811 citations · 2.4k across the 12 of their papers we have counts for
13 papers
Training Language Models to Fail Gracefully
Daman Arora, Xuecheng Liu, Himanshu Gaurav Singh +6
Reinforcement learning makes language models better at solving tasks, but the same mechanism also rewards guessing. When success is the only way to earn reward, opting for a safe f…
Radiative and Dynamical Controls on the Land-Ocean Warming Contrast in Climate Models
Paolo Giani, Arlene M. Fiore, Raffaele Ferrari +3
Surface air over land warms substantially more than over the ocean under greenhouse forcing, a phenomenon known as the land-ocean warming contrast. Current explanations for this co…
Bringing statistics to storylines: rare event sampling for sudden, transient extreme events
Justin Finkel, Paul A. O'Gorman
A leading goal for climate science and weather risk management is to accurately model both the physics and statistics of extreme events. These two goals are fundamentally at odds:…
Non-local parameterization of atmospheric subgrid processes with neural networks
Peidong Wang, Janni Yuval, Paul A. O'Gorman
Subgrid processes in global climate models are represented by parameterizations which are a major source of uncertainties in simulations of climate. In recent years, it has been su…
Climate-Invariant Machine Learning
Tom Beucler, Pierre Gentine, Janni Yuval +10
Projecting climate change is a generalization problem: we extrapolate the recent past using physical models across past, present, and future climates. Current climate models requir…
Tropical precipitation clusters as islands on a rough water-vapor topography
Ziwei Li, Paul A. O'Gorman, Daniel H. Rothman
Tropical precipitation clusters exhibit power-law frequency distributions in area and volume (integrated precipitation), implying a lack of characteristic scale in tropical convect…
Use of neural networks for stable, accurate and physically consistent parameterization of subgrid atmospheric processes with good performance at reduced precision
Janni Yuval, Paul A. O'Gorman, Chris N. Hill
A promising approach to improve climate-model simulations is to replace traditional subgrid parameterizations based on simplified physical models by machine learning algorithms tha…
Stable machine-learning parameterization of subgrid processes for climate modeling at a range of resolutions
Janni Yuval, Paul A. O'Gorman
Global climate models represent small-scale processes such as clouds and convection using quasi-empirical models known as parameterizations, and these parameterizations are a leadi…
Response of Vertical Velocities in Extratropical Precipitation Extremes to Climate Change
Ziwei Li, Paul O'Gorman
Precipitation extremes intensify in most regions in climate-model projections. Changes in vertical velocities contribute to the changes in intensity of precipitation extremes but r…
Using machine learning to parameterize moist convection: potential for modeling of climate, climate change and extreme events
Paul A. O'Gorman, John G. Dwyer
The parameterization of moist convection contributes to uncertainty in climate modeling and numerical weather prediction. Machine learning (ML) can be used to learn new parameteriz…
Understanding decreases in land relative humidity with global warming: conceptual model and GCM simulations
Michael P. Byrne, Paul A. O'Gorman
Climate models simulate a strong land-ocean contrast in the response of near-surface relative humidity to global warming: relative humidity tends to increase slightly over oceans b…
Precipitation extremes under climate change
Paul A. O'Gorman
The response of precipitation extremes to climate change is considered using results from theory, modeling, and observations, with a focus on the physical factors that control the…
Water vapor and the dynamics of climate changes
Tapio Schneider, Paul A. O'Gorman, Xavier Levine
Water vapor is not only Earth's dominant greenhouse gas. Through the release of latent heat when it condenses, it also plays an active role in dynamic processes that shape the glob…