Original image

Underground Wonders

Original image

More than just a hole in the ground, every cave has its own story. Caves are born in many different fashions, which leave them with different personalities.

Lava Tubes

Lava tube caves are formed when lava flows down the side of a volcano. The lava exposed to the air cools and hardens first, while the lava underneath continues to flow out, leaving an open tube behind when the eruption is finished. The longest and deepest lava tube is 40-mile-long Kazumura Cave on the southeast slope of Mauna Loa in Hawaii.

Tree Molds


Mount St. Helens has plenty of lava tube caves, and some lava tree molds. The tree molds were formed when an eruption 1,950 years ago knocked down trees and covered them with lava. When the trees burned, the opening left behind would be a perfect mold of the logs.

Sea Caves


Sea caves are erosional caves, formed by the action of waves against rock, usually along an existing fault. The Blue Grotto of Capri is a popular and photogenic cave due to the appearance of light from the bottom of the cave. Sunlight enters the cave through underwater channels and reflects off the limestone floor.
More types of caves, after the jump.

Wind Caves


Wind caves are formed by erosion of sandstone by blowing wind. They tend to be pretty shallow and rounded. Gaviota, California is home to some beautifully sculpted wind caves.

Glaciar Caves


Glaciar caves are also erosional, usually carved by mountain streams flowing into glaciers, but can also be formed by volcanic heat from below. Pictured is a cave carved by water flowing into the Fox Glacier in New Zealand.

Limestone Caves


Solutional caves are formed when the existing rock is dissolved. The most common type is the limestone cave, because rainwater and groundwater contain acids which dissolve limestone over time. An example is Mammoth Cave system in Kentucky, the world's most extensive cave system at 367 combined miles (and still not completely mapped)!

Another limestone cave formation, the Sarawak Chamber in the Gunung Mulu National Park in Malaysia is the world's largest single cave chamber, measuring 2,300 feet long, 1,300 feet wide and at least 230 feet high!


In New Mexico, Lechuguilla Cave and Carlsbad Caverns are a different kind of solutional cave. They were formed by sulphurous acids rising from below. The minerals from the acidic fumes leave amazing and fragile gypsum and sulphur formations such as chandeliers, soda straws, and cave pearls. Although Carlsbad Caverns is a major tourist draw, the more recently-mapped Lechuguilla Cave is off-limits to visitors in order to preserve the environment.

Salt Caves

Salt caves are also solutional caves, forming and collapsing relatively quickly. The world's longest salt cave (nearly four miles) was discovered just last year on Qeshm Island off the coast of Iran.

For all kinds of information on caves, I recommend a tour of The Virtual Cave.

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