Hasil untuk "Meteorology. Climatology"

Eduard Feireisl, Piotr Gwiazda, Agnieszka Świerczewska-Gwiazda

Data assimilation plays a crucial role in modern weather prediction, providing a systematic way to incorporate observational data into complex dynamical models. The paper addresses continuous data assimilation for a model arising as a singular limit of the three-dimensional compressible Navier-Stokes-Fourier system with rotation driven by temperature gradient. The limit system preserves the essential physical mechanisms of the original model, while exhibiting a reduced, effectively two-and-a-half-dimensional structure. This simplified framework allows for a rigorous analytical study of the data assimilation process while maintaining a direct physical connection to the full compressible model. We establish well posedness of global-in-time solutions and a compact trajectory attractor, followed by the stability and convergence results for the nudging scheme applied to the limiting system. Finally, we demonstrate how these results can be combined with a relative entropy argument to extend the assimilation framework to the full three-dimensional compressible setting, thereby establishing a rigorous connection between the reduced and physically complete models.

Gregory Hellbourg

Dynamic Spectrum Sharing (DSS) is increasingly promoted as a key element of modern spectrum policy, driven by the rising demand from commercial wireless systems and advances in spectrum access technologies. Passive radio sciences, including radio astronomy, Earth remote sensing, and meteorology, operate under fundamentally different constraints. They rely on exceptionally low interference spectrum and are highly vulnerable to even brief radio frequency interference. We examine whether DSS can benefit passive services or whether it introduces new failure modes and enforcement challenges. We propose just-in-time quiet zones (JITQZ) as a mechanism for protecting high value observations and assess hybrid frameworks that preserve static protection for core passive bands while allowing constrained dynamic access in adjacent frequencies. We analyze the roles of propagation uncertainty, electromagnetic compatibility constraints, and limited spectrum awareness. Using a game theoretic framework, we show why non-cooperative sharing fails, identify conditions for sustained cooperation, and examine incentive mechanisms including pseudonymetry-enabled attribution that promote compliance. We conclude that DSS can support passive radio sciences only as a high-reliability, safety-critical system. Static allocations remain essential, and dynamic access is viable only with conservative safeguards and enforceable accountability.

Suci Dewi Anugrah, Hamzah Latief, Nanang T. Puspito et al.

Abstract The Banda and Seram Seas, located in the eastern part of Indonesia, have experienced numerous tsunamis due to their complex tectonic setting. Seismic activity in this region is primarily influenced by the megathrust along the 180° westward-bending Banda Arc, situated at the triple junction of the Eurasian, Indo-Australian, and Pacific Plates. This study evaluates the potential tsunami hazards associated with the nine segments of the Banda Arc using worst-case scenario tsunami modeling. The analysis is based on seismicity data recorded from 1960 to November 2023, historical tsunami events, and previous credible tectonic studies. The results of the tsunami modeling are further utilized to identify tsunami-prone villages that should be prioritized for tsunami preparedness programs. This study evaluates the seismic and tsunami hazards in the Banda and Seram Seas. Seismic assessments identify seven segments with the potential to generate significant shallow earthquakes (M ≥ 5) characterized by a thrust fault mechanism. Additionally, the Aru Interplate and Intraplate exhibit a shallow oblique normal fault mechanism. Tsunami modeling indicates that the Seram Interplate, Seram Intraplate, Babar Thrust, Tanimbar Megathrust, Wetar Back-Arc, and Weber Deep could generate substantial Estimated Tsunami Heights (ETH > 3 m), impacting 426 villages. In contrast, the Aru Interplate, Aru Intraplate, and Yamdena segments do not exhibit ETH exceeding 3 m. The most severe tsunami impact is associated with the Seram Thrust Fault Intraplate scenario (M8.6, depth 34 km), affecting Seram, Buru, Ambon, and surrounding islands, as well as the southern coast of the Banda Sea across a distance of more than 500 km. The maximum ETH recorded in this scenario is 24.6 m at Saunulu-Tehuru, Central Maluku. The findings underscore the need for disaster preparedness and mitigation strategies within this tectonically active region.

Jiajun Yao, Lulin Cen, Minyu Zheng et al.

