It’s hard to avoid hearing about how Artificial Intelligence (AI) is changing the way we live and work. Today, the word AI is used to describe many different kinds of computer programs that can learn and help machines solve tough problems, sometimes with human help and sometimes completely on their own. Organizations are working to keep up with the rapid changes in AI tools, best practices, and questions about ethics. Both researchers and managers are taking these changes seriously and are figuring out how to best use AI in NASA’s mission to share the exploration of the universe around us.

Members of the Eclipse Soundscapes (ES) team recently attended a NASA open data repositories workshop that prompted us to consider how AI might impact the Eclipse Soundscapes Project, even as it comes to an end. AI is starting to influence many areas of research and data sharing. One way that AI might impact large datasets, like the 500+ ES audio datasets, is by helping future researchers find, process, and analyze large amounts of data more efficiently and effectively.  

This raised an important question for us: How might these very near-future AI possibilities impact the way we share the audio data collected by ES Data Collectors during the 2023 Annular Eclipse and the 2024 Total Solar Eclipse?  Here is what we learned and what we decided to do:

One topic of discussion was how projects can prepare data and metadata so they are searchable by AI, since this may be the way of the future.

Right now, lots of metadata (information about the data) is language-based. That means additional information about the audio data, like site notes, habitat descriptions, or weather descriptions, might be recorded as words or phrases rather than numbers or standardized codes. While this works well for people reading the data, it makes it harder for AI to process consistently.

Language-based metadata examples from ES

• Site Location notes might say “near cattle pasture.”
• Habitat notes could say “forest,” “woods,” or “woodland.” These all mean the same thing to a person, but could be interpreted differently by AI.

A data repository is a platform where projects store their data so that it can be preserved and reused by others. If data repositories want improved AI search functionality in the future, they may eventually require that data be submitted in new AI search-ready formats.

• Zenodo, the platform ES uses to store and share its audio and observation data, is one example of a data repository. 
• GitHub, the platform where ES shares its software and code, is another example of a data repository. 

Not all data repositories have decided on standards for AI search.  GitHub has introduced AI tools such as Anthropic Claude Sonnet, ChatGPT, and Gemini 2.5 Pro for creating code, but has not yet included AI agents for finding already existing code. Zenodo has not yet incorporated AI tools into its repository, and adding such tools is not in its current development roadmap.  With the AI search landscape changing so quickly, it is hard to predict how AI search tools will be implemented in data repositories and how data providers should format their data for AI. 

One AI search-friendly option that was discussed is putting each project’s data into a vector database that could be shared with its chosen data repository. A vector database combines data with metadata and also describes that metadata numerically rather than through language and keywords.

These numerical metadata descriptions make it easier for AI to:

• Recognize similarities rather than just exact search term matches
• Remember and connect previous inputs
• Understand data in a broader context

Examples of vector database platforms include:

• ChromaDB (Open Source, Python-based) https://github.com/chroma-core/chroma
• Pinecone (Commercial)  https://www.pinecone.io/

Zenodo, the repository where ES data is being archived, does not currently have a plan to support vector databases. It is impossible to predict how Zenodo or other online data repositories might incorporate vector databases and what future standards they may require.

Creating a vector database is more than what Eclipse Soundscapes can take on right now. It would take more time and resources than the project has and would mean looking for new data repositories or doing extensive work to fit it into Zenodo’s framework.

Still, we’re glad we explored this possibility. Thinking about what AI might mean for scientific data is worthwhile, even if we can’t take it on ourselves. As projects wind down, it helps to keep looking ahead. Our team will carry this knowledge into future efforts, and by sharing it here, the ES community can carry it forward too.

If you want to learn more about vector databases, check out these articles:

• Microsoft’s article: Understanding Vector Databases
• Cloudflare’s article: What is a Vector Database?

Interestingly, the preliminary findings from Dr. Pease and the team mirror the anecdotal reports presented by the Boston Society of Natural History. The Eclipse Soundscapes Project ran its 2024 audio data through BirdNET, a machine-learning tool that identifies bird species from sound recordings. Because Eclipse Soundscapes Data Collectors recorded for two days prior to the eclipse and for two days after the eclipse as baseline data, the researchers were able to estimate the probability of vocalization during a 4-minute window at the specific time of day when totality occurred. (Totality occurs when 100% of the Sun is blocked by the Moon). They then used that data to investigate the question of whether bird vocalization patterns change during a solar eclipse.

