Automated detection of craters on the lunar surface using deep learning: A review with insights from Chandrayaan-2 TMC-2 data

Abstract

The Moon’s surface, marked by craters, serves as a crucial record of the Solar System's impact history, offering key insights into planetary formation and evolution. As missions like Chandrayaan-2 generate vast amounts of high-resolution lunar data, manual annotation of features such as craters, rilles, and lava tubes become increasingly impractical. Automated lunar crater detection has thus become essential to process and analyze these growing datasets efficiently. This review explores recent advancements in deep learning (DL) and machine learning (ML) techniques applied to lunar crater detection, with a focus on the Chandrayaan-2 Terrain Mapping Camera-2 (TMC-2) data. Following PRISMA guidelines, the paper outlines state-of-the-art methodologies, datasets, and challenges in this field while offering insights into sensor capabilities and future research directions. The review aims to provide a comprehensive understanding of the current landscape and highlight potential avenues to advance the automation of crater detection on the lunar surface.