Global Models¶
-
Data-driven Mesoscale Weather Forecasting Combining Swin-Unet and Diffusion Models¶
Data-driven weather prediction models exhibit promising performance and advance continuously. In particular, diffusion models represent fine-scale details without spatial smoothing, which is crucial...Data-driven weather prediction models exhibit promising performance and advance continuously. In particular, diffusion models represent fine-scale details without spatial smoothing, which is crucial for mesoscale predictions, such as heavy rainfall forecasting. However, the applications of diffusion models to mesoscale prediction remain limited. To address this gap, this study proposes an architecture that combines a diffusion model with Swin-Unet as a deterministic model, achieving mesoscale predictions while maintaining flexibility. The proposed architecture trains the two models independently, allowing the diffusion model to remain unchanged when the deterministic model is updated. Comparisons using the Fractions Skill Score and power spectral analysis demonstrate that incorporating the diffusion model leads to improved accuracy compared to predictions without it. These findings underscore the potential of the proposed architecture to enhance mesoscale predictions, particularly for strong rainfall events, while maintaining flexibility. more
-
Local wind speed forecasting at short time horizons based on Numerical Weather Prediction and observations from surrounding stations¶
This study presents a hybrid neural network model for short-term (1-6 hours ahead) surface wind speed forecasting, combining Numerical Weather Prediction (NWP) with observational data from ground...This study presents a hybrid neural network model for short-term (1-6 hours ahead) surface wind speed forecasting, combining Numerical Weather Prediction (NWP) with observational data from ground weather stations. It relies on the MeteoNet dataset, which includes data from global (ARPEGE) and regional (AROME) NWP models of the French weather service and meteorological observations from ground stations in the French Mediterranean. The proposed neural network architecture integrates recent past station observations (over last few hours) and AROME and ARPEGE predictions on a small subgrid around the target location. The model is designed to provide both deterministic and probabilistic forecasts, with the latter predicting the parameters of a suitable probability distribution that notably allows us to capture extreme wind events. Our results demonstrate that the hybrid model significantly outperforms baseline methods, including raw NWP predictions, persistence models, and linear regression, across all forecast horizons. For instance, the model reduces RMSE by up 30% compared to AROME predictions. Probabilistic forecasting further enhances performance, particularly for extreme quantiles, by estimating conditional quantiles rather than relying solely on the conditional mean. Fine-tuning the model for specific stations, such as those in the Mediterranean island of Corsica, further improves forecasting accuracy. Our study highlights the importance of integrating multiple data sources and probabilistic approaches to improve short-term wind speed forecasting. It defines an effective approach, even in a complex terrain like Corsica where localized wind variations are significant more
-
Towards Location-Specific Precipitation Projections Using Deep Neural Networks¶
Accurate precipitation estimates at individual locations are crucial for weather forecasting and spatial analysis. This study presents a paradigm shift by leveraging Deep Neural Networks (DNNs) to...Accurate precipitation estimates at individual locations are crucial for weather forecasting and spatial analysis. This study presents a paradigm shift by leveraging Deep Neural Networks (DNNs) to surpass traditional methods like Kriging for station-specific precipitation approximation. We propose two innovative NN architectures: one utilizing precipitation, elevation, and location, and another incorporating additional meteorological parameters like humidity, temperature, and wind speed. Trained on a vast dataset (1980-2019), these models outperform Kriging across various evaluation metrics (correlation coefficient, root mean square error, bias, and skill score) on a five-year validation set. This compelling evidence demonstrates the transformative power of deep learning for spatial prediction, offering a robust and precise alternative for station-specific precipitation estimation. more
-
Development of a Data-driven weather forecasting system over India with Pangu-Weather architecture and IMDAA reanalysis Data¶
Numerical Weather Prediction (NWP) has advanced significantly in recent decades but still faces challenges in accuracy, computational efficiency, and scalability. Data-driven weather models have...Numerical Weather Prediction (NWP) has advanced significantly in recent decades but still faces challenges in accuracy, computational efficiency, and scalability. Data-driven weather models have shown great promise, sometimes surpassing operational NWP systems. However, training these models on massive datasets incurs high computational costs. A regional data-driven approach offers a cost-effective alternative for localized forecasts. This study develops a regional weather forecasting model for India by efficiently modifying the Pangu-Weather (PW) architecture. The model is trained using the Indian Monsoon Data Assimilation and Analysis (IMDAA) reanalysis dataset with limited computational resources. Prediction results are evaluated using Root Mean Square Error (RMSE), Anomaly Correlation Coefficient (ACC), Mean Absolute Percentage Error (MAPE), and Fractional Skill Score (FSS). At a 6-hour lead time, MAPE remains below 5%, FSS exceeds 0.86, and ACC stays above 0.94, demonstrating robustness. Three forecasting approaches, static, autoregressive, and hierarchical, are compared. Errors increase with lead time in all cases. The static approach exhibits periodic fluctuations in error metrics, which are absent in the autoregressive method. The hierarchical approach also shows fluctuations, though with reduced intensity after three days. Among these, the hierarchical approach performs best while maintaining computational efficiency. Furthermore, the model effectively predicts cyclone tracks using the hierarchical approach, achieving results comparable to observational and reanalysis datasets. more
