First Complete Ultraviolet Map of the Sky Created Using Multi-Agent AI

First Complete Ultraviolet Map of the Sky Created Using Multi-Agent AI Astrophysicist Brice Ménard collaborated with Claude Science to build the first full-sky ultraviolet map, filling historical observation gaps that covered roughly one-third of the sky. Prior UV surveys left roughly a third of the sky unobserved, largely because missions like NASA's GALEX avoided bright stars along the galactic plane to protect detectors. Claude orchestrated teams of AI agents to aggregate, calibrate, and align disparate telescope surveys into a unified coordinate system and scale. Machine learning inpainting and multiwavelength cross-referencing estimated missing UV emissions to within about 10% of real values. Claude corrected instrument artifacts, such as atmospheric glow footprints across 38,000 GALEX observations, and incorporated over 100 million stars from ESA Gaia data. The Ultraviolet Observation Gap Observing the universe in ultraviolet light requires space telescopes because Earth's ozone layer absorbs UV radiation. Over decades of observation, significant gaps remained in full-sky UV coverage. NASA's GALEX mission imaged about two-thirds of the sky across 38,000 observations but intentionally skipped dense, bright areas like the Milky Way's galactic plane to avoid detector damage. Although other missions contributed data, approximately one-third of the UV sky remained unobserved, leaving astronomers without a complete full-sky map. AI Agent Orchestration and Data Standardization Ménard used Claude Science to direct teams of AI agents to gather public astronomical UV surveys from missions including GALEX, Swift, and FIMS/SPEAR. The agents processed tens of thousands of images, removed stellar glare, and normalized observations across varying time periods. They then cross-calibrated instruments, unified spatial resolutions, and aligned all data to a single coordinate framework. Inpainting and Multiwavelength Estimation To reconstruct the unobserved third of the sky, Claude used machine-learning inpainting combined with cross-wavelength data from visible, infrared, and radio bands. By analyzing how mapped UV data correlated with these other spectra, the model estimated the missing UV intensities along with uncertainty values. Validation tests hiding known UV regions showed the model predicted values within roughly 10% of real measurements. Additionally, UV estimates for over 100 million individual stars were integrated using visible-light data from ESA's Gaia satellite. Iterative Artifact Correction and Final Results Early versions of the map revealed circular artifacts caused by residual atmospheric glow in GALEX's circular field footprints. Guided by Ménard, Claude diagnosed the issue and corrected for the glow across all 38,000 images within a few hours. Across more than a dozen iterations, the collaboration yielded a finished map showing dust clouds, giant stellar-explosion bubbles, faint filaments, and the Magellanic Clouds, providing an educational and research resource without requiring months of manual processing.

天体物理学家借助 Claude Science 绘制出首张完整全天紫外线地图 约翰斯·霍普金斯大学天体物理学家兼 Anthropic 研究员 Brice Ménard 借助 Claude Science 及多智能体系统，整合跨越数十年的多国太空望远镜数据，并利用跨波段机器学习修复填补了约三分之一未观测区域，成功制作出首个完整的全天紫外波段地图。 紫外线波段易被臭氧层吸收，此前虽有 NASA GALEX、Swift 等太空望远镜数据，但出于保护探测器等原因，全天仍有约三分之一区域从未被紫外望远镜观测。 Claude 编排多个 AI 智能体完成网络公开数据检索、去除亮星眩光、统一分辨率与坐标校准，并对 38,000 次 GALEX 观测残留的大气辉光进行了回溯修正。 利用已测区域学习紫外亮度与可见光、红外及射电波段的关系，Claude 通过图像修复（inpainting）填补缺失区域，验证误差在 10% 以内，并结合 Gaia 卫星数据推算出超过 1 亿颗恒星的紫外光。 完整地图标明了实测与预测像素及不确定性，清晰展现了恒星爆炸残留环、年轻恒星周围的尘埃云以及麦哲伦云等银河系结构。 紫外观测缺失与 AI 协作背景 紫外线因受地球臭氧层吸收需从太空观测，但即使合并 NASA GALEX（覆盖约三分之二天区）、Swift 以及韩国 FIMS/SPEAR 等数据，银河系盘面等亮星密集处因探测器防损保护长期处于空白。传统统计填补需耗费数周高精度的像素校准分析，常因优先级问题搁浅。研究者利用 Claude Science 编排多智能体团队，自主处理多源异构数据。 多源数据清洗、校准与伪影消除 AI 智能体并行下载并清洗了数万张巡天图像，消除恒星眩光以便精确测量周围微弱的紫外线，并将不同仪器的观测跨波段统一坐标与分辨率。在人工检查发现图像残留圆形观测轮廓后，智能体查出是地球大气辉光残留所致，并在数小时内批量修正了 GALEX 全部的 38,000 次观测，消除了接缝印记。 跨波段机器学习填补与天体细节呈现 针对未被观测的三分之一天区，Claude 基于已知紫外区域学习其与可见光、红外及射电波段的相关性，通过图像修复预测未测区域，验证测试显示其与真实紫外测量误差在 10% 左右。模型叠加了根据欧空局 Gaia 卫星可见光推算的逾 1 亿颗恒星紫外估算。最终地图不仅给出了逐像素预测与不确定度，还完整呈现了年轻恒星尘埃云、超新星爆发气泡及大、小麦哲伦云等结构。

