Despite the increasingly successful application of neural networks to many problems in the geosciences, their complex and nonlinear structure makes the interpretation of their predictions difficult, which limits model trust and does not allow scientists to gain physical insights about the problem at hand. Many different methods have been introduced in the emerging field of eXplainable Artificial Intelligence (XAI), which aim at attributing the networks prediction to specific features in the input domain. XAI methods are usually assessed by using benchmark datasets (like MNIST or ImageNet for image classification), or through deletion/insertion techniques. In either case, however, an objective, theoretically-derived ground truth for the attribution is lacking, making the assessment of XAI in many cases subjective. Also, benchmark datasets for problems in geosciences are rare. 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. We generate a long benchmark dataset and train a fully-connected network to learn the underlying function that was used for simulation. We then compare estimated attribution heatmaps from different XAI methods to the ground truth in order to identify examples where specific XAI methods perform well or poorly. We believe that attribution benchmarks as the ones introduced herein are of great importance for further application of neural networks in the geosciences, and for accurate implementation of XAI methods, which will increase model trust and assist in discovering new science.
تحميل البحث