“It’s still early stages,” Dr. Pease said about these preliminary results. “We’re starting to see some really interesting and fun things. But there are lots more questions and more analysis to do.” Dr. Brent Pease, a Soundscapes Subject Matter Expert, is leading research efforts to analyze eclipse-related audio data collected by ES volunteers. His work focuses on understanding how wildlife responds to eclipses through changes in natural soundscapes.

A few questions Dr. Pease would like to explore include:

• Proximity to totality: How close to totality do birds need to be to produce these changes? Location data tied to the audio recordings will help Eclipse Soundscapes answer this question.
• The “dawn chorus reprise:” Dr. Pease notes a slight bump in the graph after totality in which birds vocalization increased. A closer look at which birds are making these vocalizations will help researchers determine if it does in fact mimic dawn-like activity.
• Non-bird responses: Do other species (like insects) change their vocalizations during the eclipse? 
• 2023 Annular Eclipse vs. 2024 Total Solar Eclipse – Soundscapes Audio Data: Does the bird response along the path of annularity during the 2023 annular eclipse (with approximately 90% coverage) match the response just outside the path of totality during the 2024 total solar eclipse, where coverage was also around 90%?

While researchers are only beginning to scratch the surface of these questions, the collected audio data for the project will be uploaded to the Eclipse Soundscapes Community on Zenodo, a free, open-access repository before the project ends. Present and future researchers will be able to access this audio data to learn more about how eclipses impact soundscapes on Earth and other questions. The Eclipse Soundscapes team looks forward to learning more about the data collected by our fantastic Eclipse Soundscapes volunteers! 

To learn more about the preliminary results, watch or listen to Dr. Pease’s presentation “Eclipse Soundscapes: Partnering with the Public to Illuminate the Effect of Eclipses on Wildlife” or join us for a webinar. To learn what webinars are coming up, visit the ES Learning Community page. 

Wheeler, William Morton . et al. “Observations on the Behavior of Animals during the Total Solar Eclipse of August 31, 1932.” (1935).

Following the 2023 and 2024 solar eclipses, Eclipse Soundscapes participants answered a number of survey questions that asked how the experience made them feel. Did the eclipse give them an experience of “awe” or a feeling of connection to something greater than themselves? Did participating in the project improve their feelings of belonging in science?

Researchers at North Carolina State University are using those participant responses to learn more about the emotions that eclipses evoke.

Kelly Lynn Mulvey, an Associate Professor of Psychology at North Carolina State University (NCSU), has spent her career studying how to increase participation in STEM. Mulvey worked through data from approximately 3,200 Eclipse Soundscapes Apprentices, Observers, and Data Collectors, uncovering some fascinating results.

An increase in science belonging

Overall, participating in the Eclipse Soundscapes project increased feelings of belonging in science. “We saw an increase in belonging from their reports of how they felt before they participated in the role and how they felt after they had participated,” Mulvey said. 

Eclipse percentage and awe

Mulvey also studied how the eclipse impacted feelings of awe in participants. Her work built upon research surrounding the 2017 eclipse and the language used in Twitter (now X) posts. The earlier study indicated that the amount of eclipse coverage was related to increased awe. “People who were posting about the eclipse who were closer to totality used more words related to awe than those who were off the path of totality,” Mulvey said. For the Eclipse Soundscapes project, participants were specifically asked whether the eclipse increased feelings of awe. Again, the percentage of coverage proved important. “Those who experienced the total eclipse reported greater awe than those who experienced the partial eclipse,” Mulvey said.