Under global warming, persistent extreme heat events (PHEs) in China have increased significantly in both frequency and intensity, posing severe threats to agriculture and socioeconomic development. Combining observational analysis (1961–2019) and numerical simulations, this study investigates the distinct impacts of Northwest Pacific (NWP) and North Atlantic (NA) sea surface temperature (SST) anomalies on PHEs over China. Key findings include the following: (1) PHEs exhibit heterogeneous spatial distribution, with the Yangtze-Huai River Valley as the hotspot showing the highest frequency and intensity. A regime shift occurred post-2000, marked by a threefold increase in extreme indices (+3σ to +4σ). (2) Observational analyses reveal significant but independent correlations between PHEs and SST anomalies in the tropical NWP and mid-high latitude NA. (3) Numerical experiments demonstrate that NWP warming triggers a meridional dipole response (warming in southern China vs. cooling in the north) via the Pacific–Japan teleconnection pattern, characterized by an eastward-retreated and southward-shifted sub-tropical high (WPSH) coupled with an intensified South Asian High (SAH). In contrast, NA warming induces uniform warming across eastern China through a Eurasian Rossby wave train that modulates the WPSH northward. (4) Thermodynamically, NWP forcing dominates via asymmetric vertical motion and advection processes, while NA forcing primarily enhances large-scale subsidence and shortwave radiation. This study elucidates region-specific oceanic drivers of extreme heat, advancing mechanistic understanding for improved heatwave predictability.

Daniele Tôrres Rodrigues, Flavia Ferreira Batista, Lara de Melo Barbosa Andrade et al.

Climate change and its impacts on precipitation patterns have intensified the occurrence of prolonged dry periods in agricultural regions of Brazil, particularly in the MATOPIBA region (comprising the states of Maranhão, Tocantins, Piauí, and Bahia). This study analyzes the seasonal variability and trends of the Consecutive Dry Days (CDDs) index in the MATOPIBA region from 1981 to 2023. Daily precipitation data from the Brazilian Daily Weather Gridded Data (BR-DWGD) dataset were used for the analysis. The novelty of this work lies in its focus on the seasonal characterization of CDD across the entire MATOPIBA field of agriculture, addressing the following main research question: how have the frequency and persistence of dry spells evolved during the rainy and dry seasons over the past four decades? The methodology involved trend detection using the Mann–Kendall test and Sen’s Slope estimator. The results indicated that during the rainy season, the average CDD ranged from 20 to 60 days, with higher values concentrated in the states of Piauí and Bahia. In contrast, during the dry period, averages exceeded 100 days across most of the region. Trend analysis revealed a significant increase in CDD over extensive areas, particularly in Tocantins and Southern Bahia. The increasing trends were estimated at 1 to 4 days per decade during the rainy season and 4 to 14 days per decade in the dry period. Although a decreasing CDD trend was observed in small areas of Northern Maranhão, possibly associated with the influence of the Intertropical Convergence Zone, the overall scenario indicates a greater persistence of long dry spells. This pattern suggests an increase in vulnerability to water scarcity and agricultural losses. These findings highlight the need for implementing adaptation strategies, such as the use of drought-tolerant cultivars, conservation management practices, irrigation expansion, and public policies aimed at promoting climate resilience in the MATOPIBA region.

L. C. A. Resende, Y. Zhu, R. A. J. Chagas et al.

Abstract The center of the South American Magnetic Anomaly (SAMA), located in southern Brazil, is characterized by enhanced energetic particle precipitation (EPP) at low energies (<40 keV), which can significantly impact the ionosphere during intense geomagnetic storms. Typically confined to high latitudes, sporadic auroral E layers (Esa) have been observed near the SAMA center, particularly during storm recovery phases. However, during the intense geomagnetic storm on 10 May 2024, the Esa layer was detected for the first time over the equatorial Brazilian station Belém (BLM, 1.45°S, 48.49°W, dip = −2.5°). Simultaneously, blanketing Es layers were also observed during the storm's recovery phase, indicating that wind shear mechanisms were also occurring. Satellite data revealed that EPP‐induced ionization extended equatorward beyond the central region of the SAMA, reaching latitudes not previously associated with such effects. Concurrently, disturbed electric fields led to a weakening of the equatorial electrojet (EEJ), inhibiting the development of typical equatorial plasma irregularities. Numerical simulations using the E Region Ionospheric Model confirmed that low‐energy electron precipitation with energy (E) < 2 keV contributed to the observed enhancement in Es layer electron density. These findings provide the first evidence that the occurrence of the Esa layers at equatorial latitudes results from a combination of physical processes, including EPP, wind shear dynamics, and electrodynamic disturbances.

Yingtao Luo, Shikai Fang, Binqing Wu et al.

