Skip to main content

NASA tests new AI chatbot to make sense of complex data

Using its Earth-observing satellites, NASA has collected huge amounts of highly complex data about our planet over the years to track climate change, monitor wildfires, and plenty more besides.

But making sense of it all, and bringing it to the masses, is a challenging endeavor. Until now, that is.

Recommended Videos

Harnessing the power of generative AI, NASA has teamed up with Microsoft to create Earth Copilot, a new AI-powered chat tool specifically designed to simplify how users access complex geospatial satellite imagery and data, potentially unlocking new insights and discoveries.

While only a limited number of researchers and scientists can currently make sense of the data, Earth Copilot will bring it to an almost unlimited audience, with curious folks able to probe the tool with questions for an exchange that’s conversational in tone, similar to how you might already use ChatGPT or other similar generative-AI chat tools.

Microsoft suggests that users might simply ask questions like: “What was the impact of Hurricane Ian in Sanibel Island?” or, “How did the COVID-19 pandemic affect air quality in the U.S.?” Earth Copilot will then dive into the relevant data sets before offering an answer that should be relatively easy to digest.

“NASA’s Earth Science Data Systems Program is responsible for collecting an incredible variety of data from spaceborne sensors and instruments,” Microsoft said in an article introducing Earth Copilot. “This data spans everything from atmospheric conditions to land cover changes, ocean temperatures, and more. However, the sheer scale and complexity of this information can be overwhelming. For many, finding and extracting insights requires navigating technical interfaces, understanding data formats, and mastering the intricacies of geospatial analysis — specialized skills that very few nontechnical users possess. AI could streamline this process, reducing time to gain insights from Earth’s data to a matter of seconds.”

Currently, Earth Copilot is being tested by NASA scientists and researchers to ensure its safety and reliability.

The next step will be to integrate it into NASA’s Visualization, Exploration, and Data Analysis (VEDA) platform, which makes it easier for users to search, discover, and analyze data related to Earth science.

Trevor Mogg
Contributing Editor
Not so many moons ago, Trevor moved from one tea-loving island nation that drives on the left (Britain) to another (Japan)…
People are making entire short films with this new AI video-generation app
screenshot of a MiniMax AI video of a dog running through a field

Alibaba- and Tencent-backed startup Minimax, one of China's "AI tigers," has released its Video-01 text-to-video model, which can generate highly accurate depictions of humans, down to their hand motions. Minimax unveiled the new tool Saturday at its inaugural developer conference in Shanghai.

https://x.com/JunieLauX/status/1829950412340019261

Read more
Venus gets a taste of Missy Elliot in NASA communications test
This illustration of the large Quetzalpetlatl Corona located in Venus’ southern hemisphere depicts active volcanism and a subduction zone, where the foreground crust plunges into the planet’s interior.

This illustration of the large Quetzalpetlatl Corona located in Venus’ southern hemisphere depicts active volcanism and a subduction zone, where the foreground crust plunges into the planet’s interior. NASA/JPL-Caltech/Peter Rubin

In space, they say, no one can hear your scream -- but at certain points in our solar system, you might be able to pick up some Missy Elliot. NASA has recently made special use of its communication system, called the Deep Space Network, by sending the lyrics of Missy Elliot's song The Rain (Supa Dupa Fly) to Venus.

Read more
A dangerous new jailbreak for AI chatbots was just discovered
the side of a Microsoft building

Microsoft has released more details about a troubling new generative AI jailbreak technique it has discovered, called "Skeleton Key." Using this prompt injection method, malicious users can effectively bypass a chatbot's safety guardrails, the security features that keeps ChatGPT from going full Taye.

Skeleton Key is an example of a prompt injection or prompt engineering attack. It's a multi-turn strategy designed to essentially convince an AI model to ignore its ingrained safety guardrails, "[causing] the system to violate its operators’ policies, make decisions unduly influenced by a user, or execute malicious instructions," Mark Russinovich, CTO of Microsoft Azure, wrote in the announcement.

Read more