Learning skillful medium-range global weather forecasting
Open accessThe DOI matches its Crossref record; 65 of the 66 references it cites were found in a registry or an index, and 1 are not checked yet; 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.
Verified 2026-11-19 · 1 reference not checked yet
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
- [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.
- [31] David H Levinson, Howard J Diamond, Kenneth R Knapp, Michael C Kruk, and Ethan J Gibney. Toward a homogenous global tropical cyclone best-track dataset. Bulletin of the American Meteorological Society, 91(3):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
Cited by
Items 701–800 of 2,424
Shi, H., Yang, X., Tang, H., & Tu, Y. (2025) · Journal of Environmental Management · doi:10.1016/j.jenvman.2025.125371 · Cited by 6
Yan, Z., Lu, X., Wu, L., Zhang, H., Fa, L., Wang, X., Xu, W., & Liu, W. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.128042 · Cited by 11
Enforcing the principle of locality for physical simulations with neural operators
Chen, J., Xu, W., Xu, Z., Gutiérrez, N. G., Narra, S. P., & McComb, C. (2025) · Journal of Computational Physics · doi:10.1016/j.jcp.2025.114131 · Cited by 11
Deng, Y., Chen, W., Ding, J., El‐Mowafy, A., Weng, D., Tang, L., Bai, L., & Mi, X. (2025) · Geo-spatial Information Science · doi:10.1080/10095020.2025.2513650 · Cited by 6
DustNet (v1): skilful neural network predictions of dust aerosols over the Saharan desert
Nowak, T., Augousti, A. T., Simmons, B. I., & Siegert, S. (2025) · Geoscientific model development · doi:10.5194/gmd-18-3509-2025 · Cited by 6
Thermodynamics-informed graph neural networks for real-time simulation of digital human twins
Tesan, L., González, D., Martins, P. A. L. D. S., & Cueto, E. (2025) · Computational Mechanics · doi:10.1007/s00466-025-02633-1 · Cited by 9
Brodeur, Z., Taylor, W., Herman, J. D., & Steinschneider, S. (2025) · Water Resources Research · doi:10.1029/2024wr039324 · Cited by 6
Baño‐Medina, J., Sengupta, A., Michaelis, A., Monache, L. D., Kalansky, J. F., & Watson‐Parris, D. (2025) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-24-0090.1 · Cited by 8
Advancing Radar Echo Extrapolation With Hypergraph-Enhanced Latent Diffusion Model
Sun, X., Zhang, Y., Di, X., Piao, X., Wang, F., Jing, G., Lin, D., & Yin, B. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3596232 · Cited by 7
Multi-exit Kolmogorov–Arnold networks: enhancing accuracy and parsimony
Bagrow, J. P., & Bongard, J. (2025) · Machine Learning Science and Technology · doi:10.1088/2632-2153/adf9bd · Cited by 10
Ocean Emulation With Fourier Neural Operators: Double Gyre
Bire, S., Lütjens, B., Azizzadenesheli, K., Anandkumar, A., & Hill, C. (2025) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2023ms004137 · Cited by 11
Hierarchical Joint Graph Learning and Multivariate Time Series Forecasting
Kim, J., Lee, H., Yu, S., Hwang, U., Jung, W., & Yoon, K. (2023) · IEEE Access · doi:10.1109/access.2023.3325041 · Cited by 6
Forecasting water resources from satellite image time series using a graph-based learning strategy
Dufourg, C., Pelletier, C., May, S., & Lefèvre, S. (2024) · The international archives of the photogrammetry, remote sensing and spatial information sciences/International archives of the photogrammetry, remote sensing and spatial information sciences · doi:10.5194/isprs-archives-xlviii-2-2024-81-2024 · Cited by 8
Applied Machine Learning to Study the Movement of Air Masses in the Wind Farm Area