Changes in animal behavior

Other teams at NCSU, led by Professor of Biological Sciences Adam Hartstone-Rose, are studying observations of animal behavior collected by Eclipse Soundscapes Observers. The teams hope to identify which groups of animals (birds, insects, mammals, etc.) changed or did not change their behavior during the eclipse. If animal groups did change their behavior, the team is trying to identify when, and how long it took them to return to “normal” behavior. “It’s laborious work, there is a lot of coding involved,” Mulvey said, but she expects to have some basic animal behavior findings soon. To learn more about the preliminary work done by Harstone-Rose using 2023 ES Observer data check out “Extraordinary Darkness: A Participatory Approach to Assessing Animal Behavior During Eclipses.“ 

Implications for future science

Mulvey’s research demonstrates the long-lasting scientific impact of the data from Eclipse Soundscapes participants. Not only does participatory science provide researchers with reliable and authentic data, it benefits the participants as well. “I think the belonging results especially are really important, because it suggests that doing these participatory science projects can help you feel like you fit in more with science,” Mulvey said. “I think it has the potential to really harness folks’ nascent interest in science and launch them into continuing to select either informal science activities, or maybe more formal science work, like pursuing a degree or a job in science. We have a lot of deficits in terms of who is entering STEM fields right now, and a need for more people and more people from (various) backgrounds…to leverage their skills and help us to answer the big scientific questions that are out there.”

When Eclipse Soundscapes Data Collectors submitted the audio data they recorded during the week of the April 8, 2024 eclipse, they had the option to keep or donate their AudioMoth recorder device. Several participants donated their AudioMoths to outlets like their local Library of Things. Others sent their AudioMoths back to Eclipse Soundscapes for us to donate to other science focused projects and community organizations. Eighteen of those AudioMoths have been donated to Dark Sky Missouri, an initiative to protect our night skies and the creatures that depend on them. Eclipse Soundscapes caught up with chapter founder Don Ficken to learn more about how these AudioMoths will contribute to future science. 

Don Ficken is a Missouri Master Naturalist and amateur astronomer who launched the Missouri chapter of Dark Sky after patrons in his community library telescope program expressed difficulty seeing the sky. He found the Eclipse Soundscapes Project through SciStarter, an online hub of citizen science projects, and participated in 2024 as a Data Collector. “It opened up a door for me because I never really thought about sound acoustics in this way,” Ficken said. 

It occurred to Ficken that acoustics could help bolster Dark Sky Missouri’s efforts to study and conserve night time wildlife. One of these efforts, Lights Out Heartland, encourages homeowners and businesses to minimize artificial light usage in order to protect migrating birds from collisions due to disorienting bright lights. (A 2019 Cornell Lab survey of 125 urban cities found that the St. Louis metro area ranks as the fifth deadliest city for birds during the spring migration and the sixth deadliest for fall). 

“That’s kind of a bummer to talk about with people,” Ficken admits. To “bring a positive spin to the project,” Ficken hopes to use the AudioMoths to capture the birds’ nocturnal flight calls as they fly over locations like the Gateway Arch, Shaw Nature Reserve, and Missouri Botanical Gardens. “You would think that migrating birds would go up and just stay there,” Ficken said. “That’s not actually what happens. They drop altitudes, probably because of thermals, maybe because magnetic shifts and things like that. They move up and down. And every time they shift formation, they have to make calls to get themselves reoriented. And this adds a whole new dimension that we can study through acoustics.”

Dark Sky Missouri also hopes to take more general surveys of nature at night, by placing AudioMoths in parks and natural areas. Even though parks are not typically open or staffed at night, the AudioMoths could help map the locations and movements of wildlife, creating talking points and learning opportunities for staff and visitors alike. “The trouble is that unless we reconnect people with the night, unless we get them excited about what’s out there at night, they won’t care about nature,” Ficken said. “If I can show them things like owls and bats and frogs and peepers and insects making noise, if I can show them how alive nature is at night, I think I might make them convert.” 

Both initiatives will be piloted during the fall bird migration, with the goal of developing a framework for an expanded long term project. “The idea is we’re going to build this little network of people that know about AudioMoths and how they work,” Ficken said. “I’m drawing on people that already have expertise around birds. They’re really passionate. We’ll probably have a small team of maybe six to eight people doing this so we can just learn together, figure this out.”

While there are no opportunities for the general to get involved in the projects just yet, Ficken said participatory science surrounding birds and light pollution is as abundant as it is important. He cites the Globe at Night project, in which participants helped determine that global light pollution is growing 10 percent each year.

Ficken says participatory scientists can benefit from the multisensory methods employed in the Eclipse Soundscapes Project. “I think that the thing that they should think about is really the door that acoustics would be opening for them,” he said. “In other words, you don’t have to just visually look at daytime. Think about sound. Think about night.”

