Using explainability to design physics-aware CNNs for solving subsurface inverse problems

TL;DR

This paper introduces a novel approach using explainability techniques to design physics-aware CNNs for subsurface inverse problems, improving interpretability without sacrificing predictive accuracy.

Contribution

The study demonstrates how explainability methods can guide hyperparameter selection to develop more interpretable physics-aware CNNs for geophysical imaging.

Findings

Shallow CNN with two convolutional layers performs comparably to deeper networks.

Explainability methods help evaluate model complexity and decision-making.

Atypical kernel size (3x1) enhances model interpretability.

Abstract

We present a novel method of using explainability techniques to design physics-aware neural networks. We demonstrate our approach by developing a convolutional neural network (CNN) for solving an inverse problem for shallow subsurface imaging. Although CNNs have gained popularity in recent years across many fields, the development of CNNs remains an art, as there are no clear guidelines regarding the selection of hyperparameters that will yield the best network. While optimization algorithms may be used to select hyperparameters automatically, these methods focus on developing networks with high predictive accuracy while disregarding model explainability (descriptive accuracy). However, the field of Explainable Artificial Intelligence (XAI) addresses the absence of model explainability by providing tools that allow developers to evaluate the internal logic of neural networks. In this study, we use the explainability methods Score-CAM and Deep SHAP to select hyperparameters, such as kernel sizes and network depth, to develop a physics-aware CNN for shallow subsurface imaging. We begin with a relatively deep Encoder-Decoder network, which uses surface wave dispersion images as inputs and generates 2D shear wave velocity subsurface images as outputs. Through model explanations, we ultimately find that a shallow CNN using two convolutional layers with an atypical kernel size of 3x1 yields comparable predictive accuracy but with increased descriptive accuracy. We also show that explainability methods can be used to evaluate the network's complexity and decision-making. We believe this method can be used to develop neural networks with high predictive accuracy while also providing inherent explainability.