Lunar Landing Site Selection using Machine Learning

The value of a planetary landing mission is critically dependent on the choice of landing sites which are generally influenced by several scientific and engineering constraints. The conventional method for Landing Site (LS) selection requires the manual analyses of individual sites involving a large talent force of multi-domain experts hence rendering the process cumbersome and expensive. Simultaneously, the currently employed methodology of recycling previously selected LSs for future missions would not be realized in the case of hitherto unexplored planets. As a consequence, machine learning algorithms are being actively explored in aiding effective space exploration. However, their application to selection of LSs that satisfy the scientific and engineering requirements of a mission have not yet been explored. In this paper, we propose an end-to-end Landing Site selection methodology using Moon as a case study and employing Hierarchical clustering of regions based on their altitude, expandable to other planets. Furthermore, we enforce commonly used constraints on the potential sites and select final sites for landing based on the user provided scientific and engineering constraints. With this approach, the LS selection process is simplified and the temporal requirement is reduced.