loading page

Unsupervised Distribution Learning for Lunar Surface Technosignature Detection
  • Daniel Angerhausen,
  • Valentin Tertius Bickel,
  • Lesnikowski Adam
Daniel Angerhausen
ETH, BMSIS, ETH, BMSIS

Corresponding Author:daniel.angerhausen@gmail.com

Author Profile
Valentin Tertius Bickel
Swiss Federal Institute of Technology in Zurich,Max Planck Institute for Solar System Research
Author Profile
Lesnikowski Adam
NVIDIA
Author Profile

Abstract

In this work we show that modern data-driven machine learning techniques can be successfully applied on lunar surface remote sensing data to learn, in an unsupervised way, sufficiently good representations of the data distribution to enable lunar technosignature and anomaly detection. In particular we have trained an unsupervised distribution learning model to find the landing module of the Apollo 15 landing site in a testing dataset, with no specific model or hyperparameter tuning .