Quantus x Climate: Applying Explainable AI Evaluation in Climate Science

In climate science, explainable artificial intelligence (XAI) can be used to improve and validate deep learning methods, but evaluation and selection of XAI methods is challenging. Learn how to use the explainable AI evaluation package Quantus to compare and select an appropriate XAI for your climate AI research task.

Author(s):

• Philine Lou Bommer, Technische Universität Berlin & Leibniz Institute of Agricultural Engineering and Bio-economy Potsdam, pbommer@atb-potsdam.de
• Anna Hedstroem, Technische Universität Berlin & Leibniz Institute of Agricultural Engineering and Bio-economy Potsdam, ahedstroem@atb-potsdam.de
• Marlene Kretschmer, University of Reading & University of Leipzig, m.j.a.kretschmer@reading.ac.uk
• Marina M.-C. Hoehne, University of Potsdam & Leibniz Institute of Agricultural Engineering and Bio-economy Potsdam, mhoehne@atb-potsdam.de

Originally presented at ICLR 2023

Access this tutorial

We recommend executing this notebook in a Colab environment to gain access to GPUs and to manage all necessary dependencies.

Estimated time to execute end-to-end: 30 minutes

Contribute to this tutorial

Please refer to these GitHub instructions to open a pull request via the "fork and pull request" workflow.

Pull requests will be reviewed by members of the Climate Change AI Tutorials team for relevance, accuracy, and conciseness.

Climate Change AI Tutorials

Check out the tutorials page on our website for a full list of tutorials demonstrating how AI can be used to tackle problems related to climate change.

License

Usage of this tutorial is subject to the MIT License.

Cite

Plain Text

Bommer, P., Hedstroem, A., Kretschmer, M., & Hoehne, M. (2023). Quantus x Climate: Applying Explainable AI Evaluation in Climate Science [Tutorial]. In International Conference on Learning Representations. Climate Change AI. https://doi.org/10.5281/zenodo.11622537

BibTeX

@misc{bommer2023quantus,
  title={Quantus x Climate: Applying Explainable AI Evaluation in Climate Science},
  author={Bommer, Philine and Hedstroem, Anna and Kretschmer, Marlene and Hoehne, Marina},
  year={2023},
  organization={Climate Change AI},
  type={Tutorial},
  doi={https://doi.org/10.5281/zenodo.11622537},
  booktitle={International Conference on Learning Representations},
  howpublished={\url{https://github.com/climatechange-ai-tutorials/quantus-x-climate}}
}