NASA AI Model That Found 370 Exoplanets Now Digs Into TESS Data - UNIVERSE

This artist's impression shows the star TRAPPIST-1 with two planets transiting across it. ExoMiner++, a recently updated open-source software package developed by NASA, uses artificial intelligence to help find new transiting exoplanets in data collected by NASA’s missions.

NASA, ESA, and G. Bacon (STScI)

Scientists have discovered over 6,000 planets that orbit stars other than our Sun, known as exoplanets. More than half of these planets were discovered thanks to data from NASA’s retired Kepler mission and NASA’s current TESS (Transiting Exoplanet Survey Satellite) mission. However, the enormous treasure trove of data from these missions still contains many yet-to-be-discovered planets. All of the data from both missions is publicly available in NASA archives, and many teams around the world have used that data to find new planets using a number of techniques.

In 2021, a team from NASA’s Ames Research Center in California’s Silicon Valley created ExoMiner, a piece of open-source software that used artificial intelligence (AI) to validate 370 new exoplanets from Kepler data. Now, the team has created a new version of the model trained on both Kepler and TESS data, called ExoMiner++.

Artist's impression of NASA’s Transiting Exoplanet Survey Satellite (TESS), which launched in 2018 and has discovered nearly 700 exoplanets so far. NASA’s ExoMiner++ software is working toward identifying more planets in TESS data using artificial intelligence.

NASA's Goddard Space Flight Center

The new algorithm, which is discussed in a recent paper published in the Astronomical Journal, identified 7,000 targets as exoplanet candidates from TESS on an initial run. An exoplanet candidate is a signal that is likely to be a planet but requires follow-up observations from additional telescopes to confirm.

ExoMiner++ can be freely downloaded from GitHub, allowing any researcher to use the tool to hunt for planets in TESS’s growing public data archive.

“Open-source software like ExoMiner accelerates scientific discovery,” said Kevin Murphy, NASA’s chief science data officer at NASA Headquarters in Washington. “When researchers freely share the tools they've developed, it lets others replicate the results and dig deeper into the data, which is why open data and code are important pillars of gold-standard science.”

ExoMiner++ sifts through observations of possible transits to predict which ones are caused by exoplanets and which ones are caused by other astronomical events, such as eclipsing binary stars. “When you have hundreds of thousands of signals, like in this case, it’s the ideal place to deploy these deep learning technologies,” said Miguel Martinho, a KBR employee at NASA Ames who serves as the co-investigator for ExoMiner++.

This animation shows a graph of the tiny amount of dimming that takes place when a planet passes in front of its host star. NASA’s Kepler and TESS missions spot exoplanets by looking for these transits. ExoMiner++ uses artificial intelligence to help separate real planet transits from other, similar-looking astronomical phenomena.

NASA's Goddard Space Flight Center

Kepler and TESS operate differently — TESS is surveying nearly the whole sky, mainly looking for planets transiting nearby stars, while Kepler looked at a small patch of sky more deeply than TESS. Despite these different observing strategies, the two missions produce compatible datasets, allowing ExoMiner++ to train on data from both telescopes and deliver strong results. “With not many resources, we can make a lot of returns,” said Hamed Valizadegan, the project lead for ExoMiner and a KBR employee at NASA Ames.

The next version of ExoMiner++ will improve the usefulness of the model and inform future exoplanet detection efforts. While ExoMiner++ can currently flag planet candidates when given a list of possible transit signals, the team is also working on giving the model the ability to identify the signals themselves from the raw data.

“Open-source science and open-source software are why the exoplanet field is advancing as quickly as it is.

Jon Jenkins

Exoplanet Scientist, NASA Ames Research Center

In addition to the ongoing stream of data from TESS, future exoplanet-hunting missions will give ExoMiner users plenty more data to work with. NASA’s upcoming Nancy Grace Roman Space Telescope will capture tens of thousands of exoplanet transits — and, like TESS data, Roman data will be freely available in line with NASA’s commitment to Gold Standard Science and sharing data with the public. The advances made with the ExoMiner models could help hunt for exoplanets in Roman data, too.

“The open science initiative out of NASA is going to lead to not just better science, but also better software,” said Jon Jenkins, an exoplanet scientist at NASA Ames. “Open-source science and open-source software are why the exoplanet field is advancing as quickly as it is.”

NASA's Office of the Chief Science Data Officer leads the open science efforts for the agency. Public sharing of scientific data, tools, research, and software maximizes the impact of NASA’s science missions. To learn more about NASA’s commitment to transparency and reproducibility of scientific research, visit science.nasa.gov/open-science. To get more stories about the impact of NASA’s science data delivered directly to your inbox, sign up for the NASA Open Science newsletter.  

By Lauren Leese 
Web Content Strategist for the Office of the Chief Science Data Officer

Source: NASA AI Model That Found 370 Exoplanets Now Digs Into TESS Data - NASA Science