Weather forecasting is essential but remains computationally intensive and physically incomplete in traditional numerical weather prediction (NWP) methods. Deep learning (DL) models offer efficiency and accuracy but often ignore physical laws, limiting interpretability and generalization. We propose PhyDL-NWP, a physics-guided deep learning framework that integrates physical equations with latent force parameterization into data-driven models. It predicts weather variables from arbitrary spatiotemporal coordinates, computes physical terms via automatic differentiation, and uses a physics-informed loss to align predictions with governing dynamics. PhyDL-NWP enables resolution-free downscaling by modeling weather as a continuous function and fine-tunes pre-trained models with minimal overhead, achieving up to 170x faster inference with only 55K parameters. Experiments show that PhyDL-NWP improves both forecasting performance and physical consistency.

Sencan Sun, Congyi Nai, Baoxiang Pan et al.

Precipitation remains one of the most challenging climate variables to observe and predict accurately. Existing datasets face intricate trade-offs: gauge observations are relatively trustworthy but sparse, satellites provide global coverage with retrieval uncertainties, and numerical models offer physical consistency but are biased and computationally intensive. Here we introduce PRIMER (Precipitation Record Infinite MERging), a deep generative framework that fuses these complementary sources to produce accurate, high-resolution, full-coverage precipitation estimates. PRIMER employs a coordinate-based diffusion model that learns from arbitrary spatial locations and associated precipitation values, enabling seamless integration of gridded data and irregular gauge observations. Through two-stage training--first learning large-scale patterns, then refining with accurate gauge measurements--PRIMER captures both large-scale climatology and local precision. Once trained, it can downscale forecasts, interpolate sparse observations, and correct systematic biases within a principled Bayesian framework. Using gauge observations as ground truth, PRIMER effectively corrects biases in existing datasets, yielding statistically significant error reductions at most stations and furthermore enhancing the spatial coherence of precipitation fields. Crucially, it generalizes without retraining, correcting biases in operational forecasts it has never seen. This demonstrates how generative AI can transform Earth system science by combining imperfect data, providing a scalable solution for global precipitation monitoring and prediction.

Hans J. Haubold, Arak M. Mathai

This paper was prepared for Open-Access-only publication as a guide reporting on Education (all aspects of space science and technology), Teaching (remote sensing and GIS, satellite meteorology and global climate, satellite communication, space and atmospheric sciences, global navigation satellite systems), and Research (solar neutrino problem, formation of structure in the Universe) in astronomy (solar physics, cosmology), physics (nuclear physics, neutrino physics), and mathematics (fractional calculus, special functions of mathematical physics) exercised over 50 years (1974-2024). In this period, more than twenty workshops were held and seven regional centres for space science and technology education were established in all regions of the world: Asia and the Pacific, Latin America and the Caribbean, Africa, Western Asia, and Europe. This effort was undertaken in cooperation with ESA, NASA, JAXA, and 193 member states of the United Nations under the auspices of the UN, also supported by the Committee on Space Research (COSPAR) and the International Astronomical Union (IAU). The paper provides access to most of the documents in the six official languages of the United Nations (Arabic, Chinese, English, French, Russian, and Spanish), proceedings, and published papers and books focusing on education, teaching, and research (listed in Google Scholar and Research Gate).

Christopher H. O’Reilly, Lukas Brunner, Saïd Qasmi et al.

Abstract Observations are increasingly used to constrain multi-model projections for future climate assessments. This study assesses the performance of five constraining methods, which have previously been applied to attempt to improve regional climate projections from CMIP5-era models. We employ an out-of-sample testing approach to assess the efficacy of these constraining methods when applied to “pseudo-observational” datasets to constrain future changes in the European climate. These pseudo-observations are taken from CMIP6 simulations, for which future changes were withheld and used for verification. The constrained projections are more accurate and broadly more reliable for regional temperature projections compared to the unconstrained projections, especially in the summer season, which was not clear prior to this study. However, the constraining methods do not improve regional precipitation projections. We also analysed the performance of multi-method projections by combining the constrained projections, which are found to be competitive with the best-performing individual methods and demonstrate improvements in reliability for some temperature projections. The performance of the multi-method projection highlights the potential of combining constraints for the development of constraining methods.

Sijie Zhao, Hao Chen, Xueliang Zhang et al.

