Mushroom Clouds in Mississippi: the Little-Known History of Nuclear Testing in the American South

When you think of nuclear test sites, remote Pacific islands and desert wastelands come to mind. Not many people think of Hattiesburg, MIssissippi -- but the United States carried out two nuclear tests in a little town just outside that city in 1964, in an operation that went by the reassuring-to-no-one moniker Project Dribble. No one saw any mushroom clouds, though, because the two nukes they tested were detonated underground, in a 3,000-foot-deep shaft drilled into a reservoir of ancient salt called the Tatum Salt Dome (left over from the Mesozoic era, when that part of the state was covered by sea water). Those were the early days of the Nuclear Test Ban, and we were trying to figure out if other nations could cheat by doing underground tests that could fool seismographs -- so we did a few of our own. Here's a bit of Shatner-narrated footage of the tests:

An area five miles downwind and two miles upwind from the test site was evacuated. Inconvenienced residents were paid $10 per adult and $5 per child for their trouble, and many came back to find collapsed shelves in their kitchens, cracks in their ceilings, and wells that had gone dry. People a few miles from the site who weren't evacuated said that they felt three separate shocks, during which the soil rose and fell like ocean waves. Two miles from the blast, the shockwave shook pecans from the pecan trees. In Hattiesburg, thirty miles away, tall buildings swayed for several minutes, and people noticed rivers and streams running black from churned-up silt. All this from a bomb one-third the strength of the one dropped on Hiroshima twenty years earlier. When a crew lowered a television camera and some equipment into the underground crater after the explosion, it measured more than a hundred feet in diameter. Three months later, the air in the hole it made was still four hundred degrees.

The government reimbursed people for damage to their homes, and to ease fears about radioactive drinking water, they built a pipeline to serve people who lived near the test site. Over the years, there have been scattered claims of higher-than-average rates of illness in the area, and at least one person was paid by the government to resolve unspecified health claims, but there hasn't been any great public outcry. A lot of younger people in Lamar County, Mississippi have never heard of Project Dribble -- but if they were to venture past the gates erected by the Department of Energy to the test site, they would find a stone monument and a brass plaque warning future generations not to drill in the area. (Let's hope that plaque can last 10,000 years or so, when people -- if there are any -- will really need it.)

Oh, and as for the test results, we figured out that you could indeed fool a seismograph by performing nuclear tests in underground caves, which significantly muffle shockwaves. Thanks to Project Dribble, though, we pioneered new ways to catch nuclear cheaters.

Original image
iStock // Ekaterina Minaeva
Man Buys Two Metric Tons of LEGO Bricks; Sorts Them Via Machine Learning
May 21, 2017
Original image
iStock // Ekaterina Minaeva

Jacques Mattheij made a small, but awesome, mistake. He went on eBay one evening and bid on a bunch of bulk LEGO brick auctions, then went to sleep. Upon waking, he discovered that he was the high bidder on many, and was now the proud owner of two tons of LEGO bricks. (This is about 4400 pounds.) He wrote, "[L]esson 1: if you win almost all bids you are bidding too high."

Mattheij had noticed that bulk, unsorted bricks sell for something like €10/kilogram, whereas sets are roughly €40/kg and rare parts go for up to €100/kg. Much of the value of the bricks is in their sorting. If he could reduce the entropy of these bins of unsorted bricks, he could make a tidy profit. While many people do this work by hand, the problem is enormous—just the kind of challenge for a computer. Mattheij writes:

There are 38000+ shapes and there are 100+ possible shades of color (you can roughly tell how old someone is by asking them what lego colors they remember from their youth).

In the following months, Mattheij built a proof-of-concept sorting system using, of course, LEGO. He broke the problem down into a series of sub-problems (including "feeding LEGO reliably from a hopper is surprisingly hard," one of those facts of nature that will stymie even the best system design). After tinkering with the prototype at length, he expanded the system to a surprisingly complex system of conveyer belts (powered by a home treadmill), various pieces of cabinetry, and "copious quantities of crazy glue."

Here's a video showing the current system running at low speed:

The key part of the system was running the bricks past a camera paired with a computer running a neural net-based image classifier. That allows the computer (when sufficiently trained on brick images) to recognize bricks and thus categorize them by color, shape, or other parameters. Remember that as bricks pass by, they can be in any orientation, can be dirty, can even be stuck to other pieces. So having a flexible software system is key to recognizing—in a fraction of a second—what a given brick is, in order to sort it out. When a match is found, a jet of compressed air pops the piece off the conveyer belt and into a waiting bin.

After much experimentation, Mattheij rewrote the software (several times in fact) to accomplish a variety of basic tasks. At its core, the system takes images from a webcam and feeds them to a neural network to do the classification. Of course, the neural net needs to be "trained" by showing it lots of images, and telling it what those images represent. Mattheij's breakthrough was allowing the machine to effectively train itself, with guidance: Running pieces through allows the system to take its own photos, make a guess, and build on that guess. As long as Mattheij corrects the incorrect guesses, he ends up with a decent (and self-reinforcing) corpus of training data. As the machine continues running, it can rack up more training, allowing it to recognize a broad variety of pieces on the fly.

Here's another video, focusing on how the pieces move on conveyer belts (running at slow speed so puny humans can follow). You can also see the air jets in action:

In an email interview, Mattheij told Mental Floss that the system currently sorts LEGO bricks into more than 50 categories. It can also be run in a color-sorting mode to bin the parts across 12 color groups. (Thus at present you'd likely do a two-pass sort on the bricks: once for shape, then a separate pass for color.) He continues to refine the system, with a focus on making its recognition abilities faster. At some point down the line, he plans to make the software portion open source. You're on your own as far as building conveyer belts, bins, and so forth.

Check out Mattheij's writeup in two parts for more information. It starts with an overview of the story, followed up with a deep dive on the software. He's also tweeting about the project (among other things). And if you look around a bit, you'll find bulk LEGO brick auctions online—it's definitely a thing!

Original image
Name the Author Based on the Character
May 23, 2017
Original image