-
Probabilistic Forecasting for Dynamical Systems with Missing or Imperfect Data¶
The modeling of dynamical systems is essential in many fields, but applying machine learning techniques is often challenging due to incomplete or noisy data. This study introduces a variant of...The modeling of dynamical systems is essential in many fields, but applying machine learning techniques is often challenging due to incomplete or noisy data. This study introduces a variant of stochastic interpolation (SI) for probabilistic forecasting, estimating future states as distributions rather than single-point predictions. We explore its mathematical foundations and demonstrate its effectiveness on various dynamical systems, including the challenging WeatherBench dataset. more
-
Predicting Tropical Cyclone Track Forecast Errors using a Probabilistic Neural Network¶
A new method for estimating tropical cyclone track uncertainty is presented and tested. This method uses a neural network to predict a bivariate normal distribution, which serves as an estimate for...A new method for estimating tropical cyclone track uncertainty is presented and tested. This method uses a neural network to predict a bivariate normal distribution, which serves as an estimate for track uncertainty. We train the network and make predictions on forecasts from the National Hurricane Center (NHC), which currently uses static error distributions based on forecasts from the past five years for most applications. The neural network-based method produces uncertainty estimates that are dynamic and probabilistic. Further, the neural network-based method allows for probabilistic statements about tropical cyclone trajectories, including landfall probability, which we highlight. We show that our predictions are well calibrated using multiple metrics, that our method produces better uncertainty estimates than current NHC approaches, and that our method achieves similar performance to the Global Ensemble Forecast System. Once trained, the computational cost of predictions using this method is negligible, making it a strong candidate to improve the NHC's operational estimations of tropical cyclone track uncertainty. more
-
Physics-Informed Residual Neural Ordinary Differential Equations for Enhanced Tropical Cyclone Intensity Forecasting¶
Accurate tropical cyclone (TC) intensity prediction is crucial for mitigating storm hazards, yet its complex dynamics pose challenges to traditional methods. Here, we introduce a Physics-Informed...Accurate tropical cyclone (TC) intensity prediction is crucial for mitigating storm hazards, yet its complex dynamics pose challenges to traditional methods. Here, we introduce a Physics-Informed Residual Neural Ordinary Differential Equation (PIR-NODE) model to precisely forecast TC intensity evolution. This model leverages the powerful non-linear fitting capabilities of deep learning, integrates residual connections to enhance model depth and training stability, and explicitly models the continuous temporal evolution of TC intensity using Neural ODEs. Experimental results in the SHIPS dataset demonstrate that the PIR-NODE model achieves a significant improvement in 24-hour intensity prediction accuracy compared to traditional statistical models and benchmark deep learning methods, with a 25. 2% reduction in the root mean square error (RMSE) and a 19.5% increase in R-square (R2) relative to a baseline of neural network. Crucially, the residual structure effectively preserves initial state information, and the model exhibits robust generalization capabilities. This study details the PIR-NODE model architecture, physics-informed integration strategies, and comprehensive experimental validation, revealing the substantial potential of deep learning techniques in predicting complex geophysical systems and laying the foundation for future refined TC forecasting research. more
-
Weakly-Constrained 4D Var for Downscaling with Uncertainty using Data-Driven Surrogate Models¶
Dynamic downscaling typically involves using numerical weather prediction (NWP) solvers to refine coarse data to higher spatial resolutions. Data-driven models such as FourCastNet have emerged as a...Dynamic downscaling typically involves using numerical weather prediction (NWP) solvers to refine coarse data to higher spatial resolutions. Data-driven models such as FourCastNet have emerged as a promising alternative to the traditional NWP models for forecasting. Once these models are trained, they are capable of delivering forecasts in a few seconds, thousands of times faster compared to classical NWP models. However, as the lead times, and, therefore, their forecast window, increase, these models show instability in that they tend to diverge from reality. In this paper, we propose to use data assimilation approaches to stabilize them when used for downscaling tasks. Data assimilation uses information from three different sources, namely an imperfect computational model based on partial differential equations (PDE), from noisy observations, and from an uncertainty-reflecting prior. In this work, when carrying out dynamic downscaling, we replace the computationally expensive PDE-based NWP models with FourCastNet in a “weak-constrained 4DVar framework” that accounts for the implied model errors. We demonstrate the efficacy of this approach for a hurricane-tracking problem; moreover, the 4DVar framework naturally allows the expression and quantification of uncertainty. We demonstrate, using ERA5 data, that our approach performs better than the ensemble Kalman filter (EnKF) and the unstabilized FourCastNet model, both in terms of forecast accuracy and forecast uncertainty. more