In the context of global climate change and frequent extreme weather events, forecasting future geospatial vegetation states under these conditions is of significant importance. The vegetation change process is influenced by the complex interplay between dynamic meteorological variables and static environmental variables, leading to high levels of uncertainty. Existing deterministic methods are inadequate in addressing this uncertainty and fail to accurately model the impact of these variables on vegetation, resulting in blurry and inaccurate forecasting results. To address these issues, we propose VegeDiff for the geospatial vegetation forecasting task. To our best knowledge, VegeDiff is the first to employ a diffusion model to probabilistically capture the uncertainties in vegetation change processes, enabling the generation of clear and accurate future vegetation states. VegeDiff also separately models the global impact of dynamic meteorological variables and the local effects of static environmental variables, thus accurately modeling the impact of these variables. Extensive experiments on geospatial vegetation forecasting tasks demonstrate the effectiveness of VegeDiff. By capturing the uncertainties in vegetation changes and modeling the complex influence of relevant variables, VegeDiff outperforms existing deterministic methods, providing clear and accurate forecasting results of future vegetation states. Interestingly, we demonstrate the potential of VegeDiff in applications of forecasting future vegetation states from multiple aspects and exploring the impact of meteorological variables on vegetation dynamics. The code of this work will be available at https://github.com/walking-shadow/ Official_VegeDiff.

Atsushi Kudo

Numerical weather prediction (NWP) centers around the world operate a variety of NWP models. In addition, recent advances in AI-driven NWP models have further increased the availability of NWP outputs. While this expansion holds the potential to improve forecast accuracy, it raises a critical question: which prediction is the most plausible? If the NWP models have comparable accuracy, it is impossible to determine in advance which one is the best. Traditional approaches, such as ensemble or weighted averaging, combine multiple NWP outputs to produce a single forecast with improved accuracy. However, they often result in meteorologically unrealistic and uninterpretable outputs, such as the splitting of tropical cyclone centers or frontal boundaries into multiple distinct systems. To address this issue, we propose DeepMedcast, a deep learning method that generates intermediate forecasts between two or more NWP outputs. Unlike averaging, DeepMedcast provides predictions in which meteorologically significant features -- such as the locations of tropical cyclones, extratropical cyclones, fronts, and shear lines -- approximately align with the arithmetic mean of the corresponding features predicted by the input NWP models, without distorting meteorological structures. We demonstrate the capability of DeepMedcast through case studies and verification results, showing that it produces realistic and interpretable forecasts with higher accuracy than the input NWP models. By providing plausible intermediate forecasts, DeepMedcast can significantly contribute to the efficiency and standardization of operational forecasting tasks, including general, marine, and aviation forecasts.

Alicja Miniak-Górecka, Krzysztof Podlaski, Tomasz Gwizdałła

The problem of data clustering is one of the most important in data analysis. It can be problematic when dealing with experimental data characterized by measurement uncertainties and errors. Our paper proposes a recursive scheme for clustering data obtained in geographical (climatological) experiments. The discussion of results obtained by k-means and SOM methods with the developed recursive procedure is presented. We show that the clustering using the new approach gives more acceptable results when compared to experts assessments.

Matthew Nyaaba, Alyson Wright, Gyu Lim Choi

This study examines how Generative Artificial Intelligence reproduces global power hierarchies in education and proposes a framework to address resulting inequities. Using a critical qualitative design, the study conducted zero-shot prompt testing with two leading systems, ChatGPT-4 Turbo and Gemini 1.5, and collected real-time outputs from Global North and South contexts. A critical interpretive analysis traced textual, visual, and structural patterns that revealed forms of digital neocolonialism and their implications for educational equity. Findings show six ways in which GenAI can reinforce Western dominance. Western curriculum assumptions appeared when Gemini listed the same four seasons for the United States and Ghana, reflecting Western climatology and overlooking regional knowledge systems. Other patterns included cultural stereotyping in imagery, Western-centered examples in instructional outputs, limited support for Indigenous and local languages, underrepresentation of non-Western identities in visuals, and access barriers linked to subscription-based models. These patterns demonstrate how GenAI can reproduce inequities even as it introduces new educational opportunities. In response, the study proposes a dual-pathway mitigation model. The Inclusive AI Design pathway includes three components: liberatory design methods that center non-Western epistemologies, anticipatory approaches to reduce representational harm, and decentralized GenAI hubs that support local participation and data sovereignty. The pedagogical pathway, human-centric prompt engineering, equips educators to contextualize prompts and critically engage with outputs. Together, these pathways position GenAI as a tool that can support more equitable and culturally responsive education.

