Pluto's Surface Mapping using Unsupervised Learning from Near-Infrared Observations of LEISA/Ralph

TL;DR

This study demonstrates that unsupervised machine learning can effectively map Pluto's surface composition from near-infrared data without prior labels, revealing geographic and compositional patterns consistent with previous findings.

Contribution

The paper introduces an unsupervised Gaussian mixture model approach for planetary surface mapping, eliminating the need for prior spectral indices or radiative transfer models.

Findings

Successful mapping of Pluto's surface units using unsupervised learning.

Identification of latitudinal compositional patterns consistent with prior studies.

Method applicable to other planetary bodies with limited labeled data.

Abstract

We map the surface of Pluto using an unsupervised machine learning technique using the near-infrared observations of the LEISA/Ralph instrument onboard NASA's New Horizons spacecraft. The principal component reduced Gaussian mixture model was implemented to investigate the geographic distribution of the surface units across the dwarf planet. We also present the likelihood of each surface unit at the image pixel level. Average I/F spectra of each unit were analyzed -- in terms of the position and strengths of absorption bands of abundant volatiles such as N${}_{2}$, CH${}_{4}$, and CO and nonvolatile H${}_{2}$O -- to connect the unit to surface composition, geology, and geographic location. The distribution of surface units shows a latitudinal pattern with distinct surface compositions of volatiles -- consistent with the existing literature. However, previous mapping efforts were based primarily on compositional analysis using spectral indices (indicators) or implementation of complex radiative transfer models, which need (prior) expert knowledge, label data, or optical constants of representative endmembers. We prove that an application of unsupervised learning in this instance renders a satisfactory result in mapping the spatial distribution of ice compositions without any prior information or label data. Thus, such an application is specifically advantageous for a planetary surface mapping when label data are poorly constrained or completely unknown, because an understanding of surface material distribution is vital for volatile transport modeling at the planetary scale. We emphasize that the unsupervised learning used in this study has wide applicability and can be expanded to other planetary bodies of the Solar System for mapping surface material distribution.