Big Data

How one data scientist went from coding camp to defending the earth from meteorites

A Holberton School student will be rubbing shoulders with students from Berkeley and Cambridge as part of a major NASA internship looking for meteorites.

Image: NASA

Everyone wants to launch a code camp these days. Even the White House is backing its own initiative. Despite the rush to spin up new schools to try to train developers to meet rising demand, there is little information about how good the students are who graduate from these programs. Do they stack up?

While it's too soon to give a definitive answer, Holberton School in San Francisco just got a big boost to its bona fides. Holberton student Sravanthi Sinha was just accepted into one of the most prestigious engineering internships in the world, NASA's Frontier Development Lab with the SETI Institute in Mountain View, California. The interns, gathered from around the world from top universities such as U.C. Berkeley and Cambridge, are teaming up to help NASA plan for a potential cosmic armageddon, an asteroid strike on earth.

Think of it as machine learning for planetary defense. It's also a very good indication that some code academies really work. I recently spoke to Sinha to learn more about her summer work for SETI and how Holberton prepared her for the challenge.

Machine learning for planetary defense? Really!?

When I asked Sinha what she'll be doing all day at SETI in the NASA internship, her response was anything but typical of most internships: Data scientist on a "breakthrough" project idea—developing an unmanned aerial vehicle (UAV) to aid in finding meteorites in the field.

SEE: More women developers? Hell yes, says Holberton School

And what did you do this summer, dear reader?

To better understand Sinha's work, it's useful to know that meteorites that are currently discovered on earth are identified visually through a labor-intensive, manual search in the field. Those that we find in this manner tend to be big. Smaller meteorite falls, which are more frequent, are harder to recover. As a result, the number of recovered meteorites on known approach orbits is small.

As such, Sinha told me her "project is aimed at developing a small UAV—such as a commercially available quadcopter—equipped with cameras and on-board processors that can identify potential meteorite targets in the search areas calculated from triangulated meteor observations." This, she continues, "will make it possible to discover meteorites even from smaller falls."

So where does the data science come in? Sinha explained:

We'll apply machine learning techniques to sample images in the lab and then the resulting search algorithms will be transferred to small processors on board the UAV. The machine learning will be developed using NVIDIA computing hardware—which will remain in the lab under NASA and SETI Institute control. We expect that the UAV, cameras, and onboard computing processing hardware will all be commercially available items.

How does one prepare for planetary defense?

Not surprisingly, Sinha is ecstatic about the honor of being chosen, telling me she's on "cloud nine." Part of the reason, she said, is that she "made many sacrifices to come this far and, at the end of the day, it gives meaning to my life." Working for NASA "has always been my dream," she concludes, while stressing the internship "is just the beginning."

This NASA dream job was never an obvious outcome for her. Sinha grew up in India and and earned a bachelor's degree in electronics and communication engineering from Jawaharlal Nehru Technological University in Hyderabad. She then interned at National Resource for Network Biology (NRNB) in 2012, and completed the Google Summer of Code in 2013 and 2014, first as a student and then as a mentor.

SEE Women in tech: Under-represented and paid less

All great achievements, but they don't explain why she ended up at Holberton, and how that led her to NASA.

Holberton School, which I've covered before is an excellent example of one of the emerging new programs teaching beginners to become full-stack software engineers, but it's not the only one. There is, for example, Ecole 42 that started in Paris and is now coming to Silicon Valley, not to mention ESBC in Berlin. There are dozens to choose from, and more crop up all the time.

When pressed on why she chose Holberton School, the answer came down to engineering. As Sinha informed me, her undergraduate degree didn't give her "a chance to take a lot of hardcore computer science and programming courses" as "the curriculum mostly revolved around electronics and embedded engineering with limited software engineering coursework." She needed something that would round out her experience with a deep immersion into software engineering.

As she stressed, the Holberton curriculum is not limited to one language or one web stack. Every week students cover algorithms, low-level programming, front-end, back-end, sys-admin and devops. Interestingly, she said, "On top of those tech tracks, we also train on soft skills like networking, public speaking, and writing, which gives us more confidence and also a huge advantage versus tech-only developers."

This is very different from her university days, where "scoring a higher GPA was the only goal. There were some hands-on labs but mostly it was theoretical," she said. The big draw for Holberton School's curriculum, she summarized, is that it "gives you challenging projects that teach you how to fix problems and build software."

Or, how to get super-impressive work with NASA. Not bad.

Also see

About Matt Asay

Matt Asay is a veteran technology columnist who has written for CNET, ReadWrite, and other tech media. Asay has also held a variety of executive roles with leading mobile and big data software companies.

Editor's Picks