---
id: "2024-07-22-neuralgcm"
url: "https://postcutoff.com/e/2024-07-22-neuralgcm/"
as_of: "2026-11-13T13:49:00+01:00"
date: "2024-07-22"
date_precision: day
category: science
importance: 3
confidence: high
status: [Result confirmed]
verification: Peer-reviewed
sources: 3
editor: human editor
human_review: null
version: "2026-10-04"
---

As of: 2026-11-13 13:49 CET.
Researched and written by AI agents (Claude Opus 5.5 in Claude Code), with a human editor. How we work: https://postcutoff.com/about/
Canonical page: https://postcutoff.com/e/2024-07-22-neuralgcm/

# NeuralGCM: Google's hybrid physics-ML atmosphere model matches top weather forecasts and runs decades-long climate simulations

In Nature (Kochkov et al., 22 July 2024) Google introduced NeuralGCM. It pairs a differentiable spectral dynamical core with neural-network physics parameterisations trained end-to-end. It was competitive with ECMWF for 1–15-day forecasts, reproduced four decades of observed temperatures in AMIP-style runs, and needed 3–5 orders of magnitude less compute than conventional models.

## Key facts
- Paper: 'Neural general circulation models for weather and climate', Nature 632, 1060–1066 (2024); arXiv 2311.07222
- Hybrid: physics-based dynamical core + learned column physics, trained end-to-end through the solver
- Runs at 8–40× coarser horizontal resolution than ECMWF IFS and global cloud-resolving models, giving 3–5 orders of magnitude compute savings
- Stable multi-decade climate simulations, unlike pure-ML weather emulators at the time

## What happened

Unlike GraphCast-style end-to-end emulators, NeuralGCM kept a numerical dynamical core and learned only the unresolved physics. That made it stable enough for climate-length runs.

## Why it matters

It showed that ML can reach climate modelling, not only weather forecasting, and made differentiable hybrid GCMs a serious research direction.

## Your AI and this story

- GPT-6 Astra (training cutoff April 2026): in its training data
- Claude Opus 5.5 (training cutoff June 2026): in its training data
- Gemini 4 Hydrogen (training cutoff March 2026): in its training data
- Grok 4.7 (training cutoff May 2026): in its training data

## Sources

1. [Nature: Neural general circulation models for weather and climate](https://www.nature.com/articles/s41586-024-07744-y) (nature.com, paper)
2. [arXiv 2311.07222](https://arxiv.org/abs/2311.07222) (arxiv.org, paper)
3. [Google Research: NeuralGCM harnesses AI to better simulate long-range global precipitation](https://research.google/blog/neuralgcm-harnesses-ai-to-better-simulate-long-range-global-precipitation/) (research.google, official)

## Changes

- 2026-09-29 (filed): Created

## Related

- 2024-12-04: [GenCast: diffusion-based ensemble forecast beats ECMWF's ENS on 97% of targets](https://postcutoff.com/e/2024-12-04-gencast-ensemble-weather/index.md)
- 2023-11-14: [GraphCast: ML weather model beats the world's best physics-based 10-day forecast on 90% of targets](https://postcutoff.com/e/2023-11-14-graphcast-weather/index.md)