Dec 14, 2017

Axios Science

By Alison Snyder
Alison Snyder

Thanks for reading Axios Science. If you enjoy it, please invite your friends and colleagues to sign up for the newsletter. And, as always, send me your feedback. You can reply to this email or send me a note at

1. Two new planets found with Google AI

Two new planets have been discovered by giving a Google machine learning algorithm data from NASA's Kepler Space Telescope.

The details:

  • Kepler-90i is the eighth planet to be found in the Kepler-90 system, which is 2,545 light years away from Earth. “This discovery ties Kepler-90 with our own solar system for having the most known planets," says NASA's Paul Hertz in a press conference.
  • The rocky planet is about 30% larger than Earth, likely has an average temperature of about 800°F, and orbits its star every 14.4 days. All of the known planets in the Kepler-90 system are closer to their star than Earth is to the Sun, says astronomer and co-discoverer Andrew Vanderburg from the University of Texas at Austin.
  • A second Earth-sized planet, Kepler-80g, was also spotted.
  • Exoplanets can be found by looking for a change in a star's brightness as a planet passes in front of it. The AI — a neural network — learned to identify planets from 15,000 Kepler signals that had already been labeled by scientists. When the AI then looked at data from 670 stars, it found the two planets.

What's next: They hope to study Kepler's data from more than 150,000 stars to see if they can spot weak signals researchers missed.

2. Cancer-detecting AI

Medicine is poised to be one place where AI makes a mark. In a study published this week, researchers report that a machine algorithm was as good — or better — than pathologists at detecting the spread of a type of breast cancer.

For all the talk about the promise of AI radically changing medicine, this is one of the first peer-reviewed studies to back claims that algorithms can detect abnormalities in pathology slides, says Eric Topol from the Scripps Research Institute.

The bottom line: Radiologists and pathologists are likely to be the first in medicine affected by AI. But researchers working on the technologies don't see them replacing doctors, and instead aiding them. And even that role will require more data about the impact on the medical profession and whether AIs are accurate enough to diagnose patients.

“It is the early days," Aidoc CEO Elad Walach says. “There's not enough research at this point. Deep learning has been commoditized generally but it hasn't been commoditized for the medical domain. The algorithms out there aren't good enough as is. We need a lot of R&D to make AI work in this space. It is not just plug and play."

Read the rest of the story here.

3. Axios stories to spark your brain:
4. California wildfires, by the numbers

Erin writes: We used to define fire by seasons — they varied from place to place, but there tended to be a period of time that we could rely upon to have no fires. That is no longer the case, as the destructive fires burning this December in Southern California make clear.

The above chart shows all fires that burned over 300 acres each year from 2000 to 2017 in California, including this month's blazes.

Read the rest of her story here.

5. What we're reading elsewhere:
  • A gem from the New York Times's Natalie Angier about precious stones as a window into Earth's chemistry and physics. She writes: "Precious gems are born of strife, of shotgun marriages between hostile chemical elements, and they're tough enough to survive cataclysms that obliterate everything around them."
  • City treasures: As the L.A. subway system expands, so does the Ice Age fossil record, from the AP's Christopher Weber. Prized finding of paleontologists working under the city: a skull from a juvenile mammoth.
  • Consciousness, shared: Conjoined twins whose thalami are connected so that they share sensory information raise interesting questions about our sense of self, writes Michael Harris in a documentary film review for the Walrus.
6. Something wondrous

Each of Saturn's iconic rings — made of billions of pieces of ice, rock and organic compounds ranging in size from a marble to a house — swirls around the planet at a different speed. How they formed and evolved with the planet itself is a window into how planetary systems form around other stars.

The Cassini spacecraft gave researchers an up-close look at the rings as it dove between them and the planet. Researchers are beginning to announce some of the findings from the final months of the mission called the Grand Finale:

  • The rings cast shadows on Saturn and may rain tiny particles of ice on the planet that can affect its upper atmosphere.
  • They are home to propeller moons — typically football field-sized masses too small to be seen by Cassini. But they create disturbances in the rings that the spacecraft detected and tracked for over a decade. In its final months, Cassini grazed the rings and sent unprecedented images of the propellers, says SETI Institute's Matthew Tiscareno, who is part of the team.
  • Saturn's rings may be younger than previously thought and formed as early as 150 million years ago, according to work presented at the American Geophysical Union's fall meeting this week and reported in Science.
  • The conclusion depends, in part, on the mass of Saturn's primary ring. A large mass is thought to indicate an old ring born billions of years ago when raw material abounded in the solar system.
  • Tiscareno says there is a discrepancy between Cassini's Grand Finale measurements of gravitational effects of the rings' mass and a decade-plus of the spacecraft tracking the orbits of the planet's moons. "Until that discrepancy is ironed out, the Grand Finale gravity measurement for the mass of the rings cannot be considered to be final."
Alison Snyder