no code implementations • 19 Aug 2022 • Antonios Mamalakis, Elizabeth A. Barnes, Imme Ebert-Uphoff
We highlight that different baselines can lead to different insights for different science questions and, thus, should be chosen accordingly.
1 code implementation • 7 Feb 2022 • Antonios Mamalakis, Elizabeth A. Barnes, Imme Ebert-Uphoff
Convolutional neural networks (CNNs) have recently attracted great attention in geoscience due to their ability to capture non-linear system behavior and extract predictive spatiotemporal patterns.
1 code implementation • 18 Mar 2021 • Antonios Mamalakis, Imme Ebert-Uphoff, Elizabeth A. Barnes
Here, we provide a framework, based on the use of additively separable functions, to generate attribution benchmark datasets for regression problems for which the ground truth of the attribution is known a priori.
Explainable artificial intelligence Explainable Artificial Intelligence (XAI) +1