To find intelligent life beyond earth, NASA FDL turns to artificial intelligence

Are we alone in the universe? Does intelligent life exist on other planets? If so, what does it look like?

According to researchers at NASA Frontier Development Lab (FDL), deep questions like these could be answered by one of humankind's greatest technological advancements: artificial intelligence.

For an eight-week session of AI-fueled rapid experimentation and iteration, NASA FDL assembled an interdisciplinary team to prototype, crunch numbers, and explore the final frontier from the comfort of their own offices, boldly going where no researcher may have gone before.

To accomplish this, Google Cloud teamed up with NASA FDL researchers, offering mentorship, compute resources, and AI expertise to guide them in the search for exoplanets — worlds that exist outside of our own solar system — where intelligent life may be waiting to be found.

exoplanet challenge

Hunting for exoplanets, millions of (very subtle) light patterns at a time

NASA's satellite dedicated to finding exoplanets, TESS (Transiting Exoplanet Survey Satellite), translates their universe-wide search into a complex data challenge. Every 27 days, TESS scans a portion of the sky, capturing millions of tiny fluctuations of light as exoplanets orbit their suns, generatating terabytes upon terabytes of raw data. For researchers, combing through it all was quite the challenge.

To help detect patterns in these massive datasets, NASA FDL's team relied upon Google Cloud AutoML, a suite of tools that simplifies the machine learning process for people with limited expertise. Using Cloud AutoML's resources helped researchers root out false positives, rapidly classify light curves, and identify key variables they hadn't noticed yet.

From data to planets

"Machine learning can tell us in the blink of an eye what is a planet and what isn't," said Hugh Osborn, an astronomer on the exoplanet team.

It didn't take long for researchers to notice the benefits of Cloud Auto ML. Running a single retrieval used to take researchers several days at a 94% accuracy rate. With Cloud Auto ML backed by Compute Engine, retrievals ran in seconds at 96% accuracy. That hundreds of retrievals could be run simultaneously with Cloud Auto ML added even more value for NASA FDL's research team.

astrobiology challenge

Imagining life on other planets starts by studying our own

Astrobiology, the study of life on other planets, has one major constraint: our home planet as its only point of reference. Earth is the only planet we know of with intelligent life, which is why scientists at NASA FDL use its biological data as a foundation to imagine what life on other planets looks like, and the environments they may reside in.

With Compute Engine, Cloud Machine Learning Engine, Google Kubernetes Engine, Cloud Dataflow, and other Cloud products, NASA FDL researchers could, for the first time, unify hundreds of disparate astrobiological datasets to connect the dots and look for meaningful patterns. In turn, these patterns help researchers better envision the broad range of life that may exist across the universe.

Researchers also generated millions of data points to simulate the effect of life on planets and atmospheres. This data was used to train ML models to detect life signatures on other planets that can be measured with new instruments and satellites in the future.

Understanding our place on the universe
Extraterrestrial surface

Passing on datasets — and inspiration — to future NASA FDL teams

Now the quest to find extraterrestrial life continues at NASA FDL. Research teams will build off of the progress made over the eight week summer session by continuing to use the same techniques and datasets.

Backed by Google Cloud's speed, scale, and intelligence, NASA FDL inches closer to answering our most fundamental questions, while also inspiring the scientific community at large.

All astrobiological datasets developed during the eight-week stretch will be made public, allowing other researchers to iterate on the models, dig deeper, and keep pushing until we make contact with intelligent life-forms on other planets.

NASA FDL researchers are pushing the limits of discovery, imagination, and knowledge. With help from Google Cloud, they can keep going above and beyond to search for a truth which is, as of the time of this writing, still out there.

Solutions

Artificial intelligence solutions

Prepackaged or build-your-own AI solutions for your enterprise.

Related stories

Google Cloud

Get started

Try it yourself

Get $300 credit on your first GCP project or try G Suite free for 14 days.

Need help on a bigger project?

Our experts will help you build the right solutions or find the right partner for your needs.