AI Learns to Build Simple Equations for Complex Systems
Duke researchers have developed a new AI system that helps scientists make sense of complex systems that change over time, from climate patterns and electrical circuits to biological signals. Instead of producing black-box predictions, the tool identifies simple, interpretable rules that explain how these systems behave and evolve. By turning massive streams of data into understandable equations, the approach could help researchers detect instability earlier, improve long-term forecasts and accelerate scientific discovery across many fields. The work opens the door to using AI not just to predict outcomes, but to deepen understanding of the world’s most complex processes.
This research is supported by the National Science Foundation (NSF), the Army Research Office and DARPA.