Kovalnogov, V. N., Fedorov, R. V., Chukalin, A. V., Klyachkin, V. N., Tabakov, V. P., & Demidov, D. A. (2024) · Energies · doi:10.3390/en17163961 · Cited by 6
Niu, Z., & Zou, X. (2024) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2024jh000170 · Cited by 6
HR-Extreme: A High-Resolution Dataset for Extreme Weather Forecasting
Ran, N., Xiao, P., Wang, Y., Shi, W., Lin, J., Qi, M., & Allmendinger, R. (2025) · International Conference on Learning Representations · doi:10.48550/arxiv.2409.18885 · Cited by 9
Yan, W., Liu, S., Zou, Y., Liu, X., Wen, D., Hu, Y., Yang, D., Xie, J., & Zhao, L. (2024) · Advances in Atmospheric Sciences · doi:10.1007/s00376-024-3347-z · Cited by 8
Oceanscape: A graph-based framework for autonomous coastal navigation
Fagerhaug, E., Bye, R. T., Osen, O. L., & Hatledal, L. I. (2025) · Ocean Engineering · doi:10.1016/j.oceaneng.2024.120230 · Cited by 6
Wang, S., Li, W., & Hsu, C.-Y. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3532219 · Cited by 6
Zhang, W., Wu, Y., Fan, K., Song, X., Pang, R., & Guoan, B. (2025) · Remote Sensing · doi:10.3390/rs17040610 · Cited by 6
Li, H., Li, J., Wu, Z., Wang, M., Liu, G., Sun, R., Li, R., Wang, N., Song, H., & Zhen, S. (2025) · Machine Learning Science and Technology · doi:10.1088/2632-2153/adc53b · Cited by 9
Patel, D., Arcomano, T., Hunt, B. R., Szunyogh, I., & Ott, E. (2025) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2024ms004480 · Cited by 8
Lovo, A., Lancelin, A., Herbert, C., & Bouchet, F. (2025) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-24-0094.1 · Cited by 12
Wang, M., Xiao, X., Gao, M., & Coveney, P. V. (2026) · Science Advances · doi:10.1126/sciadv.aec5049 · Cited by 14
SciVid: Cross-Domain Evaluation of Video Models in Scientific Applications
Hasson, Y., Luc, P., Momeni, L., Ovsjanikov, M., Moing, G. L., Kuznetsova, A., Ktena, S. I., Sun, J. J., Koppula, S., Gokay, D., et al. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.02024 · Cited by 11
Tabas, S. S., Wang, J., Li, W., Row, M., Zhang, Z., Zhu, L., Li, W., & Carley, J. R. (2025) · NOAA Institutional Repository · doi:10.25923/xd3y-wy31 · Cited by 9
Old Dog, New Trick: Reservoir Computing Advances Machine Learning for Climate Modeling
Bretherton, C. S. (2023) · Geophysical Research Letters · doi:10.1029/2023gl104174 · Cited by 6
Sources of predictability of synoptic‐scale rainfall during the West African summer monsoon
Satheesh, A. R., Knippertz, P., Fink, A. H., Walz, E., & Gneiting, T. (2023) · Quarterly Journal of the Royal Meteorological Society · doi:10.1002/qj.4581 · Cited by 12
Convolutional GRU Network for Seasonal Prediction of the El Niño-Southern OscillationPreprint
Wang, L., Ammons, S., Hur, V. M., Sriver, R. L., & Zhao, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2306.10443 · Cited by 12
Kunyu: A High-Performing Global Weather Model Beyond Regression LossesPreprint
Ni, Z. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2312.08264 · Cited by 7
An ensemble of data-driven weather prediction models for operational sub-seasonal forecastingPreprint
Weyn, J. A., Kumar, D., Berman, J. D., Kazmi, N., Klocek, S., Luferenko, P., & Thambiratnam, K. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2403.15598 · Cited by 7
Deep learning for precipitation nowcasting: A survey from the perspective of time series forecastingPreprint
An, S., Oh, T.-J., Sohn, E.-H., & Kim, D. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2406.04867 · Cited by 7
