Learning skillful medium-range global weather forecasting
Open accessThe DOI matches its Crossref record; 66 of the 66 references it cites were found in a registry or an index; 12 of the 38 sources its claims cite were checked for support.
Abstract
Global medium-range weather forecasting is critical to decision-making across many social and economic domains. Traditional numerical weather prediction uses increased compute resources to improve forecast accuracy but does not directly use historical weather data to improve the underlying model. Here, we introduce GraphCast, a machine learning–based method trained directly from reanalysis data. It predicts hundreds of weather variables for the next 10 days at 0.25° resolution globally in under 1 minute. GraphCast significantly outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets, and its forecasts support better severe event prediction, including tropical cyclone tracking, atmospheric rivers, and extreme temperatures. GraphCast is a key advance in accurate and efficient weather forecasting and helps realize the promise of machine learning for modeling complex dynamical systems.
Overview
CoChat Summary
TL;DR
GraphCast is a graph neural network trained directly on ERA5 reanalysis that produces 10-day global weather forecasts at 0.25° resolution in under one minute. It outperforms the operational HRES deterministic system on most evaluated targets and supports better prediction of tropical cyclones, atmospheric rivers, and extreme temperatures.
Key findings
- GraphCast significantly outperformed HRES on 90.3% of 1380 verification targets, and significantly on 89.9% of targets; excluding 50 hPa it significantly outperformed HRES on 96.9% of 1280 targets, and excluding 50 and 100 hPa on 99.7% of 1180 targets.
- On z500, GraphCast had better skill across all lead times, with skill score improvement around 7%–14%; it also outperformed Pangu-Weather on 99.2% of the 252 targets Pangu-Weather presented.
- For severe events, GraphCast had lower median cyclone track error and was significantly better than HRES for lead times 18 hours to 4.75 days; it improved atmospheric river ivt prediction from 25% at short lead time to 10% at longer horizons; extreme heat precision-recall curves were above HRES at 5- and 10-day lead times, while HRES was better at 12 hours.
- Training on more recent data improved GraphCast’s skill scores, with variants trained up to before 2021 generally outperforming earlier-trained variants on 2021 test data.
Methods
- GraphCast is a 36.7-million-parameter graph neural network in an encode-process-decode configuration, using a multi-mesh icosahedral representation with 40,962 nodes and 327,660 mesh edges; it takes two most recent weather states and predicts the next 6-hour state autoregressively.
- It was trained on 39 years (1979–2017) of ERA5 reanalysis, using a weighted MSE objective over 12 autoregressive steps, with training taking roughly four weeks on 32 Cloud TPU v4 devices; evaluation used held-out 2018 data, with some analyses on 2018–2021 and 2021.
- Forecast skill was evaluated against HRES using RMSE and ACC, with HRES-fc0 as HRES ground truth and ERA5 as GraphCast ground truth; comparisons used 06z/18z initializations and 12-hour target intervals to match data assimilation lookahead.
Limitations
- The paper states that GraphCast is deterministic and does not explicitly model uncertainty like ECMWF’s ensemble system ENS; its MSE training objective encourages spatial blurring, which may limit value for some applications.
- The paper states GraphCast operates at 0.25° resolution, 37 vertical levels, and 6-hour time steps, versus HRES at 0.1°, 137 levels, and up to 1-hour time steps, and that it depends critically on large quantities of high-quality data assimilated via NWP, so it should not be regarded as a replacement for traditional weather forecasting.
- The paper reports reduced skill in the stratosphere, especially at 50 hPa, and at high surface elevations; it also notes possible ERA5 versus HRES-fc0 domain differences and spurious spectral artifacts around 100 km wavelengths.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures



























Verification
Claims the paper makes
9 Valid · 0 Not valid · 18 Not checked · 150 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Generally, verifying a model against its own analysis gives the best skill estimates [45].”
§ 5. Verification methods > 5.2. Comparing GraphCast to HRES
What the sources say
- Partly supportedcites [45] [45] Richard Swinbank, Masayuki Kyouda, Piers Buchanan, Lizzie Froude, Thomas M Hamill, Tim D Hewson, Julia H Keller, Mio Matsueda, John Methven, Florian Pappenberger, et al. The TIGGE project and its achievements. Bulletin of the American Meteorological Society, 97(1):49–67, 2016. sourceExperimental — accuracy not yet measured
The Verification section reports an example in low-level tropical regions where the model verified against its own analysis appeared most accurate. It does not establish this as a general rule; instead, it warns that skill rankings depend strongly on the analysis used and recommends verifying against more than one analysis. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“For the HRES baseline, we used the TIGGE archive, which provides cyclone tracks estimated with the operational tracker, from HRES's forecasts at 0.1° resolution [8, 46].”