*Here, Brice Ménard, an astrophysicist at Johns Hopkins University and a researcher at Anthropic, explains how he worked with Claude Science to produce the first complete map of the sky in UV light. The map will be a valuable educational tool, allowing students to see in detail the rich structure of the Milky Way visible at this wavelength.* The entire sky, with the galactic center in the middle, in the ultraviolet (combining far-UV 154 nm and near-UV 232 nm). About a third of this map, including much of the galactic plane, was predicted with Claude Science using the method outlined in this post. Additional layers of the map label each pixel as “measured” or “predicted” and provide uncertainty estimates; [you can see it here](https://menard.pha.jhu.edu/uvmap/). When I teach astrophysics, I often begin by showing my students that the sky looks completely different depending on the wavelength you observe it in. Each brings out different features. In visible light, one mainly sees stars. Switching to infrared reveals the glow of tiny grains of dust concentrated in a band along the Milky Way. In radio waves, the stars and dust fade and hydrogen gas—the raw material from which new stars form—becomes visible. And in X-rays, one can see violent phenomena, like stars exploding, or matter spiraling into a black hole. Together, these features let astronomers understand how gas collapses into stars, how stars seed the galaxy with dust, and how galaxies like ours take shape. When talking about UV light and how it reveals dust illuminated by starlight, from the clouds around young stars to the rings left by stellar explosions, I have always had to apologize. The only UV map I could show was full of holes. UV light is absorbed by the ozone layer of the atmosphere, so to observe the universe in the UV spectrum, one has to go to space. Over the past 50 years, space telescopes have observed parts of the sky in UV and published their data. But much remains unobserved. The largest dataset comes from NASA’s GALEX mission, which ran from 2003 to 2013 and imaged about two-thirds of the sky in some 38,000 separate observations. But GALEX deliberately skipped locations with very bright stars, including those on the plane of the Milky Way (the flat disk of the galaxy, where stars are most densely packed), because of the risk of damaging the satellite’s detectors. Other space telescopes, such as NASA’s Swift and South Korea’s FIMS/SPEAR, acquired additional data, but even in those combined datasets, there are a number of missing pieces. Statistical techniques exist to estimate the missing data and create a complete UV map of the sky. But doing this properly takes weeks of painstaking work, involving meticulous calibrations at the level of individual pixels and sophisticated, repeated analyses. Understandably, astrophysicists tend to put this kind of work aside in pursuit of more pressing research. Most fields have a backlog of similar projects, ones that would explain a key concept or help other researchers, but which never rise high enough on anyone’s list to get done. With Claude, it has become easier to tackle such lower-priority work. This summer, I set out to make a complete UV map of the sky with [Claude Science](https://www.anthropic.com/news/claude-science-ai-workbench). The instructions were simple to state, but not to carry out: gather every available UV dataset, put them all on a common scale, merge them into a single map, and fill in every patch of sky that no UV telescope has ever observed. To do this, Claude orchestrated a team of AI agents. First, the agents searched the web for publicly available astronomical UV surveys, each comprising a massive collection of individual data points or images—tens of thousands of images, in the case of NASA’s GALEX mission—taken over several years and under varying conditions. After downloading the data, the agents had to make each survey internally consistent, so that an image taken in one time period could be compared with an image taken in another. This required paying special attention to the regions around bright stars. Just as the sun or a streetlight can add glare to a photo here on Earth, stars can add glare to an image of the sky captured by a space telescope. That glare needed to be removed before the fainter UV light around the stars could be measured precisely. Many agents, working in parallel on different regions of the sky, were able to even out these differences. Next, the surveys had to be combined. The datasets were collected by different instruments on different telescopes, and each one captures the ultraviolet sky slightly differently, so they had to be cross-calibrated against one another, redrawn at the same resolution, and mapped onto a common coordinate system before they could be merged into one map. I gave high-level instructions to Claude on how to do so, and Claude set a team of agents on the tasks. Then came the hardest part: filling in the gaps in the map. Roughly a third of the sky has never