Interactive Mars Image Content-Based Search with Interpretable Machine Learning
This work addresses the need for interpretable image classification to support scientific discovery and public engagement in planetary data, but it is incremental as it builds on existing prototype-based methods.
The paper tackled the problem of classifying Mars rover images with interpretability by using a prototype-based architecture to provide explanations and validate evidence, and it will be deployed on the NASA PDS Image Atlas to replace a non-interpretable system.
The NASA Planetary Data System (PDS) hosts millions of images of planets, moons, and other bodies collected throughout many missions. The ever-expanding nature of data and user engagement demands an interpretable content classification system to support scientific discovery and individual curiosity. In this paper, we leverage a prototype-based architecture to enable users to understand and validate the evidence used by a classifier trained on images from the Mars Science Laboratory (MSL) Curiosity rover mission. In addition to providing explanations, we investigate the diversity and correctness of evidence used by the content-based classifier. The work presented in this paper will be deployed on the PDS Image Atlas, replacing its non-interpretable counterpart.