CoChat

Neural general circulation models for weather and climate

Open access

The DOI matches its Crossref record; 54 of the 54 references it cites were found in a registry or an index; 13 of the 26 sources its claims cite were checked for support.

Abstract

General circulation models (GCMs) are the foundation of weather and climate prediction. GCMs are physics-based simulators that combine a numerical solver for large-scale dynamics with tuned representations for small-scale processes such as cloud formation. Recently, machine-learning models trained on reanalysis data have achieved comparable or better skill than GCMs for deterministic weather forecasting. However, these models have not demonstrated improved ensemble forecasts, or shown sufficient stability for long-term weather and climate simulations. Here we present a GCM that combines a differentiable solver for atmospheric dynamics with machine-learning components and show that it can generate forecasts of deterministic weather, ensemble weather and climate on par with the best machine-learning and physics-based methods. NeuralGCM is competitive with machine-learning models for one- to ten-day forecasts, and with the European Centre for Medium-Range Weather Forecasts ensemble prediction for one- to fifteen-day forecasts. With prescribed sea surface temperature, NeuralGCM can accurately track climate metrics for multiple decades, and climate forecasts with 140-kilometre resolution show emergent phenomena such as realistic frequency and trajectories of tropical cyclones. For both weather and climate, our approach offers orders of magnitude computational savings over conventional GCMs, although our model does not extrapolate to substantially different future climate…

Overview

CoChat Summary

## TL;DR

NeuralGCM is a fully differentiable hybrid general circulation model trained on ERA5 weather trajectories that combines a physical dynamical core with learned parameterizations. It achieves competitive performance for weather forecasting and multi-decade climate simulation, while the paper notes it does not extrapolate to substantially different future climates.

## Key findings

  • On medium-range weather forecasting, NeuralGCM-0.7° and GraphCast achieved the best RMSE for the first 1–3 days (depending on variable), while NeuralGCM models compared favorably on persistent bias, including notably lower specific-humidity bias in the tropics.
  • The stochastic NeuralGCM-ENS at 1.4° had lower error than ECMWF-ENS across almost all variables, lead times, and vertical levels for ensemble-mean RMSE, RMSB, and CRPS; its spread-skill ratio was approximately 1.
  • In climate simulations with prescribed SST, NeuralGCM captured seasonal climate metrics and long-term warming trends: the ensemble-mean global temperature RMSE was 0.16 K versus 0.45 K for climatology, and all 22 stable 40-year NeuralGCM-2.8° runs had smaller spatial bias than the 22 CMIP6 AMIP runs.
  • For tropical cyclones, NeuralGCM at 1.4° produced 83 cyclones versus 86 in ERA5 for the corresponding period, while X-SHiELD produced 40 after regridding to 1.4°.

## Methods

  • The model is a fully differentiable hybrid GCM with a JAX-implemented dynamical core solving the hydrostatic primitive equations with moisture on sigma coordinates, plus a learned physics module that operates on single atmospheric columns.
  • Weather evaluation used 732 forecasts from noon and midnight UTC in 2020 (held out from training for machine-learning models), regridded to 1.5°, with comparisons against ERA5 or ECMWF operational analysis depending on the baseline.
  • Deterministic models were trained with a combination of losses for accuracy, spectral matching, and bias; stochastic models used CRPS and injected Gaussian random fields, with two ensemble members per forecast for training.
  • Climate experiments used deterministic models at 2.8° and 1.4° with prescribed historical SST and sea ice, including 37 initial conditions for 2-year seasonal-cycle runs and 37 initial conditions for 40-year AMIP-like runs, of which 35 and 22 were stable, respectively.

## Limitations

  • The paper explicitly states that NeuralGCM does not extrapolate to substantially different future climates.
  • The authors note that for more substantial SST increases (+4 K), NeuralGCM’s response diverges from expectations, and that AMIP simulations with increased SST show climate drift.
  • The text makes evident that the current version cannot distinguish precipitation from evaporation because it directly predicts column tendencies; this is stated in the paper.

Model-written summary. Check it against the paper before relying on it.

Integrity signals

Registry

Crossref · 10.1038/s41586-024-07744-y

Cites

54 of 54 references verified0 citation errors · 0 not checkable

Statistics

Nothing to recompute.

