Pittsburgh researcher works on ‘early warning’ system for landslides, which are becoming more likely

  • Sarah Boden/WESA

Motorists were inconvenienced for months last year, when a section of Route 30 near East Pittsburgh was closed due to a landslide.

Last year was an active and brutal year for landslides in western Pennsylvania, which is already prone to this type of natural disaster. Land movements caused millions of dollars in property damaged, and evicted dozens of people from their homes.

Landslides are difficult to predict. But a Carnegie Mellon University robotics researcher is working to change that by creating an early-warning system using “deep learning.” This type of artificial intelligence programs computers to recognize patterns and then make predictions based on existing data.

CMU’s Christoph Mertz uses photographs of hillsides around Pittsburgh, which computer algorithms analyze to identify and calculate where a landslide is more likely to occur.

“You detect those things and then you can do statistics on them,” Mertz said. “Like you know, if you see that there is more dirt than their used to be. Or that the crack has become more larger, or more frequent, or has changed very recently.”

Mertz predicts this project couple be completed in about five years, when it may be even more crucial than it is today.

The land movements that occurred last year were due largely to a wetter than usual winter, that was likely related to climate change. Experts say western Pennsylvania can anticipate more landslides in its future.

Up Next

'You have no choice but to care:' In coal-centric W.Va., climate change discussion starting to grow