The selection of landing and operation sites for planetary missions represents a complex challenge that requires the integration of geological, geomorphological, and hazard-related criteria with mission and operational constraints, such as illumination, thermal cycles, communication windows, and the presence of subsurface ice. The goal of this session is to promote a systemic approach to the design of workflows capable of explicitly encoding and integrating these diverse requirements. Automated pipelines for orbital data mapping and classification will be presented, including the acquisition of images and digital elevation models, the automatic extraction of features through artificial intelligence or rule-based methods (such as crater identification, regolith depth estimation, or slope hazard assessment), and multi-criteria classification with uncertainty quantification. Special emphasis will be on best practices for code sharing, ensuring scalability and compatibility from laptops to high-performance clusters via containerized environments (Docker, Podman), standardized data formats, and community APIs to enable seamless interoperability between GIS, photogrammetry, and mission planning software.

The session also aims to stimulate the development of a collaborative and sustainable ecosystem based on shared requirement repositories and living documentation of best practices, promoting innovation while ensuring transparency and continuity. The overarching objective is to catalyze an interdisciplinary community that, by integrating tools, data, and knowledge, can effectively support landing site selection for future robotic and crewed missions, moving beyond a purely geology-centered approach toward a more integrated and scalable vision.