Figures

Fig. 1 Structure of the NeuralGCM model. a, Overall model structure, showing how forcings Ft, noise zt (for stochastic models) and inputs yt are encoded into the model state xt. The model state is fed into the dynamical core, and alongside forcings and noise into the learned physics module. This produces tendencies (rates of change) used by an implicit–explicit ordinary differential equation (ODE) solver to advance the state in time. The new model state xt+1 can then be fed back into another time step, or decoded into model predictions. b, The learned physics module, which feeds data for individual columns of the atmosphere into a neural network used to produce physics tendencies in that vertical column.
Fig. 1 Structure of the NeuralGCM model. a, Overall model structure, showing how forcings Ft, noise zt (for stochastic models) and inputs yt are encoded into the model state xt. The model state is fed into the dynamical core, and alongside forcings and noise into the learned physics module. This produces tendencies (rates of change) used by an implicit–explicit ordinary differential equation (ODE) solver to advance the state in time. The new model state xt+1 can then be fed back into another time step, or decoded into model predictions. b, The learned physics module, which feeds data for individual columns of the atmosphere into a neural network used to produce physics tendencies in that vertical column.CC BY · PubMed Central
Fig. 2 Weather forecasting accuracy scores for deterministic and stochastic models. a,c, RMSE (a) and RMSB (c) for ECMWF-ENS, ECMWF-HRES, NeuralGCM-0.7°, NeuralGCM-ENS, GraphCast3 and Pangu4 on headline WeatherBench2 variables, as a percentage of the error of ECMWF-ENS. Deterministic and stochastic models are shown in solid and dashed lines respectively. e,g, CRPS relative to ECMWF-ENS (e) and spread-skill ratio for the ENS and NeuralGCM-ENS models (g). b,d,f,h, Spatial distributions of RMSE (b), bias (d), CRPS (f) and spread-skill ratio (h) for NeuralGCM-ENS and ECMWF-ENS models for 10-day forecasts of specific humidity at 700 hPa. Spatial plots of RMSE and CRPS show skill relative to a probabilistic climatology12 with an ensemble member for each of the years 1990–2019. The grey areas indicate regions where climatological surface pressure on average is below 700 hPa.
Fig. 2 Weather forecasting accuracy scores for deterministic and stochastic models. a,c, RMSE (a) and RMSB (c) for ECMWF-ENS, ECMWF-HRES, NeuralGCM-0.7°, NeuralGCM-ENS, GraphCast3 and Pangu4 on headline WeatherBench2 variables, as a percentage of the error of ECMWF-ENS. Deterministic and stochastic models are shown in solid and dashed lines respectively. e,g, CRPS relative to ECMWF-ENS (e) and spread-skill ratio for the ENS and NeuralGCM-ENS models (g). b,d,f,h, Spatial distributions of RMSE (b), bias (d), CRPS (f) and spread-skill ratio (h) for NeuralGCM-ENS and ECMWF-ENS models for 10-day forecasts of specific humidity at 700 hPa. Spatial plots of RMSE and CRPS show skill relative to a probabilistic climatology12 with an ensemble member for each of the years 1990–2019. The grey areas indicate regions where climatological surface pressure on average is below 700 hPa.CC BY · PubMed Central
Fig. 3 Case study of a medium-range weather forecast. All forecasts are initialized at 2020-08-22T12z, chosen to highlight Hurricane Laura, the most damaging Atlantic hurricane of 2020. a, Specific humidity at 700 hPa for 1-day, 5-day and 10-day forecasts over North America and the Northeast Pacific Ocean from ERA514, ECMWF-HRES, NeuralGCM-0.7°, ECMWF-ENS (mean), NeuralGCM-ENS (mean), GraphCast3 and Pangu4. b, Forecasts from individual ensemble members from ECMWF-ENS and NeuralGCM-ENS over regions of interest, including predicted tracks of Hurricane Laura from each of the 50 ensemble members (Supplementary Information section I.2). The track from ERA5 is plotted in black.
