If a picture says a thousand words, what can one million say?
Adrian Dalca SM ’12 began taking photos of the Boston skyline when he moved to his current apartment on the MIT campus in 2010. Situated on the 22nd floor of his building, he thought he had an optimal vantage point to capture the city’s activities.
“Boston is dynamic and these photos allow you to see that,” Dalca says. “It has many different feels to it, and it isn’t just the seasons. At the end of the summer, you can see the different patterns of how people use boats. In the winter, people still try to sail. If the river is frozen, people will ski and skate on it.”
Before moving to Boston, photography was just an interest for Dalca, as he mainly snapped pictures of nature and different landscapes. Shortly after living in Boston, he started noticing distinct and varied weather patterns. He set up a time lapse on his camera to automatically take photos every 10 seconds to track thunderstorms.
“This started out as a hobby – I didn’t know how many photos I had that captured rainbows, ice breaking on the Charles River, buildings being torn down, or fires,” Dalca says.
He eventually amassed a collection of several thousand photos, and created a data set of the city skyline called the Boston Timescape Project.
Dalca is finishing his PhD in computer science, specializing in medical image analysis. His colleagues in MIT CSAIL approached him and asked if he would continue to expand his project, so they could use his photos to look at weather patterns.
“I didn’t think I would reach a million photos,” Dalca says. “Once I gathered a few hundred thousand, my friends at the computer vision lab and at some conferences asked me to release a data set so they could do some research.”
He then set up a web page to figure out how many photos he had – which was about 900,000. After reaching one million photos, he allowed his friends access to his website.
“I’m curious to see what can be done with this many photos,” Dalca says. “By taking these pictures, I was forced to explore these possibilities.”
Since this five-and-a-half-year project captured different seasons, like some mild and some frigid winters, Dalca says this collection of photos can be used to determine the temperature of the city or predict regional weather patterns.
“There are lots of things you can do with large data sets,” Dalca says.
Set to receive his PhD at the end of August, Dalca plans to move to another apartment while he completes his postdoc at Harvard Medical School. Although his location may be different, he says he will embark on a similar project, with hopes of contributing his work to potential research.