Deep Learning for Precipitation Nowcasting: A Survey from the Perspective of Time Series ForecastingPreprint
An, S., Oh, T.-J., Sohn, E.-H., & Kim, D. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4888852 · Cited by 6
RAIN: Reinforcement Algorithms for Improving Numerical Weather and Climate ModelsPreprint
Nath, P., Moss, H. B., Shuckburgh, E. F., & Webb, M. J. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2408.16118 · Cited by 6
Gridded Transformer Neural Processes for Large Unstructured Spatio-Temporal DataPreprint
Ashman, M., Diaconu, C., Langezaal, E., Weller, A., & Turner, R. E. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2410.06731 · Cited by 7
Khadir, I., Stevenson, S., Li, H., Krick, K., Burrows, A., Hall, D., Posey, S., & Shen, S. S. P. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2504.17028 · Cited by 6
PEAR: Equal Area Weather Forecasting on the SpherePreprint
Linander, H., Tykesson, T., Rosso, P., Petersson, C., Persson, D., & Gerken, J. E. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2505.17720 · Cited by 7
Loveday, N., & Hertneky, T. (2026) · Geoscientific model development · doi:10.48550/arxiv.2510.25045 · Cited by 6
Controllable Probabilistic Forecasting with Stochastic Decomposition LayersPreprint
Schreck, J. S., Chapman, W. E., Becker, C., Gagne, D. J., Kimpara, D., Cherukuru, N. W., Berner, J., Mayer, K. J., & Sobhani, N. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.18815 · Cited by 6
Divergence-Free Diffusion Models for Incompressible Fluid FlowsPreprint
Genuist, W., Savin, É., Gatti, F., & Clouteau, D. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.19368 · Cited by 6
Universal Diffusion-Based Probabilistic DownscalingPreprint
Molinaro, R., Siegenheim, N., Martin, H., Frey, M., Poulsen, N., Seitz, P., & Gabler, M. V. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.11893 · Cited by 7
PhysMetrics.Weather: An Evaluation Framework for Physical Consistency in ML Weather ModelsPreprint
Kasteleyn, E., Maier, T., Lauer, A., Eyring, V., Gentine, P., & Lučić, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.10642 · Cited by 8
From Observation to Insight: Mechanistic World Models and the Quest for Autonomous DiscoveryPreprint
Posner, I., Lei, A., & Schölkopf, B. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2607.12474 · Cited by 6
Discovery Foundation Models: Toward Open-Ended Discovery IntelligencePreprint
Yang, L., Yin, Z., & Wu, Y. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2609.15973 · Cited by 5
Evaluation of Near-Taiwan Strait Sea Surface Wind Forecast Based on PanGu Weather Prediction Model
Yi, J. J., Li, X., Zhang, Y., Yao, J., Qu, H., & Yi, K. (2024) · Atmosphere · doi:10.3390/atmos15080977 · Cited by 5
Shenolikar, J., Ruti, P. M., Lee, D., Thonipparambil, S., Tervo, R., Fierli, F., Obligis, E., Cacciari, A., Raspaud, M., Bouchet, V. S., et al. (2024) · Bulletin of the American Meteorological Society · doi:10.1175/bams-d-23-0261.1 · Cited by 6
Atmospheric Transport Modeling of CO2 With Neural Networks
Benson, V., Bastos, A., Reimers, C., Winkler, A. J., Yang, F., & Reichstein, M. (2025) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2024ms004655 · Cited by 9
U‐Net Kalman Filter (UNetKF): An Example of Machine Learning‐Assisted Data Assimilation
Lu, F. (2025) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2023ms003979 · Cited by 6
Wang, G., Hou, M., Qin, M., Wu, X., Gao, Z., Chao, G., & Zhang, X. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13050966 · Cited by 5