§ 1. Datasets > 1.3. Tropical cyclone datasets
What the sources say
- Partly supportedcites [8] [8] Philippe Bougeault, Zoltan Toth, Craig Bishop, Barbara Brown, David Burridge, De Hui Chen, Beth Ebert, Manuel Fuentes, Thomas M Hamill, Ken Mylne, et al. The THORPEX interactive grand global ensemble. Bulletin of the American Meteorological Society, 91(8):1059–1072, 2010. sourceExperimental — accuracy not yet measured
The Applications of TIGGE section says TIGGE providers supplied tropical cyclone tracks and that the archive centers would distribute them. It does not establish that those tracks came from HRES forecasts at 0.1° resolution or were estimated with the operational tracker; the examples instead describe ECMWF and UKMO ensemble tracks. (LLM, conf=0.85)
- Partly supportedcites [46] [46] Richard Swinbank, Masayuki Kyouda, Piers Buchanan, Lizzie Froude, Thomas M. Hamill, Tim D. Hewson, Julia H. Keller, Mio Matsueda, John Methven, Florian Pappenberger, Michael Scheuerer, Helen A. Titley, Laurence Wilson, and Munehiko Yamaguchi. The TIGGE project and its achievements. Bulletin of the American Meteorological Society, 97(1):49 – 67, 2016. sourceExperimental — accuracy not yet measured
The TIGGE Project and Its Achievements describes TIGGE as an archive of ensemble forecasts, and its Dynamics and Predictability section reports cyclone tracks derived from TIGGE data using a tracking method employed operationally by ECMWF. It does not establish that the archive provides tracks from HRES forecasts at 0.1° resolution; the tracking passage concerns global ensembles, not HRES. (LLM, conf=0.85)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“Because extreme prediction is by definition an imbalanced classification problem, we base our analysis on precision-recall plots which are well-suited for this case [42].”
§ 1 2 3 4 5 6 7 8 9 10 > 8.3. Extreme heat and cold
What the sources say
- Supportedcites [42] [42] Takaya Saito and Marc Rehmsmeier. The precision-recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets. PloS one, 10(3):e0118432, 2015. 101 https://confluence.ecmwf.int/display/FCST/202208+-+Heatwave+-+UK https://confluence.ecmwf.int/display/FCST/202208+-+Heatwave+-+UK https://www.ecmwf.int/node/17262 https://www.ecmwf.int/node/17262 GraphCast: Learning skillful medium-range global weather forecasting source
The Summary of the re-evaluation says precision-recall plots show classifiers’ susceptibility to imbalanced datasets with clear visual cues. This supports using them to evaluate an imbalanced classification problem; the citing authors’ characterization of extreme prediction is their own framing. (LLM, conf=0.93)
boostedstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“However, the HRES cyclone tracks in the TIGGE archive [8] are only initialized at 00z and 12z.”
§ 8. Additional severe event forecasting results > 8.1. Tropical cyclone track forecasting
What the sources say
- Partly supportedcites [8] [8] Philippe Bougeault, Zoltan Toth, Craig Bishop, Barbara Brown, David Burridge, De Hui Chen, Beth Ebert, Manuel Fuentes, Thomas M Hamill, Ken Mylne, et al. The THORPEX interactive grand global ensemble. Bulletin of the American Meteorological Society, 91(8):1059–1072, 2010. sourceExperimental — accuracy not yet measured
The Applications of TIGGE section says tropical cyclone tracks were to be distributed by TIGGE archive centers. Table 3 lists two daily forecast cycles for ECMWF’s ensemble, but the paper does not identify HRES cyclone tracks or state that their only initialization times are 00z and 12z. (LLM, conf=0.79)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
Every source the paper cites for this claim was checked and supports it.
In the paper
“we can derive this quantity from the predicted atmospheric variables specific humidity, q, and horizontal wind, (u, v), via the relation [38]:”
§ 1 2 3 4 5 > 8.2. Atmospheric rivers
What the sources say
- Supportedcites [38] [38] Paul J Neiman, F Martin Ralph, Gary A Wick, Jessica D Lundquist, and Michael D Dettinger. Meteorological characteristics and overland precipitation impacts of atmospheric rivers affecting the West Coast of North America based on eight years of ssm/i satellite observations. Journal of Hydrometeorology, 9(1):22–47, 2008. source
In section c, “The link between SSM/I IWV plumes and atmospheric rivers” (page not provided), the paper defines IVT as vertically integrated horizontal water-vapor flux calculated from q and the horizontal wind components. It describes summing the flux components through pressure layers, which supports the cited relation; the paper uses reanalysis variables rather than predictions. (LLM, conf=0.92)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Supported
65 more claims
Create a free account to see all 177 claims and to verify the 16 references still open.
- Probably not a substantial claim. 54
- It may state two separate claims as one. 70
- The quote only partly states this claim. 2
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?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Existing machine-learning models have focused on deterministic prediction, and surpass deterministic numerical weather prediction in terms of the aggregate metrics for which they are trained3,4.”
From Neural general circulation models for weather and climate (2024) · cites this paper as [3]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Most state-of-the-art machine learning models utilized in medium-range weather forecasting are built upon encoder-decoder84 architectures27–29,85.”
