Sky and Telescope - December 2017 - 25

The algorithm turned up another surprise: ﬁve runaway
stars not coming from the Milky Way's center, each traveling
between 400 and 780 kilometers per second (900,000 to 1.7
million mph). These stars may once have been part of binary
systems in the Milky Way's disk that were ejected when
their stellar partners went supernova. But such explosions
don't typically eject stars at speeds this high. "Our algorithm
picked up a very special case of this mechanism," Rossi says.
Gaia's next data release, which will help validate Rossi's
ﬁnds, will come in April 2018.
Astronomers have had success honing machine learning to build samples of known, rare objects. But self-taught
algorithms can do more than that - they can also discover
entirely new types of celestial gems.
Detecting the unexpected comes second nature to
humans, who excel at pattern recognition and can therefore
easily pick out rare and unusual objects. Citizen science has
reams of examples: green pea galaxies, Hanny's Voorwerp,
and Tabby's Star (S&T: June 2017, p. 16), to name a few.
Now machines are becoming capable of, as Walkowicz
puts it, "systematizing serendipity." Walkowicz is working
with graduate student Daniel Giles (Illinois Institute of Technology) to train an algorithm that separates Kepler-observed
stars into groups and ranks them by "weirdness." Using
Tabby's Star as a test subject, Walkowicz and Giles are creating the tool to pick out Tabby's Star analogs in Kepler data
and, eventually, in other surveys such as LSST.

Making Connections
Some are taking these programs even further - rather than
ﬁnding needles in a haystack for future study, astronomers
can apply machine learning to inspect all of the hay. Selftaught algorithms can make unforeseen connections between

Rather than finding needles in a
haystack, astronomers are using machine
learning to study all of the hay.
features in the data, enabling computers to classify and characterize objects en masse.
That ability may help solve one of the biggest problems
facing the LSST. When the telescope comes online early next
decade, it'll produce 15 terabytes' worth of brightness measurements every night, but it'll be missing something crucial:
spectra. Spectral lines from the heavy elements that lace a
star's gas reveal its physical properties, such as its surface
temperature and gravity. However, follow-up spectroscopy
will only be feasible for 0.1% of LSST-observed stars.
Nevertheless, astronomers can learn a lot about a star by
its color, as well as by its light curve, which tracks the change
in brightness over time. In 2015 Adam Miller, then a graduate student at University of California, Berkeley, and Joshua
Bloom, his advisor, realized that machine learning could connect brightness measurements of variable stars to the physical
properties normally gleaned from their spectra.
They conducted a proof of concept using a collection of
decision trees, collectively known as a random forest. Each tree
asks a series of questions to separate the variable stars into
groups. The questions aren't programmed in; the trees decide
the questions themselves based on the data they train on.
In this test case, the training set consisted of 9,000 variable stars observed in the Stripe 82 survey, a 315-squaredegree ﬁeld repeatedly imaged by the SDSS project. Followup spectroscopy came from the 6.5-meter Multiple Mirror
Telescope in Arizona.

TREES TO FOREST: LE A H TISCIONE / S&T; LOST IN THE WOODS: JA K E VA NDERPL AS

Random Forest
Input data

Tree
ee 1

Tree
ee 2

ee 3
Tree

Class A

Class B

Output: Class A

t FROM TREES TO FORESTS Random forest algorithms, such as the
one shown in this simple schematic, are a collection of decision trees.
Each tree is shaped slightly differently from its neighbors, asking different
questions of the data and separating data points in different ways. The
outputs from all the trees are averaged before providing an answer. As in
neural networks, humans don't program the decision points - the trees
determine what questions to ask from the data itself.
p LOST IN THE WOODS A decision tree asks questions to separate
data - the more questions it asks, the more it divides the data (left). But
a single series of decisions may miss the forest for the trees, carving up
the training data so much that the algorithm is no longer useful for classifying new data sets. By averaging an ensemble of decision trees (right),
a random forest algorithm reaches more robust conclusions.
s k y a n d t e l e s c o p e . c o m * D E C E M B E R 2 0 17

http://www.skyandtelescope.com

Sky and Telescope - December 2017

Table of Contents for the Digital Edition of Sky and Telescope - December 2017