English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

We map the surface of Pluto using an unsupervised machine learning techniqueusing the near-infrared observations of the LEISA/Ralph instrument onboardNASA's New Horizons spacecraft. The principal component reduced Gaussianmixture model was implemented to investigate the geographic distribution of thesurface units across the dwarf planet. We also present the likelihood of eachsurface unit at the image pixel level. Average I/F spectra of each unit wereanalyzed -- in terms of the position and strengths of absorption bands ofabundant volatiles such as N${}_{2}$, CH${}_{4}$, and CO and nonvolatileH${}_{2}$O -- to connect the unit to surface composition, geology, andgeographic location. The distribution of surface units shows a latitudinalpattern with distinct surface compositions of volatiles -- consistent with theexisting literature. However, previous mapping efforts were based primarily oncompositional analysis using spectral indices (indicators) or implementation ofcomplex radiative transfer models, which need (prior) expert knowledge, labeldata, or optical constants of representative endmembers. We prove that anapplication of unsupervised learning in this instance renders a satisfactoryresult in mapping the spatial distribution of ice compositions without anyprior information or label data. Thus, such an application is specificallyadvantageous for a planetary surface mapping when label data are poorlyconstrained or completely unknown, because an understanding of surface materialdistribution is vital for volatile transport modeling at the planetary scale.We emphasize that the unsupervised learning used in this study has wideapplicability and can be expanded to other planetary bodies of the Solar Systemfor mapping surface material distribution.

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