Fig. 3 Case study of a medium-range weather forecast. All forecasts are initialized at 2020-08-22T12z, chosen to highlight Hurricane Laura, the most damaging Atlantic hurricane of 2020. a, Specific humidity at 700 hPa for 1-day, 5-day and 10-day forecasts over North America and the Northeast Pacific Ocean from ERA514, ECMWF-HRES, NeuralGCM-0.7°, ECMWF-ENS (mean), NeuralGCM-ENS (mean), GraphCast3 and Pangu4. b, Forecasts from individual ensemble members from ECMWF-ENS and NeuralGCM-ENS over regions of interest, including predicted tracks of Hurricane Laura from each of the 50 ensemble members (Supplementary Information section I.2). The track from ERA5 is plotted in black.CC BY · PubMed Central
Fig. 4 Simulation of climate with NeuralGCM. a, Global mean temperature for ERA514 (orange), 1990–2019 climatology (black) and NeuralGCM-1.4° (blue) for 2020 using 35 simulations initialized every 10 days during 2019 (thick line, ensemble mean; thin lines, different initial conditions). b, Yearly global mean temperature for ERA5 (orange), mean over 22 CMIP6 AMIP experiments34 (violet; model details are in Supplementary Information section I.3) and NeuralGCM-2.8° for 22 AMIP-like simulations with prescribed SST initialized every 10 days during 1980 (thick line, ensemble mean; thin lines, different initial conditions). c, The RMSB of the 850-hPa temperature averaged between 1981 and 2014 for 22 NeuralGCM-2.8° AMIP runs (labelled NGCM), 22 CMIP6 AMIP experiments (labelled AMIP) and debiased 22 CMIP6 AMIP experiments (labelled AMIP*; bias was removed by removing the 850-hPa global temperature bias). In the box plots, the red line represents the median. The box delineates the first to third quartiles; the whiskers extend to 1.5 times the interquartile range (Q1 − 1.5IQR and Q3 + 1.5IQR), and outliers are shown as individual dots. d, Vertical profiles of tropical (20° S–20° N) temperature trends for 1981–2014. Orange, ERA5; black dots, Radiosonde Observation Correction using Reanalyses (RAOBCORE)41; blue dots, mean trends for NeuralGCM; purple dots, mean trends from CMIP6 AMIP runs (grey and black whiskers, 25th and 75th percentiles for NeuralGCM and CMIP6 AMIP runs, respectively). e–g, Tropical cyclone tracks for ERA5 (e), NeuralGCM-1.4° (f) and X-SHiELD31 (g). h–k, Mean precipitable water for ERA5 (h) and the precipitable water bias in NeuralGCM-1.4° (i), initialized 90 days before mid-January 2020 similarly to X-SHiELD, X-SHiELD (j) and climatology (k; averaged between 1990 and 2019). In d–i, quantities are calculated between mid-January 2020 and mid-January 2021 and all models were regridded to a 256 × 128 Gaussian grid before computation and tracking.
Fig. 4 Simulation of climate with NeuralGCM. a, Global mean temperature for ERA514 (orange), 1990–2019 climatology (black) and NeuralGCM-1.4° (blue) for 2020 using 35 simulations initialized every 10 days during 2019 (thick line, ensemble mean; thin lines, different initial conditions). b, Yearly global mean temperature for ERA5 (orange), mean over 22 CMIP6 AMIP experiments34 (violet; model details are in Supplementary Information section I.3) and NeuralGCM-2.8° for 22 AMIP-like simulations with prescribed SST initialized every 10 days during 1980 (thick line, ensemble mean; thin lines, different initial conditions). c, The RMSB of the 850-hPa temperature averaged between 1981 and 2014 for 22 NeuralGCM-2.8° AMIP runs (labelled NGCM), 22 CMIP6 AMIP experiments (labelled AMIP) and debiased 22 CMIP6 AMIP experiments (labelled AMIP*; bias was removed by removing the 850-hPa global temperature bias). In the box plots, the red line represents the median. The box delineates the first to third quartiles; the whiskers extend to 1.5 times the interquartile range (Q1 − 1.5IQR and Q3 + 1.5IQR), and outliers are shown as individual dots. d, Vertical profiles of tropical (20° S–20° N) temperature trends for 1981–2014. Orange, ERA5; black dots, Radiosonde Observation Correction using Reanalyses (RAOBCORE)41; blue dots, mean trends for NeuralGCM; purple dots, mean trends from CMIP6 AMIP runs (grey and black whiskers, 25th and 75th percentiles for NeuralGCM and CMIP6 AMIP runs, respectively). e–g, Tropical cyclone tracks for ERA5 (e), NeuralGCM-1.4° (f) and X-SHiELD31 (g). h–k, Mean precipitable water for ERA5 (h) and the precipitable water bias in NeuralGCM-1.4° (i), initialized 90 days before mid-January 2020 similarly to X-SHiELD, X-SHiELD (j) and climatology (k; averaged between 1990 and 2019). In d–i, quantities are calculated between mid-January 2020 and mid-January 2021 and all models were regridded to a 256 × 128 Gaussian grid before computation and tracking.CC BY · PubMed Central