Online Test of a Neural Network Deep Convection Parameterization in ARP-GEM1
Balogh, B., Saint‐Martin, D., & Geoffroy, O. (2025) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-24-0100.1 · Cited by 7
Spatial verification of global precipitation forecasts
Skok, G., & Lledó, L. (2025) · Quarterly Journal of the Royal Meteorological Society · doi:10.1002/qj.5006 · Cited by 9
Tropical monsoon rainfall can be predicted with lead times up to 10 months
Ran, G., Meng, J., & Fan, J. (2025) · Communications Earth & Environment · doi:10.1038/s43247-025-02391-1 · Cited by 5
Spatio-temporal graph neural networks to improve precipitation forecasts from numerical models
Yousaf, U., Rango, A. D., Furnari, L., D’Ambrosio, D., Senatore, A., & Mendicino, G. (2025) · Soft Computing · doi:10.1007/s00500-025-10635-7 · Cited by 9
Anomalous Behavior in Weather Forecast Uncertainty: Implications for Ship Weather Routing
Marjanović, M., Prpić-Oršić, J., Turk, A., & Valčić, M. (2025) · Journal of Marine Science and Engineering · doi:10.3390/jmse13061185 · Cited by 5
Evaluating the Potential of ChatGPT to Support Climate Risk and Adaptation Assessment
Wilby, R. L. (2025) · Climate Resilience and Sustainability · doi:10.1002/cli2.70013 · Cited by 6
A deep learning approach for coastal downscaling: The northern Adriatic Sea case-study
Adobbati, F., Bonin, L., Cossarini, G., Biagio, V. D., Giordano, F., Manzoni, L., & Querin, S. (2025) · Ocean Modelling · doi:10.1016/j.ocemod.2025.102581 · Cited by 5
Ding, J., Xu, C., Chen, W., Chen, J., Wang, J., Zhang, Y., Bai, L., Han, T., & Xiong, Y. (2025) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2025.3587944 · Cited by 5
Joint Intensity and Spatio-Temporal Representation Learning for Extreme Precipitation Nowcasting
Pan, Z., Hang, R., Liu, Q., Shi, C., Xu, Z., & Yuan, X. (2025) · IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing · doi:10.1109/jstars.2025.3590059 · Cited by 8
Evaluating machine‐learning models for wind‐speed downscaling from ECMWF‐IFS data
Ericson, W., Achermann, F., Lawrance, N., Pasquier, J. T., Andersson, O., & Siegwart, R. (2025) · Quarterly Journal of the Royal Meteorological Society · doi:10.1002/qj.5063 · Cited by 5
Forecast‐Error Diagnostics in Neural Weather Models
Perkan, U., Skok, G., & Zaplotnik, Ž. (2026) · Quarterly Journal of the Royal Meteorological Society · doi:10.1002/qj.70212 · Cited by 5
ORCAst: Operational High-Resolution Current Forecasts
Garcia, P., Larroche, I., Pesnec, A., Bull, H., Archambault, T., Moschos, E., Stegner, A., Charantonis, A., & Béréziat, D. (2025) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-25-0002.1 · Cited by 9
Constructing extreme heatwave storylines with differentiable climate models
Whittaker, T., & Luca, A. D. (2026) · Weather and Climate Dynamics · doi:10.5194/wcd-7-393-2026 · Cited by 14
Zhao, S., Qiu, Y., Yan, Z., Wu, L., Qiu, R., & Luo, Y. (2025) · Journal of Hydrology · doi:10.1016/j.jhydrol.2025.134363 · Cited by 5
Trotta, B., Johnson, R., de Burgh-Day, C., Hudson, D., Abellán, E., Canvin, J., Kelly, A., Mentiplay, D., Owen, B. J., & Whelan, J. (2025) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-25-0037.1 · Cited by 5
Latent Diffusion and Spatiotemporal Transformers Generate Large Ensemble Climate Simulations
Meuer, J., Witte, M., Finn, T. S., Timmreck, C., Ludwig, T. G., & Kadow, C. (2025) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2025.3621121 · Cited by 10
Intelligent Decision‐Making Driven by Large AI Models: Progress, Challenges and Prospects
