发表机构
Institut de Recherche Technologique Saint Exupéry（圣埃克苏佩里技术研究学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究针对Φsat-2任务开发轻量型海洋异常检测流水线，经仿真训练后因仿真与在轨数据不匹配，改用真实Level-1影像重训提升性能，验证了星载AI的可行性及仿真开发的价值。
AI 中文摘要
星载人工智能可通过在卫星上直接处理数据，提升地球观测系统的响应速度与带宽效率。本文介绍了欧洲空间局Φsat-2任务中部署的轻量型海洋异常检测流水线的开发、星载集成及发射后适配经验。该应用结合了海域分割、海洋区域的自监督特征编码、基于正常海态偏差的通用异常检测，以及可选的选定异常类型表征。发射前，该流水线在仿真Φsat-2影像上完成训练与验证，以评估算法性能及与资源受限星载硬件的兼容性。在任务环境中完成集成与功能验证后，对真实Φsat-2采集数据的早期实验显示，仿真数据与在轨数据存在显著不匹配。因此，研究人员采用改进的标注策略，在真实Level-1影像上对流水线进行重新训练，以更好地处理模糊海洋区域，大幅提升了性能。除了证明该应用的星载可行性外，Φsat-2的经验还凸显了鲁棒标注策略与感知传感器设计的重要性，表明基于仿真的开发对降低发射前风险具有价值，而可靠的科学验证需要具有代表性的在轨数据，且应与功能验证明确区分。
英文摘要
Onboard Artificial Intelligence can improve responsiveness and bandwidth efficiency of Earth Observation systems by processing data directly on the satellite. This paper presents the experience gained from the development, onboard integration, and post-launch adaptation of a lightweight marine anomaly detection pipeline deployed on the European Space Agency's $Φ$sat-2 mission. The application combines sea segmentation, self-supervised feature encoding of marine regions, generic anomaly detection based on deviations from a normal sea state, and optional characterization of selected anomaly types. Before launch, the pipeline was trained and validated on simulated $Φ$sat-2 imagery to assess algorithmic performance and compatibility with resource-constrained onboard hardware. After integration and functional validation in the mission environment, early experiments on real $Φ$sat-2 acquisitions revealed a significant mismatch between simulated and in-orbit data. The pipeline was therefore retrained on real Level-1 imagery using an improved annotation strategy to better handle ambiguous marine regions, substantially enhancing performance. Beyond demonstrating the onboard feasibility of the application, the $Φ$sat-2 experience highlights the importance of robust annotation strategies and sensor-aware design, and shows that simulation-based development is valuable for pre-flight risk reduction, while reliable scientific validation requires representative in-orbit data and should be clearly distinguished from functional validation.