Yakun Chen, Kaize Shi, Zhangkai Wu et al.

Spatiotemporal data analysis is pivotal across various domains, such as transportation, meteorology, and healthcare. The data collected in real-world scenarios are often incomplete due to device malfunctions and network errors. Spatiotemporal imputation aims to predict missing values by exploiting the spatial and temporal dependencies in the observed data. Traditional imputation approaches based on statistical and machine learning techniques require the data to conform to their distributional assumptions, while graph and recurrent neural networks are prone to error accumulation problems due to their recurrent structures. Generative models, especially diffusion models, can potentially circumvent the reliance on inaccurate, previously imputed values for future predictions; However, diffusion models still face challenges in generating stable results. We propose to address these challenges by designing conditional information to guide the generative process and expedite the training process. We introduce a conditional diffusion framework called C$^2$TSD, which incorporates disentangled temporal (trend and seasonality) representations as conditional information and employs contrastive learning to improve generalizability. Our extensive experiments on three real-world datasets demonstrate the superior performance of our approach compared to a number of state-of-the-art baselines.

Alexander Lobbe, Dan Crisan, Oana Lang

Data assimilation plays a crucial role in numerical modeling, enabling the integration of real-world observations into mathematical models to enhance the accuracy and predictive capabilities of simulations. This approach is widely applied in fields such as meteorology, oceanography, and environmental science, where the dynamic nature of systems demands continuous updates to model states. However, the calibration of models in these high-dimensional, nonlinear systems poses significant challenges. In this paper, we explore a novel calibration methodology using diffusion generative models. We generate synthetic data that statistically aligns with a given set of observations (in this case the increments of the numerical approximation of a solution of a partial differential equation). This allows us to efficiently implement a model reduction and assimilate data from a reference system state modeled by a highly resolved numerical solution of the rotating shallow water equation of order 104 degrees of freedom into a stochastic system having two orders of magnitude less degrees of freedom. To do so, the new samples are incorporated into a particle filtering methodology augmented with tempering and jittering for dynamic state estimation, a method particularly suited for handling complex and multimodal distributions. This work demonstrates how generative models can be used to improve the predictive accuracy for particle filters, providing a more computationally efficient solution for data assimilation and model calibration.

Yang Meng, Hossain Noman

Adequate CO₂ is essential for vegetation, but industrial chimneys and land, space and oceanic vehicles exert tons of excessive CO₂ and are mostly responsible for the greenhouse effect, global warming and climate change. Due to COVID-19, CO₂ emission was in 2020 at its lowest level compared to prior decades. However, it is unknown how long it will take to reduce CO₂ emission to a tolerable point. Furthermore, it is also unknown to what extent it can increase or change in the future. Accurate forecasting of CO₂ emissions has real significance for choosing the optimum ways of reducing CO₂ emissions. Although some existing models have noticeable CO₂ emission forecasting accuracy, the models implemented in this work have more efficacy in prediction due to incorporating COVID-19’s effect on CO₂ emission. This paper implements four prediction models using SARIMA (SARIMAX) based on ARIMA. The four models are based on the time period of the surge of the COVID-19 pandemic. The main objective of this work is to compare these four models to suggest an effective model to predict the total CO₂ emissions for the future. The study forecasts global total CO₂ emission from 2022 to 2027 for near future prediction, 2022 to 2054 for future prediction and 2022 to 2072 for far future prediction. Among the various error measures, mean absolute percentage error (MAPE) is chosen for accuracy comparison. The calculation yields different accuracy for the four SARIMAX models. The MAPEs for the four methods are: pre-COV (MAPE: 0.32), start-COV (MAPE: 0.28), trans-COV (MAPE: 0.19), post-COV (MAPE: 0.09). The MAPE value is relatively low for post-COV (MAPE: 0.09). Hence, it can be inferred that post-COV are suitable models to forecast the global total CO₂ emission for the future. The post-COV predictions for the global total CO₂ emission for the years 2022 to 2027 are: 36,218.59, 36,733.69, 37,238.29, 37,260.88, 37,674.01 and 37,921.47 million tons (MT). This study successfully predicts CO₂ emission either for the COVID-19 period or the post-COVID-19 normal periods. The Machine Learning (ML) method used in this study has shown good agreement with the IPCC model in predicting the past emissions, the current emissions due to COVID-19 and the emissions of the upcoming future. These prediction results can be an asset for the decision support system to develop a suitable policy for global CO₂ emission reduction. For future research, a number of other external influence variables responsible for CO₂ emission can be added for finer forecasts. This research is an original work in predicting COVID-19-affected CO₂ emission using AI through the ML methodology.