Check out the recorded webinar when special guest Don Ficken joined Eclipse Soundscapes to talk about how he is using AudioMoths for Nighttime Conservation. Click DarkSky webinar here to watch the recording.

Non-visual designer Lindsay Yazzolino shares her experience aboard the AstroAccess “AA2” Zero Gravity Flight

Listen to the audio interview or read the full transcript below.

Kelsey Perrett: Hi, I’m Kelsey Perrett with ARISA Lab. Today, I’m speaking with non-visual designer Lindsay Yazzolino. Lindsay is a consultant with ARISA Lab and the Eclipse Soundscapes: Citizen Science Project. She recently returned from a zero-gravity flight with AstroAccess, a project dedicated to promoting disability inclusion in space. Lindsay joined us to discuss what it’s like to experience zero gravity, how the crew’s experiments will impact the future of accessibility in space, and why it’s important to include people with disabilities in the design process from the start. And now, let’s hear from Lindsay.

Lindsay Yazzolino: I’m Lindsay Yazzolino, I am a non-visual designer, I have a background in cognitive neuroscience research,  and I’ve always loved science. Growing up, I always knew I wanted to do something related to science, I was always really curious about how things worked. I’m also totally blind and I’ve been blind since birth. I have always, of course, been surrounded by this theme, I guess, of needing science to be non-visually accessible. And I’m just really passionate about, not only science accessibility, but also just making it not just accessible, but also really hands on and interesting and fun for people with disabilities, specifically for for blind people. And making it accessible in a way where someone can just participate, not necessarily because they’re blind, but just to be able to participate in science in really cool and interesting ways that also happen to be hands on.

Kelsey Perrett: Lindsay says she first heard about the opportunity with AstroAccess when she was presenting at the SciAccess conference in 2019.

Lindsay Yazzolino: So I was at this conference, and I met a whole bunch of cool people, among them Anna Voelker and Sheri Wells-Jensen, who were both organizers of this conference. And turns out, they also were both organizers of what would become AstroAccess. AstroAccess of courses is the organization that ran this really cool zero gravity flight that we’re talking about. So yeah, I found out about them through SciAccess and that’s how I knew to apply. I applied the first year that they were doing the first zero gravity flight, which was 2021. They were very clear that they wanted people who were really open about talking about their disabilities, and who are really passionate about creating accessibility in space travel, spaceflight, and all this stuff. So I applied the first year, and it was super competitive, and I didn’t get in. You know, it was really cool that there was so many qualified people that it would be this competitive. So then the next year, I applied again, and I got in. I was really excited, because I mean, zero gravity flight. I was just super curious, you know, what it would feel like to experience zero gravity. And of course, I believed in what the organization is doing. And, of course, I wanted to use my skills and my experience, and, whatever I can bring to help increase accessibility in space in spaceflight. So it was a combination of like, I want to help science and wow, I get to be in an airplane and fly around in zero gravity, because I love airplanes and I love like thrill seeking experiences. And so it was just like, a whole combination of of coolness. And a lot of people have tried to explain, people get asked, what does it feel like to be in zero gravity? And everyone’s like, it’s really hard to explain. So one of my sort of goals when I was doing this was to try and be able to explain it as best as I could. And specifically, of course, me being totally blind, I was experiencing it totally non-visually. And I remember the first that initial feeling of the floor just kind of disappearing, and being like, Oh crap, there’s no floor. Because my instinct was to find the floor, because you know when you’re on Earth, and you’re tossed up in the air, you know that you’re going to end up having to fall back down onto the floor. And usually that’s not a very comfortable thing to happen. But of course, I knew it was zero gravity. But still I felt that need to sort of test what it feels like to be in this place where the laws of gravity are different. So in a way, I sort of felt like a baby. That’s the best I can explain is like, because it was this whole kind of relearning what happens when you move in this new environment. But after a few parabolas, I was just like, Okay, this is really fun. And that that point I was, well, I had to do my my actual science experiments. But like, let’s face it, the really fun part, was being in zero gravity. Actually, what I realized, the best way to describe it for me, is in some ways, it felt like instead of me moving within the plane, it felt like the plane was moving around me. And it would sort of feel like being on a hamster wheel where like, whatever you were on was sort of under you, like you’re actually propelling it under you, as opposed to feeling like I was, you know, upside down on the ceiling or sideways. So it was a really interesting sensation and nothing like anything I’ve experienced before.