From A machine learning model that outperforms conventional global subseasonal forecast models (2024) · cites this paper as [27]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, these advances have focused primarily on single, deterministic forecasts that fail to represent uncertainty and estimate risk.”
From Probabilistic weather forecasting with machine learning (2025) · cites this paper as [2]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“They are typically trained to minimize the mean squared error (MSE) of their predictions and as a result tend to produce blurry forecasts, especially at longer lead times, rather than a specific realization of a possible weather state2.”
From Probabilistic weather forecasting with machine learning (2025) · cites this paper as [2]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Even so, these techniques are still fundamentally reliant on precise meteorological observations [1-3].”
From Advancing Data Quality Assurance with Machine Learning: A Case Study on Wind Vane Stalling Detection (2025) · cites this paper as [3]
10 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 7. Additional forecast verification results > 7.1. Detailed results for additional variables
“The ACC skill score is the normalized ACC difference between model 𝐴 and baseline 𝐵 as (ACC𝐴 − ACC𝐵)/(1 − RMSE𝐵).”
§ 1 2 3 4 > 5.3. Evaluation metrics
“and the normalized ACC difference as (ACC𝐴 − ACC𝐵)/(1 − ACC𝐵).”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 1 2 3 4 5 6 7
“The x-axis represents lead time, at 6-hour steps over 10 days.”
§ 6. Comparison with previous machine learning baselines
“Pangu-Weather[7] reports its 7-day forecast accuracy (RMSE and ACC) on: z500, t500, t850,”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ Conclusions
“because of the ERA5 training data's native 0.25° resolution”
§ 102 103 104
“the native resolution of ERA5 is 0.28125◦ corresponding to a shortest wavelength of 62km”
Citations
Cites
Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A. N., Kaiser, L., & Polosukhin, I. (2017) · arXiv · doi:10.48550/arxiv.1706.03762 · Cited by 120,404
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Exploiting Generative AI to Scale up Intelligent Tutoring Systems
Jakubův, J., Chvalovský, K., Goertzel, Z., Kaliszyk, C., Olšák, M., Piotrowski, B., Schulz, S., Suda, M., & Urban, J. (2023) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.itp.2023.19 · Cited by 76,658
Hersbach, H., Bell, B., Berrisford, P., Hirahara, S., Horányi, A., Muñoz‐Sabater, J., Nicolas, J., Peubey, C., Radu, R., Schepers, D., et al. (2020) · Quarterly Journal of the Royal Meteorological Society · doi:10.1002/qj.3803 · Cited by 31,882
Decoupled Weight Decay Regularization
Loshchilov, I., & Hutter, F. (2017) · arXiv · doi:10.48550/arxiv.1711.05101 · Cited by 12,522
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1710.10903 · Cited by 12,107
Saito, T., & Rehmsmeier, M. (2015) · PLOS ONE · doi:10.1371/journal.pone.0118432 · Cited by 5,309
SGDR: Stochastic Gradient Descent with Warm Restarts
Loshchilov, I., & Hutter, F. (2016) · arXiv · doi:10.48550/arxiv.1608.03983 · Cited by 5,309
Backpropagation through time: what it does and how to do it
Werbos, P. J. (1990) · Proceedings of the IEEE · doi:10.1109/5.58337 · Cited by 4,879
Knapp, K. R., Kruk, M. C., Levinson, D. H., Diamond, H. J., & Neumann, C. J. (2010) · Bulletin of the American Meteorological Society · doi:10.1175/2009bams2755.1 · Cited by 3,237
Research works printed but not linked: 3
- D. H. Levinson, H. J. Diamond, K. R. Knapp, M. C. Kruk, E. J. Gibney, Toward a homogenous global tropical cyclone best-track dataset. Bull. Am. Meteorol. Soc. 91, 377–380 (2010).
