Tom Dietterich

Simple curiosity drove Tom Dietterich’s broad research interests that span several areas of science, engineering, and biomedicine.

Widely recognized for his role in creating and nurturing the area of machine learning — a field revolutionizing science, industry and government — his influence was acknowledged this year by Oregon State University when he was selected to be a “Distinguished Professor,” the highest honor for faculty.

“Tom Dietterich is known as a renaissance man,” says Terri Fiez, Head of the School of Electrical Engineering and Computer Science.

Dietterich has a more modest way of stating it: “I like to say I have research attention deficit disorder in the sense that I’m curious about many things and I like to work on a lot of different projects.”

In graduate school he realized that computer science was much more than just programming, and got hooked on the area of artificial intelligence because it examined fundamental questions about psychology and philosophy.

Over his career, he has worked on a wide variety of problems ranging from drug design to user interfaces to computer security. His current focus is on ways that computer science methods can help advance ecological science and improve our management of the Earth’s ecosystems.

“I realized I wanted to have an impact on something that really mattered — and certainly the whole Earth’s ecosystem, of which we are part, is under threat in so many ways.

“And so if there’s some way that I can use my technical skills to improve both the science base and the tools needed for policy and management decisions, then I would like to do that,” he says. “I am passionate about that.”

This passion has led to several projects including research in wildfire management, invasive vegetation and bird migration.

For example, Dietterich’s research is helping scientists at the Cornell Lab of Ornithology answer questions like: How do birds decide to migrate north? How do they know when to land and stop over for a few days? How do they choose where to make a nest?

Video: Machine Learning Applied to Bird Migration

Tens of thousands of volunteer birdwatchers (citizen scientists) all over the world contribute data to the study by submitting their bird sightings to the eBird website. The amount of data is overwhelming — in March 2012 they had over 3.1 million bird observations.

“We take this data which is rather large and messy and apply techniques of machine learning to convert them into accurate models for prediction and recognition,” Dietterich says.

Machine learning can uncover patterns in data to model the migration of species like the black-throated blue warbler traveling from the Dominican Republic through North America to southern Canada. But, he says, there are many other applications for the same techniques which will allow organizations to better manage our forests, oceans and endangered species, as well as improve traffic flow, public water systems, the electrical power grid, and more.

 “It's been a thrill to be a part of this field as it's developed and to see all the different ways that machine learning is transforming society,” Dietterich says.