Artificial Intelligence

Satellite image of Hurricane Helene, 2006

Penn professor and colleages develop Aurora AI

Penn professor Paris Perdikaris and collaborators developed Aurora, a machine-learning model that has predictive capabilities for air quality, ocean waves, tropical cyclone tracks, and weather.

5 min. read

A.I. is poised to revolutionize weather forecasting. A new tool shows promise

Paris Perdikaris of the School of Engineering and Applied Science and collaborators at Microsoft Research have created Aurora, a low-cost AI model that can predict a wide range of environmental events.

Is empathy required in the age of AI — or can we just outsource it?

Lynn Wu of the Wharton School says that machine-generated data produces worse content than human data when it’s fed into an AI algorithm, causing the output of generative AI to gradually degrade when it relies solely on itself.

Trading bots are evolving: What happens when AI cheats the market?

Itay Goldstein of the Wharton School discusses problems in the regulation of AI trading bots.

AI x Science Postdoctoral Fellowship

Bhuvnesh Jain and René Vidal have teamed up to create the AI x Science Fellowship, which builds on the thriving postdoctoral program of the Data Driven Discovery Initiative to foster cross-disciplinary collaboration among researchers across the University.

6 min. read

Your A.I. radiologist will not be with you soon

Charles E. Kahn Jr. of the Perelman School of Medicine comments on the use of AI in radiology.

Would you hire for this role if AI could do the first draft?

Ethan Mollick of the Wharton School says that the most effective AI implementation comes when humans and machines collaborate rather than when either works alone.

Designing the future: Penn Engineering’s 2025 Senior Design Project Competition

At Penn Engineering’s 2025 Senior Design Project Competition, four teams won awards for demonstrating how to improve stroke recovery, automate eye exams, turn old tires into battery components and improve the efficiency of AI computation on May 2. The four winners received awards in categories ranging from social impact to technological innovation.

How tech companies could shrink AI’s climate footprint

Benjamin Lee of the School of Engineering and Applied Science says that it’s more efficient to cool off a hot computer through liquid cooling rather than blowing air through the entire machine.

Generative AI can help doctors diagnose patients—but is it biased?

A new study by Annnenberg School for Communication professor Damon Centola tests if AI tools could help improve medical care without increasing bias. The findings suggest that “AI can meaningfully augment physician decision-making without introducing inequities in clinical decisions,” Centola says.

Filters