Qingjiu Gao, Li Wang, Yan Li et al.

Based on the daily minimum air temperature (T_min) data from the China Meteorological Data Network and the NCEP/DOE reanalysis data, the intra-seasonal circulation characteristics and evolution of extreme cold events (ECEs) in Northeast–North China (NE-N) during the winter of 1979–2018 are explored, and the synergistic effects of key circulation systems in the mid-high latitude on ECEs are discussed. The results show that: (1) the winter daily T_min in the NE-N region presents a significant low-frequency period of 10–30 d; during the cooling phases, a pair of cyclone–anticyclone in the lower troposphere moves southeastward, accompanying the intensifying Siberian High, and leads to the abnormal northerly; the developing wave trains in the middle troposphere result in enhancing and maintaining cold air; furthermore, the situation of the upper tropospheric jet weakening in the north and strengthening in the south is favorable for cold air to move southward and accumulate in the NE-N region. (2) There are two wave trains in the Eurasian at 200 hPa level. The north one moves southeastward through the Ural Mountains to the coast of East Asia, with the upstream wave activity flux dispersing to NE-N region, causing the northeast cold vortex to develop. The south one with relatively weak intensity disperses the wave flux northward, and enhances the cold vortex. (3) The key circulation systems of ECEs are the Siberian High, the Ural Mountain Blocking High, the Northeast Cold Vortex, and the East Asian Subtropical Jet. The Ural Mountains Blocking High leads four phases earlier than low temperature, and the rest of the systems are basically in phase with low temperature. The synergistic effect of circulation systems will lead to extended-range cold in the NE-N region.

Lucas Teinturier, Nicholas Vieira, Elisa Jacquet et al.

Reflected light photometry of terrestrial exoplanets could reveal the presence of oceans and continents, hence placing direct constraints on the current and long-term habitability of these worlds. Inferring the albedo map of a planet from its observed light curve is challenging because different maps may yield indistinguishable light curves. This degeneracy is aggravated by changing clouds. It has previously been suggested that disk-integrated photometry spanning multiple days could be combined to obtain a cloud-free surface map of an exoplanet. We demonstrate this technique as part of a Bayesian retrieval by simultaneously fitting for the fixed surface map of a planet and the time-variable overlying clouds. We test this approach on synthetic data then apply it to real disk-integrated observations of the Earth. We find that eight days of continuous synthetic observations are sufficient to reconstruct a faithful low resolution surface albedo map, without needing to make assumptions about cloud physics. For lightcurves with negligible photometric uncertainties, the minimal top-of-atmosphere albedo at a location is a good estimate of its surface albedo. When applied to observations from the Earth Polychromating Imaging Camera aboard the DSCOVR spacecraft, our approach removes only a small fraction of clouds. We attribute this difficulty to the full-phase geometry of observations combined with the short correlation length for Earth clouds. For exoplanets with Earth-like climatology, it may be hard to do much better than a cloud-averaged map. We surmise that cloud removal will be most successful for exoplanets imaged near quarter phase that harbour large cloud systems.

Jaideep Pathak, Shashank Subramanian, Peter Harrington et al.

FourCastNet, short for Fourier Forecasting Neural Network, is a global data-driven weather forecasting model that provides accurate short to medium-range global predictions at $0.25^{\circ}$ resolution. FourCastNet accurately forecasts high-resolution, fast-timescale variables such as the surface wind speed, precipitation, and atmospheric water vapor. It has important implications for planning wind energy resources, predicting extreme weather events such as tropical cyclones, extra-tropical cyclones, and atmospheric rivers. FourCastNet matches the forecasting accuracy of the ECMWF Integrated Forecasting System (IFS), a state-of-the-art Numerical Weather Prediction (NWP) model, at short lead times for large-scale variables, while outperforming IFS for variables with complex fine-scale structure, including precipitation. FourCastNet generates a week-long forecast in less than 2 seconds, orders of magnitude faster than IFS. The speed of FourCastNet enables the creation of rapid and inexpensive large-ensemble forecasts with thousands of ensemble-members for improving probabilistic forecasting. We discuss how data-driven deep learning models such as FourCastNet are a valuable addition to the meteorology toolkit to aid and augment NWP models.