- ECMWF IFS Documentation CY45R1 – Part II: Data assimilation (European Centre for Medium-Range Weather Forecasts 2018); .10.21957/a3ri44ig4 · doi:10.21957/a3ri44ig4
- T. Haiden M. Janousek F. Vitart L. Ferranti F. Prates “Evaluation of ECMWF forecasts including the 2019 upgrade ” ECMWF Technical Memorandum No. 853 (European Centre for Medium-Range Weather Forecasts 2019); .10.21957/mlvapkke · DOI
Cited by
Items 901–1,000 of 2,424
Pan-spatial Earth information system: A new methodology for cognizing the earth system
Tao, L., Xu, Y., He, K., Ma, X., & Wang, L. (2024) · The Innovation · doi:10.1016/j.xinn.2024.100770 · Cited by 4
Deng, J., Zhang, J., Liu, H., Li, H., Chen, F., & Chen, J. (2025) · Atmospheric and Oceanic Science Letters · doi:10.1016/j.aosl.2025.100589 · Cited by 4
Fourier neural operators for spatiotemporal dynamics in two-dimensional turbulence
Atif, M., Dubey, P., Aghor, P. P., López, V., Zhang, T., Sharfuddin, A. A. M., Yu, K., Yang, F., Ladeinde, F., Liu, Y., et al. (2024) · International Conference for High Performance Computing, Networking, Storage and Analysis (SC) · doi:10.1109/scw63240.2024.00013 · Cited by 6
Chen, K., Chen, J., Xu, M., Wu, M., & Zhang, C. (2025) · Remote Sensing · doi:10.3390/rs17020206 · Cited by 4
Meddahi, A., Tuomiranta, A., & Guillon, S. (2025) · Solar RRL · doi:10.1002/solr.202400664 · Cited by 4
Deep Learning-based Bias Correction Method for Seasonal Prediction of Summer Rainfall in China
Qu, A., Bao, Q., Zhu, Τ., & Zhao-ming, L. U. O. (2024) · Journal of Tropical Meteorology · doi:10.3724/j.1006-8775.2024.040 · Cited by 4
Pahlavan, H. A., Hassanzadeh, P., & Alexander, M. J. (2025) · Geophysical Research Letters · doi:10.1029/2024gl114136 · Cited by 5
Digging deeper with deep learning? Explanatory understanding and deep neural networks
Beisbart, C. (2025) · European Journal for Philosophy of Science · doi:10.1007/s13194-025-00668-y · Cited by 4
Anand, V., Poole-Selters, L., Spognardi, A. G., Bekele, B. T., & de Perez, E. C. (2025) · The Geneva Papers on Risk and Insurance Issues and Practice · doi:10.1057/s41288-025-00355-2 · Cited by 4
Shukla, P., & Halem, M. (2025) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-24-0073.1 · Cited by 5
Artificial Intelligence for Scientific Discovery at High-Performance Computing Scales
Lee, K. L. K., & Kumar, N. (2023) · Computer · doi:10.1109/mc.2023.3241692 · Cited by 6
Stochastic Analysis and Modeling of Velocity Observations in Turbulent Flows
Rozos, E., Leandro, J., & Koutsoyiannis, D. (2024) · Journal of Environmental & Earth Sciences · doi:10.30564/jees.v6i1.6109 · Cited by 4
Elsberry, R. L., Tsai, H., Chin, W.-C., & Marchok, T. P. (2024) · Atmosphere · doi:10.3390/atmos15050610 · Cited by 4
The Compatibility between the Pangu Weather Forecasting Model and Meteorological Operational DataPreprint
Cheng, W., Yan, Y., Xia, J., Liu, Q., Qu, C., & Wang, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2308.04460 · Cited by 7
Learning to downscale satellite gravimetry data through artificial intelligence
Sun, A. Y. (2024) · Nature Water · doi:10.1038/s44221-024-00199-5 · Cited by 4
Advancing Data-driven Weather Forecasting: Time-Sliding Data Augmentation of ERA5Preprint
Cheon, M., Kang, D., Choi, Y.-H., & Kang, S.-Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.08185 · Cited by 5
Opinion: Why all emergent constraints are wrong but some are useful – a machine learning perspectivePreprint
Nowack, P. J., & Watson‐Parris, D. (2024) · doi:10.5194/egusphere-2024-1636 · Cited by 6
Ding, J., Chen, W., Chen, J., Wang, J., Zhang, Y., Weng, D., Liu, T., Mi, X., Soja, B. S., & Bai, L. (2024) · doi:10.22541/essoar.172081357.72805131/v1 · Cited by 4
Wang, L., Zhang, X., Leung, L.-Y. R., Chiew, F. H. S., AghaKouchak, A., Ying, K., & Zhang, Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2409.05369 · Cited by 5
EvoMesh: Adaptive Physical Simulation with Hierarchical Graph EvolutionsPreprint
Deng, H., Zhu, X., Wang, Y., & Yang, X. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.03779 · Cited by 5
Predicting time-varying flux and balance in metabolic systems using structured neural-ODE processesPreprint
