Earth system models underpin the evidence that informs net-zero policy, yet their energy demands are rarely considered when judging model quality. Using archived output from 159 models spanning five generations of the Coupled Model Intercomparison Project (CMIP), we show that model error has fallen at a constant rate of 13.5 per cent per doubling of compute since 1995. Halving CMIP6 error would require 28 times more compute. Improvements are uneven, with sea-level pressure and surface air temperature errors declining 3.5-fold and 2.7-fold since CMIP1, but precipitation error by only 7 per cent. Machine-learning weather models match or exceed operational forecast skill at a fraction of the runtime, but none publishes measured energy, and including training changes how they rank. We propose a skill-energy framework that combines an empirical Pareto front with a ranking score. These findings argue for standardised reporting of energy use and performance ahead of CMIP8.
AI foundation models pretrained on weather and climate data are increasingly fine-tuned to Earth science tasks well beyond weather forecasting. Their development and adoption are outpacing the scientific community's ability to evaluate them. These models are judged almost entirely by benchmark skill metrics, which meas...
Makoto M. Kelp, Amirhossein Arzani, P. Castellanos et al.· 1 citation
Outputs from complex Earth system models (ESMs) participating in the Coupled Model Intercomparison Project (CMIP) are a major source of information for policy-relevant assessments of climate change. The way we view and interpret the CMIP archive shapes our understanding of the real world, yet many assessments present a...
K. Marvel, Chris D. Jones, V. Cooper et al.· Frontiers in Climate· 0 citations
Repeated satellite imagery permits understanding of how our planet changes over time, letting us predict its future and plan mitigating actions. Most existing studies that rely on a time series of satellite observations forecast the spectral values at each pixel for a future target date. However, clouds, shadows, and s...
Jing-Tao Li, S. Jaffer, Anil Madhavapeddy et al.· 0 citations
Regional climate models (RCMs) have become established as essential dynamical downscaling tools, providing physically consistent, high-resolution climate information where global climate models (GCMs) are unable to resolve. Added value is obtained over heterogeneous vegetation, coastal, urban or orographically complex...
Enrique Sánchez, M. Gaertner, C. Gallardo et al.· Géosciences· 0 citations
Earth system models underpin climate projections, but their cost limits how many scenarios, ensemble members and impact pathways can be explored. Machine-learning weather models forecast as skillfully as physics-based models at a fraction of the cost, yet coupled to an ocean they have produced weak El Nino variability...
We present ClimateBench v2, a standardized protocol for evaluating climate models on diagnostics expected to be informative for their skill in projecting mid-century regional temperature and precipitation changes. The protocol is designed to evaluate any physics-based, data-driven, or hybrid climate model on equal foot...
Duncan Watson-Parris, W. Tobin, Aytaç Paçal et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.