NASA-IBM 发布开源月球地理空间 AI 基础模型

这款开源人工智能模型整合多样化月球数据集，以支持对月球的科学分析

NASA-IBM 模型复现了月球冰存在潜力的空间模式（由蓝色至黄色表示，经缩放处理），图左展示了月球极区附近的四个位置。第一行：月球南极附近 Mons Mouton 的参考冰存在潜力地图；第二行：ConvNeXt 模型的预测结果；第三行：NASA-IBM 模型的预测结果。NASA-IBM 模型保留了参考数据中的许多细粒度存在潜力模式。图片来源：NASA/IBM Research

美国华盛顿特区，2026 年 9 月 18 日。 大学空间研究协会（USRA）为新近发布的 NASA-IBM Lunar Foundation Model 提供了行星科学专业知识、月球数据集开发和科学评估支持。该开源人工智能（AI）模型旨在帮助研究人员分析月球任务收集的大规模、多样化数据集。

由 NASA 和 IBM Research 主导合作开发的 NASA-IBM Lunar Foundation Model，使用 SomBench 从头进行预训练。SomBench 是一个多模态月球数据集，包含近 200 万个共配准数据包，覆盖 11 种数据模态和两种空间尺度。该模型整合了有关月球表面的互补信息，包括影像、地形、光照几何、热物理特性、矿物学、雷达、重力以及其他地质和环境数据。

USRA 对该项目的贡献由 USRA 科学与技术研究所副科学家 Rachel Slank 博士提供，她被派驻于 NASA 马歇尔太空飞行中心。她在 NASA-IBM Lunar Foundation Model 团队中担任行星科学领域专家。Slank 跨科学团队和建模团队开展工作，帮助将月球科学优先事项以及行星数据集的物理特性，与模型开发、应用和评估方面的决策联系起来。

NASA-IBM Lunar Foundation Model 在三项下游基准测试中接受评估：区域尺度和米级尺度的陨石坑检测、不规则月海斑块（IMPs）分割，以及月球极地冰存在潜力回归。这些应用共同评估了模型在多种月球科学挑战中的表现，涵盖识别撞击特征、绘制罕见火山地貌，以及整合与极地挥发物稳定性和潜在分布相关的环境数据集。

在全部三项基准测试中，经过预训练的 NASA-IBM Lunar Foundation Model 均达到或超过了基于 ImageNet 预训练的对照模型，以及一个架构相同但未进行月球预训练的初始化模型。该研究还显示，该模型在陨石坑检测中具有尤其突出的标签效率，表明通过月球预训练学习到的表征，能够在某些应用中减少对任务专属标注数据的需求。

NASA-IBM Lunar Foundation Model 的多模态设计使其能够学习不同类型月球观测数据之间的关系，而不是将每个数据集独立处理。该模型被设计为可同时处理区域尺度的广角相机（WAC）观测和米级尺度的窄角相机（NAC）数据，并纳入地形、光照几何和其他月球表面特性等信息。

通过公开发布预训练模型、微调代码和基准数据集，NASA-IBM Lunar Foundation Model 团队希望为行星科学界和 AI 社区提供一个可复用的基础，用于开发新的月球研究应用。

这项工作的一个重要组成部分，是合作开发 SomBench。该数据集既用于预训练 NASA-IBM Lunar Foundation Model，也用于支持对月球机器学习（ML）应用进行标准化评估。

SomBench 包含两个互补组成部分：一个核心多仪器数据集，作为 NASA-IBM Lunar Foundation Model 的预训练语料；以及一套应用基准，用于评估 ML 方法在代表性月球科学问题上的表现。这套基准涵盖三大科学主题：撞击过程、火山历史和极地挥发物。

作为该项工作的一部分，Slank 领导开发了高分辨率月球勘测轨道器相机（LROC）NAC 陨石坑基准，并人工识别出超过 49,000 个月球陨石坑。所得数据集结合高分辨率月球影像与共配准数字地形模型，用于评估米级分辨率下的陨石坑检测。她还参与了更广泛的 SomBench 数据集和科学应用工作，并对 SomBench 研究及 NASA-IBM Lunar Foundation Model 研究进行了广泛的科学审查。

Slank 博士表示：“最大的挑战之一，是将来自差异很大的仪器、且空间分辨率跨度从每像素 1 米到 20 千米的月球数据集整合起来，同时仍要保留每个数据集的科学价值。由于我同时参与科学团队和建模团队，我能够帮助确保在整合数据、并利用数据训练和评估基础模型时充分考虑这些差异。我迫不及待想看到，研究人员借助 NASA-IBM Lunar Foundation Model 能够开展哪些新的科学研究！”

NASA-IBM Lunar Foundation Model 及相关数据集可通过 Hugging Face 获取。

NASA 公告：

https://science.nasa.gov/science-research/artificial-intelligence-lunar-foundation-model/

IBM 公告：

https://newsroom.ibm.com/2026-09-10-ibm-and-nasa-release-open-source-ai-model-to-support-lunar-exploration

关于 USRA

大学空间研究协会（USRA）成立于 1969 年，在美国政府请求下、由美国国家科学院主持成立，是一家经特许设立的非营利机构，旨在推动与太空相关的科学、技术和工程发展。USRA 运营科学研究所和设施，并在联邦资金支持下开展其他重大研究与教育项目。该机构与大学界合作，并依托内部科学领导力、创新研发能力和项目管理专长开展工作。