Rathod, S., Lió, P., & Zhang, X. Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.14426 · Cited by 3
Leadsee-Precip: A Deep Learning Diagnostic Model for PrecipitationPreprint
Ji, W., Feng, J., Liu, Y., Qiu, Y., & Gao, H. Y. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2411.12640 · Cited by 4
MeshMask: Physics-Based Simulations with Masked Graph Neural NetworksPreprint
Garnier, P., Lannelongue, V., Viquerat, J., & Hachem, E. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.08738 · Cited by 15
Learning General Causal Structures with Hidden Dynamic Process for Climate AnalysisPreprint
Fu, M., Huang, B., Li, Z., Zheng, Y., Ng, I., Chen, G., Hu, Y., & Zhang, K. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.12500 · Cited by 6
BARNN: A Bayesian Autoregressive and Recurrent Neural NetworkPreprint
Coscia, D., Welling, M., Demo, N., & Rozza, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.18665 · Cited by 4
Niu, Z., Huang, W., Yang, Y., Yang, M., Deng, L., Wang, H., Li, H., & Zhang, X. (2025) · Advances in Atmospheric Sciences · doi:10.1007/s00376-025-5464-8 · Cited by 4
A Study on Messaging Trade-offs in Data Streaming for Scientific WorkflowsPreprint
George, A., Brim, M. J., Zimmer, C. J., Skluzacek, T. J., Ruckman, A. J., Jansen, G. R., & Oral, S. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.07199 · Cited by 4
Saqur, R., Bergmeir, C., Horvath, B. N., Schmidt, D., Rudzicz, F., & Lyons, T. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.15506 · Cited by 6
AIFS-COMPO: A Global Data-Driven Atmospheric Composition Forecasting SystemPreprint
Harder, P., Flemming, J., Alexe, M., Mertes, G., Raoult, B., & Chantry, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.03300 · Cited by 3
Representing the Surface Ocean in ECMWF's data-driven forecasting system AIFSPreprint
Hahner, S., Zampieri, L., Bidlot, J., Browne, P., Chantry, M., Clare, M., Cook, H., Dueben, P. D., Furner, R., Keeley, S. P. E., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.25559 · Cited by 7
Heterogeneous Scientific Foundation Model CollaborationPreprint
Li, Z., Zou, J., Fang, F., Ning, X., Ai, M., Wei, T., Chen, S., Yang, X., & He, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.27351 · Cited by 6
WeatherSyn: An Instruction Tuning MLLM For Weather Forecasting Report GenerationPreprint
Zheng, Z., Liu, Y., Chen, N., Zheng, J., Cheng, H., & Li, J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.07522 · Cited by 5
Physically Viable World Models: A Case for Query-Conditioned Embodied AIPreprint
Thorpe, A. J., Tretiakov, S., Hsiao, C.-H., Low, S. A., Li, X., Iqbal, H., Bhatt, N. P., Topcu, U., & Kumar, K. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2605.30542 · Cited by 4
Toward Mechanistic Interpretability of an AI Foundation Model Fine-Tuned for Atmospheric ChemistryPreprint
Hu, J. Y., Higuera-Mendieta, I. G., Sturm, P. O., & Kelp, M. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.20778 · Cited by 4
Advancing Data Quality Assurance with Machine Learning: A Case Study on Wind Vane Stalling Detection
de Feiter, V. S., Strickland, J. M. I., & Garcia-Marti, I. (2025) · Atmosphere · doi:10.3390/atmos16020129 · Cited by 3
Zhu, H., Liu, G., Gao, X., Wang, S., & Jiang, C. (2024) · Advances in Space Research · doi:10.1016/j.asr.2024.09.003 · Cited by 3
TemperatureGAN: generative modeling of regional atmospheric temperatures
Balogun, E., Rajagopal, R., & Majumdar, A. (2024) · Environmental Data Science · doi:10.1017/eds.2024.21 · Cited by 5
Shen, J., Xue, H., Ge, F., & Zhang, J. (2025) · Quarterly Journal of the Royal Meteorological Society · doi:10.1002/qj.4966 · Cited by 3
Accelerating the Discovery of Steady‐States of Planetary Interior Dynamics With Machine Learning
Agarwal, S., Tosi, N., Hüttig, C., Greenberg, D. S., & Bekar, A. C. (2025) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2024jh000438 · Cited by 3
Adaptive Decentralized Federated Learning in LEO Satellite Networks
Li, D., Yan, Z., Hao, Y., Niyato, D. T., & Quek, T. Q. S. (2024) · IEEE International Conference on Communication Technology (ICCT) · doi:10.1109/icct62411.2024.10946644 · Cited by 3
