How do scientists studying space with data from a telescope hundreds of thousands of miles away know that what they are seeing is real? A new NASA project, Artifact InSPECtor, invites you to find out – and by doing so, to help missions like Euclid and NASA’s new Nancy Grace Roman Space Telescope answer fundamental questions about our universe.

“It’s really cool that we can help teach computers new skills,” said nine-year-old Maeve F. after trying out Artifact InSPECtor. Participants of all ages, including those as young as Maeve, can visit the project to learn how they can contribute to science by training artificial intelligence to remove errors in telescope data.

Here’s how it works.

The Euclid space telescope, a powerful observatory built by ESA (European Space Agency) with critical contributions from NASA, is collecting light from millions of distant galaxies across the universe. It will soon be joined by NASA’s Nancy Grace Roman Space Telescope, a complementary observatory that will capture a similar number of galaxies after it begins science operations, but at different distances and densities across the sky. Together, these telescopes promise to help scientists answer questions about the expansion of the universe and dark energy – the mysterious force causing this expansion.

To collect data to answer these questions, each telescope uses a special instrument called a spectrograph that works like a prism: it splits the light from each galaxy, even very distant ones, into a rainbow of colors. By studying these rainbow patterns, called spectra, scientists can figure out how far away each galaxy is, what kinds of stars it contains, and even information about the supermassive black holes at their centers.

But before that can happen, there’s a problem to solve.

Telescope data contains many “artifacts” – the general name scientists use for signals that come from things other than real astronomical objects like galaxies or stars. Artifacts can be created by light glinting off the telescope’s housing, cosmic rays striking the detector, quirks in the camera or electronics, or other sources. It’s a bit like when a smudge on your phone’s camera lens shows up in a photo, or when a glare from the Sun blocks part of your picture.

To find and remove these artifacts, astronomers have created artificial intelligence (AI) tools that learn to recognize them, similar to how your phone recognizes faces in photos. But recognizing artifacts in data from relatively new instruments is challenging work for the AI, which doesn’t always distinguish them accurately

That’s where you come in! As a volunteer with Artifact InSPECtor, you’ll look at real space telescope data from Euclid and, starting in early 2027, the Nancy Grace Roman Space Telescope. The project will teach you how to recognize artifacts in data from these telescopes. The work you do will then be used to improve the instructions guiding the AI tool. Working together, you, the AI, the scientists, and these powerful space telescopes will learn more than ever before about how our universe works.

If you want to teach computers new skills and help discover the mysteries of dark energy, use your smartphone, tablet, or computer to visit Artifact InSPECtor and begin today: https://go.nasa.gov/3Uyrguy.

Learn More and Get Involved

Artifact InSPECtor

Train the tools used to remove artifacts from the data collected by space telescopes. For anyone with a smartphone or laptop.

A thousand people voluntarily buried their cotton underpants for two months—not to keep the Underpants Gnomes from stealing them, but as part of a citizen science project to map out soil health in 25 countries around the world. The results of this unique experiment were reported in a new paper published in the journal Plants People Planet.

“Our results show that how soil is managed can significantly affect both soil life and soil quality,” said co-author Marcel van der Heijden, an agroecologist at the University of Zurich. “Healthy, biologically active soil is crucial for fertility, nutrient cycling and many other ecosystem services.”

Soil health is critical for agriculture and, by extension, food security, not to mention a healthy global ecosystem, but it has been declining worldwide, per the authors. One key indicator of soil health is decomposition rates of complex organic matter, breaking down stuff like leaves, wood, even cadavers into simpler organic and inorganic compounds, releasing C0₂ and nutrients in the process. There have been relatively few large-scale national decomposition studies involving different land use types, although smaller studies have shown that how humans use a site can significantly affect the soil's biological diversity.

Read full article

Comments

Certain kinds of clouds are misbehaving – appearing more often and lower in the sky than they used to. To help identify the factors influencing these changes (e.g. shifts in Earth’s long-term weather patterns), scientists have asked people around the world with cameras to submit fresh images of these clouds as a part of the NASA-supported Space Cloud Watch project. Now, one volunteer has developed a new tool to help other Space Cloud Watch volunteers work more efficiently. 

The misbehaving clouds are “noctilucent”  or “night-shining” clouds (NLCs). These clouds scatter light from the Sun long after sunset and long before sunrise, giving them a silvery glow. But despite this glow, it can be hard to differentiate NLCs from lower-altitude look-alikes. That confusion has meant extra work for project leaders.

Volunteer Namai Chandra shared, “I noticed that NLC images were being manually verified by the project leaders. It felt like a task well-suited for a human-in-the-loop machine learning pipeline, one that could handle the repetitive screening automatically, while keeping human judgment central for the images that matter most.” In other words, Namai found a way to help observers verify when they are indeed seeing NLCs and when they’re not. 

Namai reached out to the Space Cloud Watch scientists Drs. Chihoko Cullens and Brentha Thurairajah, who were delighted with his idea. Namai soon developed a machine learning pipeline, training it on a variety of cloud images, including both the NLCs and the lower altitude look-alikes that are often submitted to Space Cloud Watch. The pipeline combines image pre-screening, cloud classification, and confidence-based review routing. After several rounds of development, testing, and refinement, he released his NLC identification tool to the project. This tool is now being used by cloud contributors who are unsure whether they have observed NLCs, as well as project scientists that want to flag images for review. 

Grab a camera and join the Space Cloud Watch project today! If you’ve hesitated to contribute to Space Cloud Watch because you were not certain if what you were seeing was a noctilucent cloud, you now have a way to check before you share – thanks to Namai.

Learn More and Get Involved

Space Cloud Watch

Photograph clouds just after sunset or before dawn to investigate our changing atmosphere.