the-art climate data and machine learning models in a standardized, straightforward way. This library provides access to multiple datasets, a zoo of baseline approaches, and a suite of metrics and visualizations for large-scale benchmarking of statistical downscaling and temporal forecasting methods. For further context on our past motivation and future plans, check out our announcement blog post.
Python3 is required.
pip install climate-learn
We have a series of tutorial Jupyter notebooks in the notebooks folder. We recommend reading them in the following order to see a typical ClimateLearn workflow.
- Data Processing
- Model Training & Evaluation
- Visualization
To run the notebooks, please upload them to Google Colab.
We also previewed some key features of ClimateLearn at a spotlight tutorial in the "Tackling Climate Change with Machine Learning" Workshop at the Neural Information Processing Systems 2022 Conference. The slides and recorded talk can be found on Climate Change AI's website.
Find us on ReadTheDocs.
ClimateLearn is managed by the Machine Intelligence Group at UCLA, headed by Professor Aditya Grover.
Contributions are welcome! See our contributing guide.
If you use ClimateLearn, please see the CITATION.cff file or use the citation prompt provided by GitHub in the sidebar.