He, Y., Ruan, S., Wang, D. J., Lu, H., Li, Z., Liu, Y., Xu, C. G., Li, S., Zhao, J., & Liang, J. (2025) · CAAI Transactions on Intelligence Technology · doi:10.1049/cit2.70084 · Cited by 8
Applying deep learning to a chemistry-climate model for improved ozone prediction
Liu, Z., Li, K., Wild, O., Doherty, R. M., O’Connor, F. M., & Turnock, S. T. (2025) · Atmospheric chemistry and physics · doi:10.5194/acp-25-16969-2025 · Cited by 6
Earthquake Rupture Dynamics From Graph Neural Networks
Liu, D., & Becker, T. W. (2025) · Journal of Geophysical Research Solid Earth · doi:10.1029/2025jb031981 · Cited by 5
Philosophy of Science for Machine Learning: Core Issues and New Perspectives
Durán, J. M., & Pozzi, G. (2025) · Synthese Library/Synthese library · doi:10.1007/978-3-032-03083-2 · Cited by 11
Transformers for time-series forecasting: A comprehensive survey through 2024
Okamoto, Y. (2025) · Nonlinear Theory and Its Applications IEICE · doi:10.1587/nolta.17.260 · Cited by 5
AI for Science: Opportunities, Challenges, and Future Directions
Fu, V. (2026) · Journal of Data Science · doi:10.6339/25-jds1214 · Cited by 8
Increasing resolution and accuracy in sub-seasonal forecasting through 3D U-Net: the western US
Ryu, J., Kim, H., Wang, S.-Y. (., & Yoon, J. (2026) · Geoscientific model development · doi:10.5194/gmd-19-27-2026 · Cited by 5
The Role of Equatorial Waves in Triggering Precipitation Extremes in the Maritime Continent
Latos, B., Ferrett, S., Lefort, T., Matthews, A. J., Lubis, S. W., Senior, N., Peyrillé, P., Nguyen, H., Wheeler, M. C., Yik, D. J., et al. (2026) · Monthly Weather Review · doi:10.1175/mwr-d-25-0073.1 · Cited by 7
Nelli, N., Francis, D., Fonseca, R., Hassanzadeh, P., & Cherif, C. (2026) · Atmospheric Research · doi:10.1016/j.atmosres.2026.108779 · Cited by 5
Schmidt, A., Zunker, H., Heinlein, A., & Kühn, M. J. (2026) · Scientific Reports · doi:10.1038/s41598-026-39431-5 · Cited by 5
Reanalyses in the Age of Machine Learning: Why Dataset Curation Matters Now More than Ever
Abel, M. D., Thompson, A. J., Gutmann, E. D., Mahoney, K. M., McCrary, R., Schumacher, R. S., & Slivinski, L. (2026) · Bulletin of the American Meteorological Society · doi:10.1175/bams-d-25-0149.1 · Cited by 5
The convergence of machine learning and data assimilation in Earth system science
Arcucci, R., Healy, S. B., Dance, S. L., Lei, L., Bach, E., Weaver, A., Miyoshi, T., Dillon, M. E., Draper, C. S., Schneider, R., et al. (2026) · npj Artificial Intelligence · doi:10.1038/s44387-026-00107-0 · Cited by 8
Bhosale, Y. H. (2026) · National Academy Science Letters · doi:10.1007/s40009-026-02154-2 · Cited by 6
TopoFlow: topography-aware pollutant Flow learning for high-resolution air quality prediction
Kheder, A., Toropainen, H., Peng, W., Antão, S., Chen, J., Boy, M., & Liu, Z.-S. (2026) · npj Climate and Atmospheric Science · doi:10.1038/s41612-026-01417-5 · Cited by 8
Tesfaldet, Y. T., Ali, H. A., Bershteyn, A., Mukandavire, Z., Khan, B. A., & Daneshkhah, A. (2026) · Urban Climate · doi:10.1016/j.uclim.2026.102910 · Cited by 7
Gupta, A., Sheshadri, A., & Suri, D. (2026) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2025ms005568 · Cited by 9
AI for science: Progress, challenges, and perspectives
Xu, Y., Shao, Z., Liu, X., Li, Y., An, Z., Fu, C., Huang, C., Zhang, L., Gao, F., Li, J., et al. (2026) · The Innovation · doi:10.1016/j.xinn.2026.101530 · Cited by 15
Learning Vertical Coordinates via Automatic Differentiation of a Dynamical Core
