Guiding Scientific Discovery with Explanations Using DEMUD

Abstract

In the era of large scientific data sets, there is an urgent need for methods to automatically prioritize data for review. At the same time, for any automated method to be adopted by scientists, it must make decisions that they can understand and trust. In this paper, we propose Discovery through Eigenbasis Modeling of Uninteresting Data (DEMUD), which uses principal components modeling and reconstruction error to prioritize data. DEMUD’s major advance is to offer domain-specific explanations for its prioritizations. We evaluated DEMUD’s ability to quickly identify diverse items of interest and the value of the explanations it provides. We found that DEMUD performs as well or better than existing class discovery methods and provides, uniquely, the first explanations for why those items are of interest. Further, in collaborations with planetary scientists, we found that DEMUD (1) quickly identifies very rare items of scientific value, (2) maintains high diversity in its selections, and (3) provides explanations that greatly improve human classification accuracy.

The Solar System Notification Alert Processing System (SNAPS): Asteroid Population Outlier Detection

“…Regarding (2) above, the notion of accelerating the scientific discovery process by augmenting a human researcher with machine support has been described in other works, which address providing multiple data variants to a user or guiding the scientific discovery process through data prioritization (Wagstaff et al 2013;Pankratius et al 2016). Population outlier detection across numerous multidimensional feature spaces provides both data prioritization and variant exploration.…”

Mineral classification on Martian surface using CRISM hyperspectral data: a survey

“…88 to cluster super-pixels to reduce redundancy in identified minerals and make more confident from the respective region on the Martian surface, followed by DEMUD analysis on the super-pixels to assign a label based on threshold operation for anomaly detection to find rare minerals. This method has been applied to Hesperia Planum (Fe/Mg smectite), Aram Chaos (jarosite, kieserite), and Juventae Chasma (Mg-olivine, monohydrated sulfate) 88 , 108 …”