Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

A Machine Learning Approach to Detecting Albedo Anomalies on the Lunar Surface

Sofia Strukova, Sergei Gleyzer, Patrick Peplowski, Jason P. Terry

TL;DR

This work investigates how lunar surface albedo relates to chemical composition by integrating high-resolution optical maps with gamma-ray elemental maps through a data-driven pipeline. It tackles a major challenge—resolution disparity between datasets—by applying both standard and adaptive Gaussian blurs and training an Extreme Gradient Boosting Regression model to predict full albedo from elemental abundances. An interactive error-visualization tool exposes where predictions deviate from observations, linking these errors to regional geology and optical maturity. The approach yields a predictive framework transferable to other airless bodies, enabling more informed planning for future missions and data collection.

Abstract

This study introduces a data-driven approach using machine learning (ML) techniques to explore and predict albedo anomalies on the Moon's surface. The research leverages diverse planetary datasets, including high-spatial-resolution albedo maps and element maps (LPFe, LPK, LPTh, LPTi) derived from laser and gamma-ray measurements. The primary objective is to identify relationships between chemical elements and albedo, thereby expanding our understanding of planetary surfaces and offering predictive capabilities for areas with incomplete datasets. To bridge the gap in resolution between the albedo and element maps, we employ Gaussian blurring techniques, including an innovative adaptive Gaussian blur. Our methodology culminates in the deployment of an Extreme Gradient Boosting Regression Model, optimized to predict full albedo based on elemental composition. Furthermore, we present an interactive analytical tool to visualize prediction errors, delineating their spatial and chemical characteristics. The findings not only pave the way for a more comprehensive understanding of the Moon's surface but also provide a framework for similar studies on other celestial bodies.

A Machine Learning Approach to Detecting Albedo Anomalies on the Lunar Surface

TL;DR

This work investigates how lunar surface albedo relates to chemical composition by integrating high-resolution optical maps with gamma-ray elemental maps through a data-driven pipeline. It tackles a major challenge—resolution disparity between datasets—by applying both standard and adaptive Gaussian blurs and training an Extreme Gradient Boosting Regression model to predict full albedo from elemental abundances. An interactive error-visualization tool exposes where predictions deviate from observations, linking these errors to regional geology and optical maturity. The approach yields a predictive framework transferable to other airless bodies, enabling more informed planning for future missions and data collection.

Abstract

This study introduces a data-driven approach using machine learning (ML) techniques to explore and predict albedo anomalies on the Moon's surface. The research leverages diverse planetary datasets, including high-spatial-resolution albedo maps and element maps (LPFe, LPK, LPTh, LPTi) derived from laser and gamma-ray measurements. The primary objective is to identify relationships between chemical elements and albedo, thereby expanding our understanding of planetary surfaces and offering predictive capabilities for areas with incomplete datasets. To bridge the gap in resolution between the albedo and element maps, we employ Gaussian blurring techniques, including an innovative adaptive Gaussian blur. Our methodology culminates in the deployment of an Extreme Gradient Boosting Regression Model, optimized to predict full albedo based on elemental composition. Furthermore, we present an interactive analytical tool to visualize prediction errors, delineating their spatial and chemical characteristics. The findings not only pave the way for a more comprehensive understanding of the Moon's surface but also provide a framework for similar studies on other celestial bodies.
Paper Structure (12 sections, 8 figures)

This paper contains 12 sections, 8 figures.

Table of Contents

  1. Introduction
  2. Methodology
  3. Results
  4. Blurring
  5. Interactive Analyzer
  6. User-Configurable Parameters
  7. Discussion
  8. Observations
  9. Optical Maturity
  10. Limitations
  11. Conclusions
  12. Acknowledgments

Figures (8)

  • Figure 1: Overview of the methodology to predict the full albedo
  • Figure 2: Original (in the left) and blurred (in the right) images of the Moon
  • Figure 3: The difference between the adaptive and the standard blurring
  • Figure 4: Maps of the amount of sigma applied to each pixel of the image
  • Figure 5: R2 score and root-mean-square error for each blurring configuration
  • ...and 3 more figures