NASA与IBM发布开源月球基础模型，基于17年轨道数据
原标题：NASA and IBM's open source lunar model turns 17 years of orbiter data into a foundation for lunar science
AI 摘要
NASA 与 IBM Research 联合多家学术机构发布了 NASA-IBM Lunar Foundation Model，称其为首批面向月球科学的开源基础模型之一。该模型基于 TerraMind 架构从零训练，使用包含近 200 万个瓦片、11 种模态的 SomBench 数据集，数据主要来自月球勘测轨道飞行器 17 年的观测。在极地冰沉积预测任务上，模型相比最佳基线 SwinV2-B 将误差降低最多 22%，粗尺度陨石坑检测提升近 19%。模型已在 Hugging Face 和 GitHub 公开，并集成到 TerraTorch 工具包中。
正文节选
NASA and IBM's open source lunar model turns 17 years of orbiter data into a foundation for lunar science The NASA-IBM Lunar Foundation Model makes decades of lunar observation data usable for machine learning. It's especially strong at predicting ice deposits at the poles and detecting craters. "NASA has spent decades building an extraordinary scientific record of the Moon, but collecting data is only part of the job," says Kevin Murphy, NASA's chief science data officer. The data also has to b