Original image

Europe's "Iron Harvest"

Original image

World War I ended nearly 100 years ago, but in some places along what used to be the Western Front, in France and Belgium and near the Swiss border, the shadow of death and danger cast by that war lives on. It's estimated that for every square meter in the vast battlefields around Verdun, France, a ton of explosive shells were dropped. One in four failed to go off. Many of those are still in the ground today, despite decades of work by bomb removal workers -- more than 600 of whom have died trying to clear the fields in France alone since 1945 -- and they are still dangerous. Some are live, and even more potentially deadly than when first dropped, and many others are poisonous, leaching toxic yellow sludge into the ground and posing health hazards to any who might touch them -- as hapless tourists on old battlefields sometimes do. (Not to mention vast caches of dumped mustard gas, in forests and in the ocean not far from public beaches, five grams of which can kill an adult via skin contact.)

The Iron Harvest is what Belgian and French farmers reap when they plow their fields along what used to be the Western Front. Every year, they find tons of unexploded ordnance, barbed wire, shrapnel, bullets, and trench supports. And because this was trench warfare, often fought in swampy conditions, much of the unexploded bombs worked their way down deep into the muck and were encased there, meaning no matter how hard the bomb removal crews work, sometimes the only things that can unearth the bombs are time and a farmer's plow. When they recover these objects, farmers simply leave them on the edges of their fields to be collected and disposed of by the authorities. Above: the iron harvest of a French farmer in the Somme (picture by

A particularly productive "harvest" can yield stacks of bombs or mustard gas canisters as tall as a house. This iron harvest photo by flickr user Salfordian gives you a sense of how much one field can turn up -- and how unimaginably hellish these now verdant and peaceful-looking fields must once have been.


Of course, there are "iron harvests" in former battlefields all over the world, not just France and Belgium. Southeast Asia is littered with unexploded ordnance -- the US dropped more bombs on Vietnam than were dropped during all of WWII. The citizens of Okinawa -- known by some military folk as "Bomb Island" -- are routinely evacuated so newly-discovered bombs can be cleared from urban areas and beaches. A German highway worker was recently killed when he hit a bomb while making repairs to a section of the Autobahn. More than 100 Afghan civilians -- most of them children and farmers -- are killed or wounded every month from mines and unexploded bombs, many dating back to the 80s.

Even in the United States, according to the EPA, there are unexploded bombs "at 16,000 domestic inactive military ranges within the United States that pose an 'imminent and substantial' public health risk and could require the largest environmental cleanup ever, at a cost of at least US$14 billion. Some individual ranges cover 500 square miles (1,300 km2), and, taken together, the ranges comprise an area the size of Florida." Which is to say, one of these days we may have our own iron harvest.

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