Improving Rule Mining for Entry, Descent, and Landing Simulations Using Knowledge Graphs

Abstract

Designing planetary entry, descent, and landing (EDL) systems requires analyzing large datasets containing tens of thousands of parameters. These datasets are generally manually analyzed by subject-matter experts trying to find interesting correlations and couplings between parameters that explain the behaviors observed. A popular approach to automate the extraction of explanation rules is association rule mining, in which rules with high statistical strength are mined from the dataset. However, current rule mining algorithms generate too many rules that are redundant, too complex, too obvious, or do not make sense to the user. In this paper, we propose a new approach to improve the comprehensibility, insightfulness, and usefulness of the association rules generated during the analysis of an EDL dataset by leveraging a user-provided knowledge graph. The knowledge graph captures the user knowledge about EDL and the specific problem at hand. We then use a statistical relational learning framework based on probabilistic soft logic to assess the degree of consistency of the rule with the user’s knowledge of the system. The method is validated in a small study with subject-matter experts. The results of the study also show interesting relationships between comprehensibility, usefulness, and insightfulness of the extracted rules.