Extended Data Fig. 1 Maps of bias for NeuralGCM-ENS and ECMWF-ENS forecasts. Bias is averaged over all forecasts initialized in 2020.
Extended Data Fig. 1 Maps of bias for NeuralGCM-ENS and ECMWF-ENS forecasts. Bias is averaged over all forecasts initialized in 2020.CC BY · PubMed Central
Extended Data Fig. 2 Maps of spread-skill ratio for NeuralGCM-ENS and ECMWF-ENS forecasts. Spread-skill ratio is averaged over all forecasts initialized in 2020.
Extended Data Fig. 2 Maps of spread-skill ratio for NeuralGCM-ENS and ECMWF-ENS forecasts. Spread-skill ratio is averaged over all forecasts initialized in 2020.CC BY · PubMed Central
Extended Data Fig. 3 Geostrophic balance in NeuralGCM, GraphCast3 and ECMWF-HRES. Vertical profiles of the extratropical intensity (averaged between latitude 30°–70° in both hemispheres) and over all forecasts initialized in 2020 of (a,d,g) geostrophic wind, (b,e,h) ageostrophic wind and (c,f,i) the ratio of the intensity of ageostrophic wind over geostrophic wind for ERA5 (black continuous line in all panels), (a,b,c) NeuralGCM-0.7°, (d,e,f) GraphCast and (g,h,i) ECMWF-HRES at lead times of 1 day, 5 days and 10 days.
Extended Data Fig. 3 Geostrophic balance in NeuralGCM, GraphCast3 and ECMWF-HRES. Vertical profiles of the extratropical intensity (averaged between latitude 30°–70° in both hemispheres) and over all forecasts initialized in 2020 of (a,d,g) geostrophic wind, (b,e,h) ageostrophic wind and (c,f,i) the ratio of the intensity of ageostrophic wind over geostrophic wind for ERA5 (black continuous line in all panels), (a,b,c) NeuralGCM-0.7°, (d,e,f) GraphCast and (g,h,i) ECMWF-HRES at lead times of 1 day, 5 days and 10 days.CC BY · PubMed Central
Extended Data Fig. 4 Precipitation minus evaporation calculated from the third day of weather forecasts. (a) Tropical (latitudes −20° to 20°) precipitation minus evaporation (P minus E) rate distribution, (b) Extratropical (latitudes 30° to 70° in both hemispheres) P minus E, (c) mean P minus E for 2020 ERA514 and (d) NeuralGCM-0.7° (calculated from the third day of forecasts and averaged over all forecasts initialized in 2020), (e) the bias between NeuralGCM-0.7° and ERA5, (f-g) Snapshot of daily precipitation minus evaporation for 2020-01-04 for (f) NeuralGCM-0.7° (forecast initialized on 2020-01-02) and (g) ERA5.
Extended Data Fig. 4 Precipitation minus evaporation calculated from the third day of weather forecasts. (a) Tropical (latitudes −20° to 20°) precipitation minus evaporation (P minus E) rate distribution, (b) Extratropical (latitudes 30° to 70° in both hemispheres) P minus E, (c) mean P minus E for 2020 ERA514 and (d) NeuralGCM-0.7° (calculated from the third day of forecasts and averaged over all forecasts initialized in 2020), (e) the bias between NeuralGCM-0.7° and ERA5, (f-g) Snapshot of daily precipitation minus evaporation for 2020-01-04 for (f) NeuralGCM-0.7° (forecast initialized on 2020-01-02) and (g) ERA5.CC BY · PubMed Central
Extended Data Fig. 5 Indirect comparison between precipitation bias in X-SHiELD and precipitation minus evaporation bias in NeuralGCM-1.4°. Mean precipitation calculated between 2020-01-19 and 2021-01-17 for (a) ERA514 (c) X-SHiELD31 and the biases in (e) X-SHiELD and (g) climatology (ERA5 data averaged over 1990-2019). Mean precipitation minus evaporation calculated between 2020-01-19 and 2021-01-17 for (b) ERA5 (d) NeuralGCM-1.4° (initialized in October 18th 2019) and the biases in (f) NeuralGCM-1.4° and (h) climatology (data averaged over 1990–2019).
Extended Data Fig. 5 Indirect comparison between precipitation bias in X-SHiELD and precipitation minus evaporation bias in NeuralGCM-1.4°. Mean precipitation calculated between 2020-01-19 and 2021-01-17 for (a) ERA514 (c) X-SHiELD31 and the biases in (e) X-SHiELD and (g) climatology (ERA5 data averaged over 1990-2019). Mean precipitation minus evaporation calculated between 2020-01-19 and 2021-01-17 for (b) ERA5 (d) NeuralGCM-1.4° (initialized in October 18th 2019) and the biases in (f) NeuralGCM-1.4° and (h) climatology (data averaged over 1990–2019).CC BY · PubMed Central