Artificial Intelligence for Research (AI4R): Knowledge Base and Impact
Yu, X., Xia, J., & Shen, Z. (2024) · International Conference on Intelligent Education and Intelligent Research (IEIR) · doi:10.1109/ieir62538.2024.10959986 · Cited by 3
AI Merged With Human Knowledge Produces the Best Possible Weather Forecasts
Penny, S. G. (2025) · Geophysical Research Letters · doi:10.1029/2025gl116465 · Cited by 3
Gray, M., Chattopadhyay, A., Wu, T., Lowe, A., & He, R. (2025) · Ocean science · doi:10.5194/os-21-1065-2025 · Cited by 7
The Double-Edged Sword of AI in Climate Change: Opportunities, Risks, and Responsible Governance
Handa, M. (2025) · The International Journal of Climate Change Impacts and Responses · doi:10.18848/1835-7156/cgp/v17i02/47-62 · Cited by 3
Judd, N. A., Mylona, K., Liu, H., Hogg, A., & Butler, T. (2025) · Journal of Applied Statistics · doi:10.1080/02664763.2025.2519136 · Cited by 3
Balancing accuracy versus precision: Enhancing the usability of sub-seasonal forecasts
Dunn‐Sigouin, E., Kolstad, E. W., Wulff, C. O., Parker, D. J., & Keane, R. J. (2025) · Climate Services · doi:10.1016/j.cliser.2025.100594 · Cited by 4
Jin, Y., Zeng, Z., Chen, Y., Qin, Y., Xu, H. J., & Zhang, D. (2025) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-24-0125.1 · Cited by 8
Accelerate Coastal Ocean Circulation Model with AI Surrogate
Xu, Z., Ren, J., Zhang, Y., Gonzalez-Ondina, J. M., Olabarrieta, M., Xiao, T., He, W., Liu, Z., Chen, S., Smith, K. E., et al. (2025) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps64566.2025.00028 · Cited by 8
Decoding the Primacy of Transportation Emissions of Formaldehyde Pollution in an Urban Atmosphere
Liu, S., Ma, H.-N., Tang, M., Shao, Y.-M., Yao, T.-T., He, L., & Huang, X. (2025) · Toxics · doi:10.3390/toxics13080643 · Cited by 3
Gui, S., Yang, Z., Wu, H., Yang, R., Dong, Z., Yang, Y., & Lian, Y. (2025) · Climate Dynamics · doi:10.1007/s00382-025-07781-x · Cited by 3
SirP: Semi-Recurrent Paradigm-Based Prediction Network for Satellite Image Sequences
Chen, K., Xu, M., Li, W., Mo, F., Huang, Y., Wu, M., & Zhang, C. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3610082 · Cited by 3
Advances in atmospheric, oceanic, and coupled models for meteorological forecasting
Waqas, M., Humphries, U. W., & Wangwongchai, A. (2025) · Natural Hazards Research · doi:10.1016/j.nhres.2025.10.003 · Cited by 6
Heterogeneous Spatiotemporal Graph Learning for Localized Sparse Meteorological Forecasting
Li, S., Li, Q., Du, Z., Zhou, Z., Wang, M., Zhang, L., & Li, W. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3628905 · Cited by 4
MedFormer: a data-driven model for forecasting the Mediterranean Sea
Epicoco, I., Donno, D., Accarino, G., Norberti, S., Grandi, A., Giurato, M., McAdam, R., Elia, D., Clementi, E., Nassisi, P., et al. (2026) · Earth Science Informatics · doi:10.1007/s12145-026-02169-9 · Cited by 3
Nowcasting of dust and convective storms via diffusion-model predictions of SEVIRI RGB imagery
Hermes, K., Marsham, J. H., Bollasina, M. A., Brooks, M., Klose, M., & Marenco, F. (2025) · Weather and Climate Extremes · doi:10.1016/j.wace.2025.100828 · Cited by 3
Li, Z., Xie, Y., Skakun, S. V., Jia, X., Mai, G., Lu, W., Tong, M., & Wang, Z. (2025) · Remote Sensing of Environment · doi:10.1016/j.rse.2025.115138 · Cited by 5
Gu, H., Xu, Y., Pan, H., Shi, Y., Wei, C., Cao, X., & He, Y. (2025) · Chem & Bio Engineering · doi:10.1021/cbe.5c00074 · Cited by 3
Ge, L., Chen, G., Wang, G., Cao, C., Chen, X., & Huang, B. (2025) · GIScience & Remote Sensing · doi:10.1080/15481603.2025.2596455 · Cited by 3
Cloud prediction via spatiotemporal-frequency differential and attentional network
Liu, J., Sun, J., Wei, H., Li, Q., Shi, J., & Gao, M. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.113476 · Cited by 3
NORi: An ML‐Augmented Ocean Boundary Layer Parameterization
Lee, X. K., Ramadhan, A., Souza, A. N., Wagner, G. L., Silvestri, S., Marshall, J. C., & Ferrari, R. (2026) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2025ms005667 · Cited by 3
In Which Ways Is Machine Learning Opaque?
