将大型地理空间模型压缩为可在轨运行的轻量版本，实现太空中的实时地球观测分析。
First On-Orbit Demonstration of a Geospatial Foundation Model
- 基于视觉变换器的地理空间模型经压缩与领域适配，保留下游任务性能。
- 在两种飞行环境中验证，模型体积显著减小且资源消耗降低。
- 首次在国际空间站成功实现原位推理，适合需要轻量化智能的航天任务。
地理空间基础模型（GeoFMs）有望在数据有限条件下广泛泛化于地球观测（EO）任务，但其庞大体量限制了在资源受限的航天硬件上的部署。为此，我们提出了一种基于视觉变换器（ViT）的紧凑型GeoFM变体，在保持下游任务性能的同时，支持星上执行。在五个下游任务中评估，并在两种典型飞行环境中验证，结果表明模型压缩与领域适配对降低模型尺寸和资源需求至关重要，同时在实际运行条件下仍能保持高性能。我们进一步通过国际空间站上的IMAGIN-e载荷，实现了可靠的在轨推理。这些成果确立了从大型GeoFMs到可飞行、资源高效的部署路径，拓展了地球观测任务中星载AI的可行性。
原文摘要 · Abstract (English)
Geospatial foundation models (GeoFMs) promise broad generalisation capacity for Earth observation (EO) tasks, particularly under data-limited conditions. However, their large size poses a barrier to deployment on resource-constrained space hardware. To address this, we present compact variants of a Vision Transformer (ViT)-based GeoFM that preserve downstream task performance while enabling onboard execution. Evaluation across five downstream tasks and validation in two representative flight environments show that model compression and domain adaptation are critical to reducing size and resource demands while maintaining high performance under operational conditions. We further demonstrate reliable on-orbit inference with the IMAGIN-e payload aboard the International Space Station. These results establish a pathway from large GeoFMs to flight-ready, resource-efficient deployments, expanding the feasibility of onboard AI for EO missions.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。