Forecasting "Tipping Points" with AI
Caltech-led researchers take key steps in developing deep-learning models that can predict irreversible shifts in climate and other systems
The writer Malcolm Gladwell popularized the term "tipping points" to refer to the moment when a trend or social behavior crosses a threshold and rapidly spreads everywhere. In physics, tipping points occur when systems—say, Earth's climate—reach an unstable point and topple over into a sea of change that is sometimes irreversible. Examples include global warming or the melting of polar ice caps.
While scientists have previously used AI models to predict smaller changes in weather, such as day-to-day variations, forecasting tipping points comes with more uncertainty and has thus proven more challenging. Now, a new Caltech-led paper demonstrates that an AI program—specifically a type of neural network called a recurrent neural operator (RNO)—can be used to predict when tipping points occur in simple models, including models of a climate-change system and simulations of turbulent airflow over a plane's wing.
The paper was published in the Proceedings of the National Academy of Sciences (PNAS).
"A tipping point is where you don't have that point of return anymore because it's nonstationary," says Anima Anandkumar, Caltech's Bren Professor of Computing and Mathematical Sciences and the principal author of the study. "Parts of a system are changing in a way so that you cannot bring the system back to its original state. That's why it is seen as something that could be catastrophic."
The new research, cited in a recent report from the United Nations on the importance of tipping points in climate science, was performed by Anandkumar and her colleagues at Caltech, the University of Colorado Boulder (CU Boulder), and the tech company NVIDIA. Because tipping points are so universal, the AI tool has potential applications in the fields of climate science, ecology, epidemiology, aeronautical design, and more.
"This work lays the foundations for characterizing tipping points and predicting when they might occur in the future," Anandkumar says. "We demonstrated it on a simplified climate model and a model of air turbulence over a wing—systems that weren't tractable with earlier methods."
In one part of the study, the researchers looked at a specific climate scenario in which low clouds over the oceans rapidly disappear due to rising carbon dioxide levels—a situation that has been predicted to occur in the future but has not yet been observed. This "point-of-no-return" loss of low cloud cover would further add to global warming. The researchers tested their AI program on simulated data to see if it could forecast when the clouds would disappear. The RNO was able to look more than two years ahead of the expected tipping point in the simulated data and predict its timing with an error of about 11 days.
"In the past, we used AI to learn mostly stationary systems that assume the weather from before will be the same as weather in future," Anandkumar says. "Our group has trained such AI-based weather models successfully in the past and can even predict extreme events like hurricanes with good accuracy. On the other hand, if you want to now model how that climate is changing and account for changes such as the carbon dioxide content, the system is no longer stationary, and you can no longer use standard machine learning principles."
The group's latest AI approach, based on an RNO, differs from other machine learning programs because it incorporates a built-in "memory" that tracks how the physics change over time. The RNO detects when the AI's predictions about the physics of a system no longer make sense, indicating a tipping point is imminent. In other words, when the AI's predictions no longer follow the rules of previously defined physics, a significant shift in the model is about to occur.
"The system is drifting away over time, and the laws from physics are no longer holding at the tipping point," Anandkumar says. "We can use the principles of physics on top of recurrent neural operators to make these predictions of when the tipping point is likely to
The PNAS paper also describes testing the RNO on simulations of airflow over a tilting plane wing to see if it could forecast a tipping point that occurs when the wing's lift drops precipitously. The RNO succeeded in predicting the tipping point, suggesting these kinds of AI programs could potentially help with future aeronautical and aerospace designs.
"In aerodynamics, quantities like the angle of attack can change gradually while the flow itself undergoes a much more abrupt transition, such as the onset of stall or a change in the wake," explains study coauthor Jane Bae (BS '12), assistant professor of aerospace at Caltech and a Susan Wu Scholar. "What is exciting about this work is that the model can recognize when the physics it has learned no longer adequately describes what is happening, providing a warning that the system may be approaching a tipping point. Being able to anticipate these qualitative changes before they occur could ultimately be very useful for aerodynamic prediction and design."
The paper is titled "Tipping Point Forecasting in Non-Stationary Dynamics on Function Spaces." In addition to Anandkumar, other Caltech authors are alumni Miguel Liu-Schiaffini (BS '25) and Sze Chai Leung (MS '24). Additional authors are Clare E. Singer (PhD '24) of CU Boulder and Nikola Kovachki (BS '16, PhD '22) and Kamyar Azizzadenesheli of NVIDIA. Funding was provided by the Mellon Mays Undergraduate Fellowship; Eric and Wendy Schmidt, through the AI2050 Senior Fellow Schmidt Sciences program; Caltech trustee Charles Trimble (BS '63, MS '64); the Office of Naval Research; the Carver Mead New Adventures Fund; and Caltech's Center for Autonomous Systems and Technologies (CAST). Computational time for the airfoil simulations was provided by the Pittsburgh Supercomputing Center, supported by the National Science Foundation.
Journal
Proceedings of the National Academy of Sciences
DOI
Does generative AI dilute markets for human-created work?
Summary author: Walter Beckwith
In a Policy Forum, Pamela Samuelson and colleagues discuss whether generative AI causes “market dilution,” i.e., crowding human-authors works out of markets and weakening incentives for people to create original works. Generative AI holds considerable promise for advancing scientific research, but its future depends in part on unresolved questions about copyright law. Because foundation models are trained on vast collections of material, including copyrighted books, images, and other human-authored works, more than 100 active US lawsuits are examining whether this practice is lawful. Although two federal courts have ruled that such training qualifies as “fair use,” a legal doctrine that permits certain uses of copyrighted material without permission, the broader legal dispute remains unsettled. One emerging argument, known as market dilution, proposes that AI-generated content could undermine entire markets for human-created works, even when it does not directly harm any copyrighted work. Here, Samuelson et al. question the conceptual basis of this theory and argue that it oversimplifies the relationship between human and AI creativity. According to Samuelson et al., any assessment of market dilution must account for how AI is used, the extent of human contribution, and the specific creators and markets affected. Claims of harm must be evaluated through rigorous empirical research focused on particular AI systems and creative markets, rather than broad assumptions about AI’s impact on human authorship. The authors suggest that collaboration between AI developers and researchers, alongside longitudinal data and surveys of creative practices, could help clarify these dynamics. If evidence eventually establishes that AI harms particular creative markets, they argue that legislatures, not courts resolving individual copyright disputes, are better equipped to develop targeted policies, such as licensing or funding schemes. They warn that court rulings restricting the use of copyrighted works to train AI models could create widespread legal uncertainty and significantly affect scientific researchers and developers who rely on these technologies. “If courts decide that developers of generative-AI models are likely diluting markets for human-authored works, rulings against fair uses may substantially raise the liability risks for all developers and users of generative AI in ways that are difficult to predict,” write the authors. “This could have considerable impacts on scientist users and builders of generative-AI systems, including open-source and domain-specific models.”
Journal
Science
Article Title
Market dilution, fair use, and generative AI
Article Publication Date
15-Oct-2026
No comments:
Post a Comment