Extended Data Fig. 6 Yearly temperature bias for NeuralGCM and X-SHiELD31. Mean temperature between 2020-01-19 to 2020-01-17 for (a) ERA5 at 200hPa and (b) 850hPa. (c,d) the bias in the temperature for NeuralGCM-1.4°, (e,f) the bias in X-SHiELD and (g,h) the bias in climatology (calculated from 1990–2019). NeuralGCM-1.4° was initialized in 18th of October (similar to X-SHiELD).
Extended Data Fig. 6 Yearly temperature bias for NeuralGCM and X-SHiELD31. Mean temperature between 2020-01-19 to 2020-01-17 for (a) ERA5 at 200hPa and (b) 850hPa. (c,d) the bias in the temperature for NeuralGCM-1.4°, (e,f) the bias in X-SHiELD and (g,h) the bias in climatology (calculated from 1990–2019). NeuralGCM-1.4° was initialized in 18th of October (similar to X-SHiELD).CC BY · PubMed Central
Extended Data Fig. 7 Tropical Cyclone densities and annual regional counts. (a) Tropical Cyclone (TC) density from ERA514 data spanning 1987–2020. (b) TC density from NeuralGCM-1.4° for 2020, generated using 34 different initial conditions all initialized in 2019. (c) Box plot depicting the annual number of TCs across different regions, based on ERA5 data (1987–2020), NeuralGCM-1.4° for 2020 (34 initial conditions), and orange markers show ERA5 for 2020. In the box plots, the red line represents the median; the box delineates the first to third quartiles; the whiskers extend to 1.5 times the interquartile range (Q1 − 1.5IQR and Q3 + 1.5IQR), and outliers are shown as individual dots. Each year is defined from January 19th to January 17th of the following year, aligning with data availability from X-SHiELD. For NeuralGCM simulations, the 3 initial conditions starting in January 2019 exclude data for January 17th, 2021, as these runs spanned only two years.
Extended Data Fig. 7 Tropical Cyclone densities and annual regional counts. (a) Tropical Cyclone (TC) density from ERA514 data spanning 1987–2020. (b) TC density from NeuralGCM-1.4° for 2020, generated using 34 different initial conditions all initialized in 2019. (c) Box plot depicting the annual number of TCs across different regions, based on ERA5 data (1987–2020), NeuralGCM-1.4° for 2020 (34 initial conditions), and orange markers show ERA5 for 2020. In the box plots, the red line represents the median; the box delineates the first to third quartiles; the whiskers extend to 1.5 times the interquartile range (Q1 − 1.5IQR and Q3 + 1.5IQR), and outliers are shown as individual dots. Each year is defined from January 19th to January 17th of the following year, aligning with data availability from X-SHiELD. For NeuralGCM simulations, the 3 initial conditions starting in January 2019 exclude data for January 17th, 2021, as these runs spanned only two years.CC BY · PubMed Central
Extended Data Fig. 8 Tropical Cyclone maximum wind distribution in NeuralGCM vs. ERA514. Number of Tropical Cyclones (TCs) as a function of maximum wind speed at 850hPa across different regions, based on ERA5 data (1987–2020; in orange), and NeuralGCM-1.4° for 2020 (34 initial conditions; in blue). Each year is defined from January 19th to January 17th of the following year, aligning with data availability from X-SHiELD. For NeuralGCM simulations, the 3 initial conditions starting in January 2019 exclude data for January 17th, 2021, as these runs spanned only two years.
Extended Data Fig. 8 Tropical Cyclone maximum wind distribution in NeuralGCM vs. ERA514. Number of Tropical Cyclones (TCs) as a function of maximum wind speed at 850hPa across different regions, based on ERA5 data (1987–2020; in orange), and NeuralGCM-1.4° for 2020 (34 initial conditions; in blue). Each year is defined from January 19th to January 17th of the following year, aligning with data availability from X-SHiELD. For NeuralGCM simulations, the 3 initial conditions starting in January 2019 exclude data for January 17th, 2021, as these runs spanned only two years.CC BY · PubMed Central