Kelsey Perrett: While on board, the AstroAccess crew conducted a variety of scientific experiments which were intended to advance Universal Design in space travel.

Lindsay Yazzolino: You know, I mean, it’s really cool to go into zero gravity, but of course, we were also doing experiments. And the idea of these experiments was to increase our knowledge of how we can make spaceflight accessible, how we can actually design, on a practical level, how we can design spacecraft and space stations and all these things to be accessible. So there was a group of us who were blind or low vision on the flight. And we worked on a project where we developed a set of tactile graphics to help people orient non-visually while they’re in zero gravity. A few of us actually went to New York a few times to visit the New York Public Library where there’s a whole accessibility program led by Chancey Fleet, and there’s a whole bunch of everything to make tactile graphics. So we had tactile graphics and embossers, we got the help of a couple people who are really expert designers. So they got to help us actually sketch out the graphics. We had all these tactile drawing boards. It was like a few blind people with tactile drawing tools, just collaborating, you know, brainstorming and coming up with ideas, just iterating on these designs, and coming up with the best designs that we could think of. So the most important thing we wanted to make sure people knew was which way is down, because if you think about it, you’re in zero gravity, you don’t know which way you’re facing, it’s really easy to get disoriented. And the idea is that you could reach out and touch any surface, whether it be walls or floor ceiling, and be able to feel which way is down. And then also, we had symbols to show which direction different emergency equipment was and also how far that equipment was, and whether it was on your same wall or across from you on the opposite wall. So this is a totally new system that we developed. And we wanted to do some initial testing to see how quickly and accurately people can read them while in zero gravity. So we set up a few of us with a whole set of test graphics where you had to read them. And during each parabola, you had to call out — we recorded people’s observations about what they thought they showed.

Kelsey Perrett: I asked Lindsay what was it like to work on a team that was intentionally inclusive of people with disabilities, and whether this experience changed the way she thought about herself or her career as a scientist.

Lindsay Yazzolino: I mean, it’s always nice when you work with a group of people where you don’t have to deal with people being really paternalistic, or being way too hovering, you know, hovering over you, or thinking people —blind people, people with other disabilities — can’t, you know, handle themselves or do certain things or need to be led by people without disabilities. Of course, I think you and I both know that that’s a huge problem when that does happen. I mean, on a functional level, it just meant we could get more done. We could actually design some of the experiments that we wanted to do, that we could test the things we wanted to test, and that we could experience zero gravity in a way where we weren’t being restricted unnecessarily. Because that is always a thing, you know, to think about. I know, the word empowering is overused, we use that word a lot. But it was in the sense that, you know, we are the researchers, right, like, we’re the scientists, we’re the researchers. And so it felt like, honestly, it just feels the way it should, you know, to be in a group where inclusion and participation is expected. Yeah, it just feels like the way it should be. It’s definitely shifted how I feel about the proximity of myself to space travel. Before, it always felt like the idea of going into space was one of those things that, like you said, everyone kind of dreams about at some point. But it didn’t feel like a reality exactly. It kind of felt like, oh, this is a thing that other people do. And not even just because of being blind, but just because it’s just the thing that other people did. Very few people get to do it. So I feel like now I do feel closer to that reality. I feel like, especially now that there’s a lot more commercial space travel happening, you know, the idea of me thinking of myself going into space feels a lot more conceivable than it did before. And of course, making it accessible is a big part of that.  We’re just making what we can do our part to do is to prevent designers from, whether intentionally or not, just creating bad designs that don’t need to happen and unnecessarily excluding people from going to space. I do think that, you know, we have to see this as an ongoing thing. Like yes, we did this flight. Yes, it was awesome. But now there’s just a lot more work to be done. There’s a lot more science to be done. But it’s like, I feel like we’ve barely scratched the surface when it comes to starting to explore possible, you know, accessible features and inclusion in space travel, all this stuff. So this is like just the beginning. And I’m really looking forward to seeing how things progress and to being part of contributing to that. And I think that like we just need that we need everybody who can be part of, you know, who who can contribute their expertise and their knowledge, and their belief in us as people, you know, who can eventually go to space.