Beisbart, C. (2025) · Synthese Library/Synthese library · doi:10.1007/978-3-032-03083-2_1 · Cited by 2
Yuan, S., Wang, X., Mu, B., Wang, G., Niu, Z., & Li, H. (2025) · Advances in Atmospheric Sciences · doi:10.1007/s00376-025-4520-8 · Cited by 3
Forecast Skill Is Not Decision Skill: Evidence From Weather‐Dependent Decision Tasks
Raeth, K., & Ludwig, N. (2026) · Meteorological Applications · doi:10.1002/met.70260 · Cited by 3
Quantifying the Influence of Climate on Storm Activity Using Machine Learning
Hadas, O., & Kaspi, Y. (2026) · Geophysical Research Letters · doi:10.1029/2025gl118496 · Cited by 3
Sugata, M., Masuda, N., & Yairi, I. E. (2026) · IEEE Access · doi:10.1109/access.2026.3660974 · Cited by 3
A learning-based domain decomposition method
Wu, R. F., Kovachki, N., & Liu, B. (2026) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2026.118799 · Cited by 5
Wu, C., Wu, G. H., Cai, R., Liu, Y., & Zhang, K. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.104442 · Cited by 3
AI‐Based Regional Emulation for Kilometer‐Scale Dynamical Downscaling
Sha, Y., Hertneky, T., Gutmann, E. D., McGinnis, S., McCrary, R., Xue, L., Gagne, D. J., Newman, A., & Newman, A. J. (2026) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2026jh001313 · Cited by 4
Pujol--Nicolas, K., Baggio, R., Lambert, D., Muzy, J., Filippi, J., & Pantillon, F. (2026) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-25-0031.1 · Cited by 5
Assessing seasonal climate predictability using a deep learning application: NN4CAST
Fraile, V. G., Rodríguez‐Fonseca, B., Polo, I., Martín‐Rey, M., & Moreno-García, M. N. (2026) · Geoscientific model development · doi:10.5194/gmd-19-1917-2026 · Cited by 3
Hierarchical Testing of a Hybrid Machine Learning‐Physics Global Atmosphere Model
Chen, Z., Leung, L.-Y. R., Zhou, W., Lu, J., Lubis, S. W., Liu, Y., Chang, C.-C., Harrop, B. E., Wang, Y., Yang, M. M., et al. (2026) · AGU Advances · doi:10.1029/2025av002075 · Cited by 4
Assessing Subseasonal Predictions of Stratosphere‐Troposphere Coupling of GraphCast
Wu, Z. (2026) · Journal of Geophysical Research Atmospheres · doi:10.1029/2025jd044852 · Cited by 4
Rus, M., Ličer, M., & Kristan, M. (2026) · Geoscientific model development · doi:10.5194/gmd-19-2177-2026 · Cited by 3
Bochow, N., Hess, P., & Robinson, A. (2026) · The Cryosphere · doi:10.5194/tc-20-1841-2026 · Cited by 4
Kuznetsova, M. M., Bisi, M. M., Opgenoorth, H. J., Reiß, M., Mays, M. L., Alfonsi, L., Arge, C. N., Barnes, D., Belehaki, A., Berger, T. E., et al. (2026) · Advances in Space Research · doi:10.1016/j.asr.2026.04.041 · Cited by 3
Khrabry, A. I., Startsev, E. A., Powis, A. T., & Kaganovich, I. (2026) · Physics of Fluids · doi:10.1063/5.0323107 · Cited by 3
VA-MoE: Variables-Adaptive Mixture of Experts for Incremental Weather Forecasting
Chen, H., Tao, H., Guo, S., Zhang, J., Dong, Y., Yu, Y., & Bai, L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00742 · Cited by 12
Data-driven global ocean model resolving atmospherically forced ocean dynamics
Kim, J.-H., Kang, D., Yang, Y., Park, J., & Ham, Y. (2026) · Science Advances · doi:10.1126/sciadv.aed1225 · Cited by 4
Reimagining How Flood Warnings Can Inform Decision‐Making and Community Actions
Tran, V. N., Huan, X., Antar, A. D., Banović, N., Bednar, J. H., Bergt, S., Chen, C. Y., Domínguez, F., Fatichi, S., Gonzalez, R., et al. (2026) · Earth s Future · doi:10.1029/2026ef008857 · Cited by 5
Yang, F., Xu, K., Hao, R., Liu, R., Wang, L., Wang, Z., & Zhou, D. (2026) · Geodesy and Geodynamics · doi:10.1016/j.geog.2026.06.005 · Cited by 3
A deep learning model for predicting daily PM 2.5 concentration in response to emission reduction
Liu, S., Geng, G., Xiang, Y., Hu, H., Liu, X., Huang, X., & Zhang, Q. (2026) · Science Advances · doi:10.1126/sciadv.aef5759 · Cited by 3
Buhendwa, B. M., Fang, C., & Wang, J. (2026) · Environmental Pollution · doi:10.1016/j.envpol.2026.128887 · Cited by 3
Zhou, B., Huang, X., Wang, S., Mai, G., Li, D., Wang, Z., Wu, Q., Ning, H., Wang, J., Wu, Q., et al. (2026) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2026.08.001 · Cited by 4
On the Seasonal Predictability of the 2020 North Atlantic Tropical Cyclone Season
Levin, E., Chien, M., Barnes, E. A., He, H., Vecchi, G. A., & Yang, W. (2026) · Monthly Weather Review · doi:10.1175/mwr-d-26-0045.1 · Cited by 3
Machine Learning Enables Real‐Time Proactive Quality Control: A Proof‐Of‐Concept Study
Honda, T., & Yamazaki, A. (2024) · Geophysical Research Letters · doi:10.1029/2023gl107938 · Cited by 3
DCPGRN: A Dynamic Climate Pattern Graph Recurrent Network for Weather Forecasting
