Carefully choose the baseline: Lessons learned from applying XAI attribution methods for regression tasks in geoscience. (arXiv:2208.09473v1 [physics.geo-ph])

Methods of eXplainable Artificial Intelligence (XAI) are used in
geoscientific applications to gain insights into the decision-making strategy
of Neural Networks (NNs) highlighting which features in the input contribute
the most to a NN prediction. Here, we discuss our lesson learned that the task
of attributing a prediction to the input does not have a single solution.
Instead, the attribution results and their interpretation depend greatly on the
considered baseline (sometimes referred to as reference point) that the XAI
method …

arxiv attribution geoscience lessons learned physics regression xai