been observed in UV. To account for those blank spots, I asked Claude Science to use a technique called inpainting—a common process in machine learning, in which a model trained on millions of photos learns how each part of an image relates to its surroundings, and uses that knowledge to restore damaged or missing portions of an image. Claude combined this approach with additional information we had at our disposal. Where UV data is missing, we do have observations at other wavelengths, including visible, infrared, and radio. Using the two-thirds of the sky that *has* been mapped in UV, Claude learned how UV brightness relates to these other wavelengths. It then applied that relationship to the third of the sky for which no UV data exists, and estimated what it should look like at each point, and how confident it was in that estimate. To check how accurate the model’s predictions were, I asked Claude to take regions for which we already have UV data and deliberately hide parts of them, creating the kinds of blank patches inpainting is designed to fill. The model had to use what it had learned to complete the picture without access to the real values. After several rounds of refinement, it was able to estimate the hidden data to within about 10% of the real UV measurements, a difference almost imperceptible to the human eye. Finally, on top of this diffuse inpainted background, Claude added estimates of UV light from more than 100 million individual stars inferred from measurements by the European Space Agency’s Gaia satellite in visible light. The first version of the full UV map of the sky was complete. Claude did not get everything right on the first try. Looking through the processed images one evening, for example, I noticed something *off* in one of the dimmest fields: faint circles, each a touch brighter or darker than its neighbors. These were the footprints of individual GALEX observations. Each GALEX image captures a circular patch of the sky, and each contains a slight, not-quite-uniform UV glow from the Earth’s atmosphere. If that glow is not fully removed, each circle appears slightly brighter or darker than those around it. Claude had listed this as a known issue at the start of the project, but the map had still passed two rounds of review by other agents without the problem being caught. I told Claude, “I can see discs with the imprint of individual observations; can you correct that?” The agents traced the problem back to the leftover atmospheric glow. Claude then corrected for that glow in all 38,000 observations. After a couple of hours of processing, the circles were gone. Together, Claude and I created more than a dozen successive versions of the map, each more refined than the last. Our collaboration spread over several days and took on a predictable rhythm: I would have several exchanges within Claude Science to plan the next steps, then Claude would independently perform hours of computations, while I went back to working on other projects. [The finished map](https://menard.pha.jhu.edu/uvmap/) shows the entire sky in UV light, and displays many interesting structures: dust clouds glowing around luminous young stars, giant dust rings and loops tracing gas bubbles blown out by the explosions of massive stars. Far from the galactic plane, faint filaments of dust thread across the sky, lit by the combined starlight of the entire galaxy. Below the plane sit the Large and Small Magellanic Clouds, two small neighboring galaxies bright with young stars. I think it’s beautiful—and it can join the other canonical maps in helping generations of students appreciate the variety of physical processes at work in our galaxy. For once, I was able to pursue a project like this without sacrificing time I would otherwise have devoted to research. I suspect many scientists can think of a map, a figure, or a resource they’ve been putting off for the same reason. The measurements used to create this map are from [GALEX](https://archive.stsci.edu/missions-and-data/galex) and [Swift](https://swift.gsfc.nasa.gov/archive/) (NASA), [FIMS/SPEAR](https://archive.stsci.edu/missions-and-data/fims-spear) (Korea), [TD-1](https://catalog.data.gov/dataset/td1-stellar-ultraviolet-fluxes-catalog) (Europe), and [Planck](https://pla.esac.esa.int/#home) and [Gaia](https://gea.esac.esa.int/archive/) (ESA). I’m grateful to everyone involved in these missions and in making the data public. Many agents working in Claude Science contributed the patient labor of putting this map together. My contribution was limited to guiding them in the process.