Symbolic Knowledge Extraction from Opaque Predictors Applied to Cosmic-Ray Data Gathered with LISA Pathfinder

TL;DR

This paper demonstrates how symbolic knowledge extraction can interpret complex machine learning models used in space missions, specifically analyzing cosmic-ray data from the LISA Pathfinder, balancing explanation clarity and fidelity.

Contribution

It applies and compares different symbolic knowledge extractors to an ensemble predictor for cosmic-ray data, highlighting interpretability in space mission ML models.

Findings

Effective symbolic explanations were obtained for cosmic-ray data predictions.

Trade-offs between readability and fidelity of extracted knowledge were analyzed.

The approach enhances understanding of opaque models in space applications.

Abstract

Machine learning models are nowadays ubiquitous in space missions, performing a wide variety of tasks ranging from the prediction of multivariate time series through the detection of specific patterns in the input data. Adopted models are usually deep neural networks or other complex machine learning algorithms providing predictions that are opaque, i.e., human users are not allowed to understand the rationale behind the provided predictions. Several techniques exist in the literature to combine the impressive predictive performance of opaque machine learning models with human-intelligible prediction explanations, as for instance the application of symbolic knowledge extraction procedures. In this paper are reported the results of different knowledge extractors applied to an ensemble predictor capable of reproducing cosmic-ray data gathered on board the LISA Pathfinder space mission. A discussion about the readability/fidelity trade-off of the extracted knowledge is also presented.