In the race to understand our planet's changing climate, speed and accuracy are everything. But today's most widely used climate simulators often struggle: They can't fully capture critical small-scale processes, like thunderstorms or towering tropical clouds, because of computational limits. To capture these features, scientists run ultra-high-resolution simulations called cloud-resolving models (CRMs). These simulations track how clouds form and evolve-but they're so expensive, running one for a decade of global climate forecasts is practically impossible.
What if we could distill the wisdom of these detailed simulations into a machine learning model that runs tens to hundreds of times faster, without giving up fidelity?
That's the promise of ClimSim-Online, a reproducible framework for developing and deploying hybrid physics-machine learning climate models at scale. This framework was produced by NVIDIA Earth 2 and a consortium of international climate modelers from across government and academia. And it was initiated and supported by a Columbia University-based, National Science Foundation-funded science and technology center that is exploring the future of AI-powered climate simulation technology.
From terabytes to turnkey: training AI to emulate complex nested climate physics ClimSim-Online builds on the award-winning ClimSim dataset, introduced at NeurIPS 2023. The dataset is served on the ClimSim Hugging Face repository. This dataset was created using the Energy Exascale Earth System Model-Multiscale Modeling Framework (E3SM-MMF)-a next-generation climate simulator that embeds thousands of localized, computationally-intensive CRMs within each atmospheric column of a host coarse-grid climate model. It's an experimental way to generate climate predictions that reduces the number of assumptions that must typically be made about fine-scale physics-but it comes at such computational cost that it is not used in mainstream international projections. Outsourcing the nested physics to AI could change that.
The host climate model operates at a horizontal resolution of approximately 1.5 degrees (about 150km) or coarser, while each embedded CRM runs at 2km resolution, explicitly simulating clouds and convection at much finer scales.
Over a simulated 10-year span, E3SM-MMF produced a staggering 5.7 billion samples, each describing how small-scale physical processes alter the large-scale atmospheric state. These processes include how turbulent updrafts lead to cloud formation, what causes microphysical droplets to form, how convection organizes from scales of individual clouds to large organized cloud complexes, and how these cloud systems interact with solar and infrared radiation, thereby regulating climate.
This massive dataset serves as the foundation for training ML models that emulate subgrid physics and can replace the expensive embedded CRM that consumes approximately 95% of the total computational expenses. It has already spurred a global Kaggle competition that attracted over 460 teams from around the world to develop and benchmark ML solutions on this high-fidelity climate dataset-helping accelerate progress through open, collaborative innovation.
data-src=https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-jpg.webp alt=A schematic diagram of the ClimSim dataset. The diagram shows the input variables on the left, which consist of a set of macro-scale state variables. On the right, the diagram displays the target variables, which primarily include the tendencies of those state variables due to unresolved processes. class=lazyload wp-image-103090 data-srcset=https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-jpg.webp 1999w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-300x227-jpg.webp 300w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-625x473-jpg.webp 625w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-152x115-jpg.webp 152w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-768x581-jpg.webp 768w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-1536x1163-jpg.webp 1536w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-645x488-jpg.webp 645w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-396x300-jpg.webp 396w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-119x90-jpg.webp 119w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-362x274-jpg.webp 362w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-145x110-jpg.webp 145w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-1024x775-jpg.webp 1024w, https://developer-blogs.nvidia.com/wp-content/uploads/2025/07/image4-713x540-jpg.webp 713w data-sizes=(max-width: 1999px) 100vw, 1999px />Figure 1. A schematic of the ClimSim dataset and the underlying machine-learning problem. Inputs consist of a set of macro-scale state variables; targets primarily include the tendencies of those state variables due to unresolved processes.
The challenge? These models need to be more than just accurate offline. They must remain stable when integrated into a live climate simulator-running hour after hour, year after year-without letting the virtual atmosphere drift into unrealistic states. Controlling the behavior of hybrid physics-ML simulations is a marquee challenge, especially in situations where the host physics model cannot be made differentiable. Some simple host models can be rewritten in differentiable code, enabling ML optimization of hybrid dynamics directly. But many candidate host models are not easy to rewrite differentiably, or are so nonlinear that direct optimization on hybrid behavior is impractical. Fully featured climate simulators spanning