Wei, X., Hao, J., Xu, Z., & Han, J. (2023) · International Conference on Networks, Communications and Intelligent Computing (NCIC) · doi:10.1109/ncic61838.2023.00012 · Cited by 3
At-scale Model Output Statistics in mountain environments (AtsMOS v1.0)
de Vries, M. V. W., Matthews, T. K. R., Perry, L. B., Thapa, N., & Wilby, R. L. (2024) · Geoscientific model development · doi:10.5194/gmd-17-7629-2024 · Cited by 3
Neumaier, M., Anselment, M., & Rudolph, S. (2025) · Aerospace · doi:10.3390/aerospace12050412 · Cited by 3
A Big Chill: Examining an Extremely Sharp Cold Front from Three Perspectives
Schumacher, R. S., Mazurek, A. C., Davis, C. M., Franke, M. E., & Gregg, M. (2025) · Monthly Weather Review · doi:10.1175/mwr-d-24-0132.1 · Cited by 3
Zong, P., Bao, T., Tang, J., Cai, N., & Sun, B. (2025) · Weather and Forecasting · doi:10.1175/waf-d-24-0071.1 · Cited by 3
Intercomparison of Deep Learning Model Architectures for Atmospheric River Prediction
Galea, D., & Ma, H. (2025) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-24-0057.1 · Cited by 4
Accelerating Thermal Homann Flow Simulation With Mesh-Based Graph Neural Networks
Samii, D. R., & Tembely, M. (2025) · IEEE Access · doi:10.1109/access.2025.3577098 · Cited by 3
Ensemble of Artificial Neural Networks for Seasonal Forecasting of Wind Speed in Eastern Canada
Leminski, P., Pinheiro, E., & Ouarda, T. B. M. J. (2025) · Energies · doi:10.3390/en18112975 · Cited by 3
Huang, L., Leng, H., Song, J., Wang, D., Wang, W., Hu, R., & Cao, H. (2025) · Applied Sciences · doi:10.3390/app15126399 · Cited by 3
Dong, T., Wang, R., Chen, P., Sun, C., Gan, C., Liu, J., & Zhang, A. (2025) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi14070257 · Cited by 3
Scaling Large-scale GNN Training to Thousands of Processors on CPU-based Supercomputers
Chen, Z., Zhang, L., Wu, D., Chen, P., Huang, J., Liu, X., Yokota, R., Dryden, N., Endo, T., Matsuoka, S., et al. (2025) · International Conference on Supercomputing · doi:10.1145/3721145.3730422 · Cited by 3
Benchmarking Regional Thermodynamic Trends in an AI Emulator, ACE2, and a Hybrid Model, NeuralGCM
Rucker, K., Baxter, I., Hassanzadeh, P., Shaw, T. A., & Pahlavan, H. A. (2026) · Geophysical Research Letters · doi:10.1029/2025gl120185 · Cited by 5
Data-Driven Rainfall Prediction at a Regional Scale: A Case Study with Ghana
Kalita, I., Vilallonga, L., & Atchadé, Y. F. (2025) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-24-0116.1 · Cited by 7
Machine learning for subseasonal-to-seasonal prediction
Mayer, K. J., Lerch, S., de Burgh-Day, C., & Arcodia, M. C. (2025) · Elsevier eBooks · doi:10.1016/b978-0-443-31538-1.00003-8 · Cited by 4
Challenges for Computational Reliabilism in AI and Other Computational Methods
Alvarado, R. (2025) · Synthese Library/Synthese library · doi:10.1007/978-3-032-03083-2_5 · Cited by 4
Metadata
- Authors
- Lam, R., Sanchez-Gonzalez, A., Willson, M., Wirnsberger, P., Fortunato, M., Alet, F., Ravuri, S., Ewalds, T., Eaton-Rosen, Z., Hu, W., Merose, A., Hoyer, S., Holland, G., Vinyals, O., Stott, J., Pritzel, A., Mohamed, S., & Battaglia, P.
- Affiliations
- Google DeepMind, London, UK.
- Google DeepMind (United Kingdom) (GB)
- Google (United States) (US)
- Corresponding author
- Willson, Matthew
- Wirnsberger, Peter
- Fortunato, Meire
- Alet, Ferran
- Ravuri, Suman
- Mohamed, Shakir
- Battaglia, Peter
- ORCID
- Venue
- Science
- Published
- 2023-12-22
- Volume
- 382
- Issue
- 6677
- Pages
- 1416-1421
- ISSN
- 0036-8075 (ISSN-L)
- 1095-9203
- OpenAlex
- W4388654737
- Cited by
- 1,466
- References
- 48
- Citations by year
- 2026: 599 · 2025: 522 · 2024: 319 · 2023: 25
- FWCI
- 161.54
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Science (publishedVersion, cc-by)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Earth and Planetary Sciences › Atmospheric Science › Meteorological Phenomena and Simulations
- Physical Sciences › Environmental Science › Environmental Engineering › Hydrological Forecasting Using AI
- Social Sciences › Transportation › Traffic Prediction and Management Techniques
- Keywords
- medium-range weather forecasting, GraphCast, reanalysis data, machine learning weather prediction, deterministic forecasting, tropical cyclone tracking, atmospheric rivers, severe weather forecasting
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 2026-11-08, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-08 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (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
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.