有关 USRA 的更多信息，请访问 www.usra.edu。

Open-source artificial intelligence model combines diverse lunar datasets to support scientific analysis of the Moon

The NASA-IBM model reproduces patterns of lunar ice prospectivity (scaled from blue to yellow), shown at four locations (left) near the Moon’s pole. Top row: reference ice prospectivity map of Mons Mouton near the lunar south pole; middle row: predictions from the ConvNeXt model; bottom row: predictions from the NASA-IBM model. The NASA-IBM model preserves many fine-scale prospectivity patterns in the reference data. Image credit: NASA/IBM Research

WASHINGTON, D.C., — September 18, 2026. Universities Space Research Association (USRA) contributed planetary science expertise, lunar dataset development, and scientific evaluation to the newly released NASA-IBM Lunar Foundation Model, an open-source artificial intelligence (AI) model designed to help researchers analyze the large, diverse datasets collected by lunar missions.

Developed through a collaboration led by NASA and IBM Research, the NASA-IBM Lunar Foundation Model was pretrained from scratch using SomBench, a multimodal lunar dataset containing nearly two million co-registered data bundles spanning 11 modalities and two spatial scales. The model brings together complementary information about the lunar surface, including imagery, topography, illumination geometry, thermophysical properties, mineralogy, radar, gravity, and other geologic and environmental data.

USRA's contribution to the project was provided by Dr. Rachel Slank, an associate scientist with USRA's Science and Technology Institute, on assignment at NASA’s Marshall Space Flight Center. She served as a planetary science subject-matter expert on the NASA-IBM Lunar Foundation Model team. Slank worked across both the science and modeling teams, helping connect lunar science priorities and the physical characteristics of planetary datasets with decisions about model development, applications, and evaluation.

The NASA-IBM Lunar Foundation Model was evaluated across three downstream benchmarks: crater detection at both regional and meter scales, segmentation of irregular mare patches (IMPs), and regression of lunar polar ice prospectivity. Together, these applications assess the model’s performance across a diverse range of lunar science challenges, from identifying impact features and mapping unusual volcanic landforms to integrating environmental datasets associated with the stability and potential distribution of polar volatiles.

Across all three benchmarks, the pretrained NASA-IBM Lunar Foundation Model matched or outperformed comparison models based on ImageNet pretraining, as well as an architecturally identical model initialized without lunar pretraining. The study also demonstrated particularly strong label efficiency in crater detection, suggesting that the representations learned through lunar pretraining can reduce the amount of task-specific labeled data required for certain applications.

The multimodal design of the NASA-IBM Lunar Foundation Model allows it to learn relationships among different types of lunar observations rather than treating each dataset independently. The model was designed to operate across both regional-scale Wide Angle Camera (WAC) observations and meter-scale Narrow Angle Camera (NAC) data while incorporating information such as terrain, illumination geometry, and other lunar surface properties.

By releasing the pretrained model, fine-tuning code, and benchmark datasets openly, the NASA-IBM Lunar Foundation Model team aims to provide the planetary science and AI communities with a reusable foundation for developing new lunar research applications.

A major component of this work was the collaborative development of SomBench, the dataset used both to pretrain the NASA-IBM Lunar Foundation Model and to support standardized evaluation of lunar machine learning (ML) applications.

SomBench contains two complementary components: a core multi-instrument dataset that serves as the pretraining corpus for the NASA-IBM Lunar Foundation Model and a suite of application benchmarks used to evaluate ML methods on representative lunar science problems. The benchmark suite addresses three broad science themes: impact processes, volcanic history, and polar volatiles.

As part of that effort, Slank led development of the high-resolution Lunar Reconnaissance Orbiter Camera (LROC) NAC crater benchmark, manually identifying more than 49,000 lunar craters. The resulting dataset uses high-resolution lunar imagery together with co-registered digital terrain models to evaluate crater detection at meter-scale resolution. She also contributed to the broader SomBench datasets and science applications and provided extensive scientific review of both the SomBench study and the NASA-IBM Lunar Foundation Model study.

“One of the biggest challenges was bringing together lunar datasets that span very different instruments and spatial resolutions (1m to 20km per pixel) while still preserving the scientific value of each dataset,” said Dr. Slank. “Because I worked across both the science and modeling teams, I could help make sure those differences were considered as the data was brought together and used to train and evaluate the foundation model. I can’t wait to see what new science researchers will be able to do with the help of the NASA-IBM Lunar Foundation Model!”

The NASA-IBM Lunar Foundation Model and associated datasets are available through Hugging Face.

NASA announcement:

https://science.nasa.gov/science-research/artificial-intelligence-lunar-foundation-model/

IBM announcement:

https://newsroom.ibm.com/2026-09-10-ibm-and-nasa-release-open-source-ai-model-to-support-lunar-exploration

About USRA

Founded in 1969, under the auspices of the National Academy of Sciences at the request of the U.S. Government, the Universities Space Research Association (USRA) is a nonprofit corporation chartered to advance space-related science, technology, and engineering. USRA operates scientific institutes and facilities and conducts other major research and educational programs under federal funding. It engages the university community and employs in-house scientific leadership, innovative research and development, and project management expertise.

More information about USRA is available at www.usra.edu.