From AAS NOVA: “Using Machine Learning to Find Planets”



7 December 2018
Susanna Kohler

The first science image taken by TESS. Can computers help us to classify transit light curves from missions like TESS? [NASA/MIT/TESS]

How do we find the signals of exoplanets lurking in the vast quantity of data that comes out of a mission like Kepler or the Transiting Exoplanet Survey Satellite (TESS)?


A new study has some suggestions for how best to get computers to do the heavy lifting for us.

Two common false positives — grazing eclipsing binaries (left) and background eclipsing binaries (right) — can mimic the signal of a transiting planet. [NASA/Ames Research Center]

Managing a Mess of Data

Recent years have seen a boom in exoplanet research — in large part due to the enormous data sets produced by transiting exoplanet missions like Kepler and, now, TESS. But the >3,000 confirmed Kepler planets weren’t all just magically apparent in the data! Instead, the discovery of planets is the result of careful classification of transit-like signals amid a sea of false positives from things like stellar eclipses and instrumental noise.

Given the number of light curves that need classifying, we can use any automated help we can get. Enter machine learning, a process by which computers can be trained to identify patterns and make decisions. Using a tool called deep learning, scientists have already shown that machines can do a pretty good job of automatically classifying Kepler transit signals as either exoplanets or false positives. But can we do even better?

Local (left) and global (right) views of the light curves (cyan) and centroids (maroon) for an example confirmed planet (top) and background eclipsing binary (bottom). Click for a closer look. [Ansdell et al. 2018]

The recent 2018 NASA Frontier Development Lab provided an excellent opportunity to find out. This eight-week research incubator was aimed at applying cutting-edge machine-learning algorithms to challenges in the space sciences. As part of this lab, two machine-learning experts were paired with two space-science researchers to try to improve machine-learning models for exoplanet transit classification. The results are presented in a new publication led by scientist Megan Ansdell (Center for Integrative Planetary Science, UC Berkeley).

Insider Knowledge

Ansdell and collaborators started with a basic machine-learning model that classified signals based on straightforward local and global views of the light curves. To improve upon it, they added scientific domain knowledge — information or insight that might not be generally known, but can be provided by a domain expert.

Recall (top; the fraction of true planets recovered) and precision (bottom; the fraction of classifications that are correct) of the Exonet model, as a function of MES, a measure of the signal-to-noise of candidate transits. [Ansdell et al. 2018]

More Planets to Come

How did Ansdell and collaborators do? Using their modified model, “Exonet”, a computer can classify a Kepler data set with 97.5% accuracy and 98% average precision. That means that 97.5% of its classifications — exoplanet or false-positive — are correct, and an average of 98% of transits classified as planets are true planets. Not bad, for a machine!

One of the added benefits of the authors’ model is that it is ideal for generalization — for example, from Kepler to TESS data. The authors are currently working on a study using Exonet to classify simulated TESS data. And yesterday’s first public data release from TESS has provided plenty of fresh data to work with in the future!


“Scientific Domain Knowledge Improves Exoplanet Transit Classification with Deep Learning,” Megan Ansdell et al 2018 ApJL 869 L7.

See the full article here .


Please help promote STEM in your local schools.

Stem Education Coalition


AAS Mission and Vision Statement

The mission of the American Astronomical Societyis to enhance and share humanity’s scientific understanding of the Universe.

The Society, through its publications, disseminates and archives the results of astronomical research. The Society also communicates and explains our understanding of the universe to the public.
The Society facilitates and strengthens the interactions among members through professional meetings and other means. The Society supports member divisions representing specialized research and astronomical interests.
The Society represents the goals of its community of members to the nation and the world. The Society also works with other scientific and educational societies to promote the advancement of science.
The Society, through its members, trains, mentors and supports the next generation of astronomers. The Society supports and promotes increased participation of historically underrepresented groups in astronomy.
The Society assists its members to develop their skills in the fields of education and public outreach at all levels. The Society promotes broad interest in astronomy, which enhances science literacy and leads many to careers in science and engineering.

Adopted June 7, 2009