Verification

Claims the paper makes

6 Valid · 1 Not valid · 10 Not checked · 53 Own results and interpretations

29 more claims

Create a free account to see all 70 claims and to verify the 9 references still open.

See all claims — free account
  • It may state two separate claims as one. 31
  • Probably not a substantial claim. 6

Create a free account to see these claims.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

Citations

Cites

Show all 54 references

Research works printed but not linked: 2

  1. Holton, J. R. An introduction to Dynamic Meteorology 5th edn (Elsevier, 2004).
  2. Sutskever, I., Vinyals, O. & Le, Q. V. Sequence to sequence learning with neural networks. Adv. Neural Inf. Process. Syst. 27, 3104–3112 (2014).

Cited by

See all 454

Metadata

Authors
Kochkov, D., Yuval, J., Langmore, I., Norgaard, P., Smith, J., Mooers, G., Klöwer, M., Lottes, J., Rasp, S., Düben, P., Hatfield, S., Battaglia, P., Sanchez-Gonzalez, A., Willson, M., Brenner, M. P., & Hoyer, S.
Affiliations
  • Google (United States) (US)
  • Massachusetts Institute of Technology (US)
  • European Centre for Medium-Range Weather Forecasts (GB)
  • Google DeepMind (United Kingdom) (GB)
Corresponding author
Kochkov, Dmitrii
Venue
Nature
Published
2024-07-22
Volume
632
Issue
8027
Pages
1060-1066
ISSN
  • 0028-0836 (ISSN-L)
  • 1476-4687
OpenAlex
W4400880443
Cited by
454
References
54
Citations by year
2026: 188 · 2025: 209 · 2024: 57
FWCI
82.79
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • arXiv (Cornell University)
Topics
  • Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations
  • Physical Sciences › Environmental Science › Global and Planetary Change › Climate variability and models
  • Physical Sciences › Physics and Astronomy › Statistical and Nonlinear Physics › Model Reduction and Neural Networks
Keywords
weather forecasting, climate prediction, ensemble forecasting, tropical cyclones, long-term climate simulation, computational efficiency

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

The claim verdicts this report counts are experimental: their accuracy is not yet measured.

A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).

A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).

Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Neural general circulation models for weather and climate. https://app.cochat.ai/papers/10.1038/s41586-024-07744-y
The paper
Kochkov, D., Yuval, J., Langmore, I., Norgaard, P., Smith, J., Mooers, G., Klöwer, M., Lottes, J., Rasp, S., Düben, P., Hatfield, S., Battaglia, P., Sanchez-Gonzalez, A., Willson, M., Brenner, M. P., & Hoyer, S. (2024). Neural general circulation models for weather and climate. Nature. https://doi.org/10.1038/s41586-024-07744-y

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.