Whittaker, T., Taylor, S., Cardoso‐Bihlo, E. D. S., Luca, A. D., & Bihlo, A. (2026) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2025ms005711 · Cited by 5
Physics-Inspired Adaptions to Low-Parameter Neural Network Weather Forecast Systems
Scher, S., & Messori, G. (2023) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-23-0046.1 · Cited by 6
Mu, M., Qin, B., & Dai, G. (2024) · Fundamental Research · doi:10.1016/j.fmre.2024.03.006 · Cited by 6
Beyond Ensemble Averages: Leveraging Climate Model Ensembles for Subseasonal Forecasting
Orlova, E., Liu, H., Rossellini, R., Cash, B. A., & Willett, R. M. (2024) · Artificial Intelligence for the Earth Systems · doi:10.1175/aies-d-23-0103.1 · Cited by 5
Fan, Y., Deng, X., Yang, X., Long, Y., & Bai, F. (2024) · Electronics · doi:10.3390/electronics13204032 · Cited by 5
Development of the Next-generation Atmosphere Dynamics Model in Russia: Current State and Prospects
Shashkin, V. V., Goyman, G. S., & Tretyak, I. D. (2024) · Lobachevskii Journal of Mathematics · doi:10.1134/s1995080224603746 · Cited by 5
The Prospective Application of Machine Learning in Turbulence Forecasting over China
Shao, J., Zhuang, Z., Yu, Z., Lin, K., Wu, K., Leung, Y. Y., & Chan, P. W. (2024) · Journal of Applied Meteorology and Climatology · doi:10.1175/jamc-d-23-0236.1 · Cited by 5
Learned Neural Physics Simulation for Articulated 3D Human Pose Reconstruction
Andriluka, M., Tabanpour, B., Freeman, C. D., & Sminchisescu, C. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-72907-2_19 · Cited by 7
Data-Efficient Inference of Neural Fluid Fields via SciML Foundation Model
Liu, Y., Xu, J., Soroco, M., Wei, Y., & Chen, W. (2026) · International Conference on 3D Vision (3DV) · doi:10.1109/3dv69130.2026.00119 · Cited by 7
The Year of Polar Prediction (YOPP): Achievements, Impacts, and Lessons Learnt
Jung, T. J., Wilson, J., Bauer, P., Bazile, É., Bromwich, D. H., Casati, B., Day, J. J., de Coning, E., Eayrs, C., Godøy, Ø., et al. (2025) · Bulletin of the American Meteorological Society · doi:10.1175/bams-d-23-0226.1 · Cited by 12
Fan, Y., Deng, X., Yang, X., Long, Y., & Bai, F. (2025) · IEEE Aerospace and Electronic Systems Magazine · doi:10.1109/maes.2025.3547284 · Cited by 5
Spherical multigrid neural operator for improving autoregressive global weather forecasting
Hu, Y., Yin, F., Zhang, W., Ren, K., Song, J., Deng, K., & Zhang, D. (2025) · Scientific Reports · doi:10.1038/s41598-025-96208-y · Cited by 17
Solvik, K. K., Penny, S. G., & Hoyer, S. (2025) · Journal of Advances in Modeling Earth Systems · doi:10.1029/2024ms004608 · Cited by 10
Self-citationRTide: Automating the Tidal Response Method
Monahan, T., Tang, T., Roberts, S., & Adcock, T. A. A. (2025) · Journal of Geophysical Research Machine Learning and Computation · doi:10.1029/2024jh000525 · Cited by 9
Shan, S., Sreeram, V., Li, C., Dou, W., Wang, K., Zhang, K., & Wei, H. (2025) · Journal of Renewable and Sustainable Energy · doi:10.1063/5.0254162 · Cited by 6
Roychoudhury, C., He, C., Kumar, R., & Arellano, A. F. (2025) · Earth System Dynamics · doi:10.5194/esd-16-1237-2025 · Cited by 8
Investigating the Use of Terrain‐Following Coordinates in AI‐Driven Precipitation Forecasts
Sha, Y., Schreck, J. S., Chapman, W. E., & Gagne, D. J. (2025) · Geophysical Research Letters · doi:10.1029/2025gl118478 · Cited by 7
Dynamical errors in machine learning forecasts
Fang, Z., & Mengaldo, G. (2025) · Chaos Solitons & Fractals · doi:10.1016/j.chaos.2025.117376 · Cited by 5
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.