The Boston Timescape Project, a personal endeavor launched in 2010 by Adrian Dalca, SM ’12, PhD ’16, features more than one million photos of the Boston skyline, taken during different times, weather conditions, and seasons. And now it has become a rich resource for colleagues who study imaging and weather.
Dalca began taking photos of the Boston skyline as a graduate student living on the 22nd floor of Eastgate, his MIT residence, where 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, if the river is frozen, people will ski and skate on it.”
Before moving to the Boston area, Dalca mainly snapped pictures of nature and different landscapes. While at MIT, he started noticing distinct and varied weather patterns and began taking photos from Eastgate, using several high-resolution cameras. Sometimes he has taken one shot a day; other times he’s captured hundreds of images quickly. When a thunderstorm has been predicted, for example, he’s set up his camera to automatically take an image every 10 seconds.
“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,” he says.
While Dalca was working on his PhD in computer science, specializing in medical image analysis, his colleagues in the MIT Computer Science and Artificial Intelligence Laboratory (CSAIL) asked if he would continue to expand his project.
“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.” So he tallied his photos—and discovered he had about 900,000. After reaching a million, he built the website bostontimescape.com and allowed access to researchers on request.
Since this project has captured multiple corresponding seasons in different years, including some mild and some frigid winters, the collection can be used to determine regional weather patterns, Dalca says.
“There are lots of things you can do with large data sets,” he says. Capturing dramatic weather patterns was a great motivator, he adds, but not the main goal of the project, which also documented human activities and architectural changes.
Although he completed his PhD work last summer, Dalca and his wife, Monica Stanciu, plan to remain on the 22nd floor while she finishes her PhD in biology. In the fall he began two years as a postdoc at Harvard Medical School. Meanwhile, his photography projects—including time lapse images of ballet dancers—will continue.
This new data poisoning tool lets artists fight back against generative AI
The tool, called Nightshade, messes up training data in ways that could cause serious damage to image-generating AI models.
Everything you need to know about artificial wombs
Artificial wombs are nearing human trials. But the goal is to save the littlest preemies, not replace the uterus.
Rogue superintelligence and merging with machines: Inside the mind of OpenAI’s chief scientist
An exclusive conversation with Ilya Sutskever on his fears for the future of AI and why they’ve made him change the focus of his life’s work.
Data analytics reveal real business value
Sophisticated analytics tools mine insights from data, optimizing operational processes across the enterprise.
Get the latest updates from
MIT Technology Review
Discover special offers, top stories, upcoming events, and more.