A unified framework for evaluating the robustness of machine-learning interpretability for prospect risking

TL;DR

This paper introduces a unified framework that evaluates the robustness of XAI methods like LIME and SHAP in geophysical prospect risking, using causal concepts to improve explanation reliability for high-dimensional data.

Contribution

It proposes a novel framework that generates counterfactuals and measures necessity and sufficiency to assess explanation robustness in complex geophysical datasets.

Findings

LIME and SHAP explanations vary significantly on complex data.

The framework identifies which XAI methods are more reliable with specific models.

Robustness evaluation reveals the models' ability to handle erroneous data.

Abstract

In geophysics, hydrocarbon prospect risking involves assessing the risks associated with hydrocarbon exploration by integrating data from various sources. Machine learning-based classifiers trained on tabular data have been recently used to make faster decisions on these prospects. The lack of transparency in the decision-making processes of such models has led to the emergence of explainable AI (XAI). LIME and SHAP are two such examples of these XAI methods which try to generate explanations of a particular decision by ranking the input features in terms of importance. However, explanations of the same scenario generated by these two different explanation strategies have shown to disagree or be different, particularly for complex data. This is because the definitions of "importance" and "relevance" differ for different explanation strategies. Thus, grounding these ranked features using theoretically backed causal ideas of necessity and sufficiency can prove to be a more reliable and robust way to improve the trustworthiness of the concerned explanation strategies.We propose a unified framework to generate counterfactuals as well as quantify necessity and sufficiency and use these to perform a robustness evaluation of the explanations provided by LIME and SHAP on high dimensional structured prospect risking data. This robustness test gives us deeper insights into the models capabilities to handle erronous data and which XAI module works best in pair with which model for our dataset for hydorcarbon indication.