-
ML-Physical Fusion Models Are Accelerating the Paradigm Shift in Operational Typhoon Forecasting¶
In this study, we develop a hybrid operational typhoon forecasting model that integrates the FuXi machine-learning (ML) model with the physics-based Shanghai Typhoon Model (SHTM) into a dual...In this study, we develop a hybrid operational typhoon forecasting model that integrates the FuXi machine-learning (ML) model with the physics-based Shanghai Typhoon Model (SHTM) into a dual physics-data-driven framework. By employing spectral nudging, the hybrid model named FuXi-SHTM leverages FuXi's robust large-scale forecasting capabilities alongside SHTM's mesoscale strengths, significantly enhancing track, intensity, and precipitation predictions for super typhoons Yagi (2024) and Krathon (2024). Besides, this study aims to identify the sensitive regions for the hybrid model by using Conditional Nonlinear Optimal Perturbation (CNOP) method. Despite being constrained by FuXi's large-scale forecast fields, the dense assimilation of satellite observations within these sensitive regions can further enhance typhoon forecasts. Besides, this study offers key insights into the emerging paradigms that are set to shape the future development of both machine learning and physics-based modeling approaches. more
-
Investigating the use of terrain-following coordinates in AI-driven precipitation forecasts¶
Artificial Intelligence (AI) weather prediction (AIWP) models often produce “blurry” precipitation forecasts. This study presents a novel solution to tackle this problem -- integrating...Artificial Intelligence (AI) weather prediction (AIWP) models often produce “blurry” precipitation forecasts. This study presents a novel solution to tackle this problem -- integrating terrain-following coordinates into AIWP models. Forecast experiments are conducted to evaluate the effectiveness of terrain-following coordinates using FuXi, an example AIWP model, adapted to 1.0 degree grid spacing data. Verification results show a largely improved estimation of extreme events and precipitation intensity spectra. Terrain-following coordinates are also found to collaborate well with global mass and energy conservation constraints, with a clear reduction of drizzle bias. Case studies reveal that terrain-following coordinates can represent near-surface winds better, which helps AIWP models in learning the relationships between precipitation and other prognostic variables. The result of this study suggests that terrain-following coordinates are worth considering for AIWP models in producing more accurate precipitation forecasts. more
-
Spatiotemporal Forecasting in Climate Data Using EOFs and Machine Learning Models: A Case Study in Chile¶
Effective resource management and environmental planning in regions with high climatic variability, such as Chile, demand advanced predictive tools. This study addresses this challenge by employing...Effective resource management and environmental planning in regions with high climatic variability, such as Chile, demand advanced predictive tools. This study addresses this challenge by employing an innovative and computationally efficient hybrid methodology that integrates machine learning (ML) methods for time series forecasting with established statistical techniques. The spatiotemporal data undergo decomposition using time-dependent Empirical Orthogonal Functions (EOFs), denoted as \(φ_{k}(t)\), and their corresponding spatial coefficients, \(α_{k}(s)\), to reduce dimensionality. Wavelet analysis provides high-resolution time and frequency information from the \(φ_{k}(t)\) functions, while neural networks forecast these functions within a medium-range horizon \(h\). By utilizing various ML models, particularly a Wavelet - ANN hybrid model, we forecast \(φ_{k}(t+h)\) up to a time horizon \(h\), and subsequently reconstruct the spatiotemporal data using these extended EOFs. This methodology is applied to a grid of climate data covering the territory of Chile. It transitions from a high-dimensional multivariate spatiotemporal data forecasting problem to a low-dimensional univariate forecasting problem. Additionally, cluster analysis with Dynamic Time Warping for defining similarities between rainfall time series, along with spatial coherence and predictability assessments, has been instrumental in identifying geographic areas where model performance is enhanced. This approach also elucidates the reasons behind poor forecast performance in regions or clusters with low spatial coherence and predictability. By utilizing cluster medoids, the forecasting process becomes more practical and efficient. This compound approach significantly reduces computational complexity while generating forecasts of reasonable accuracy and utility. more
-
AI Models Still Lag Behind Traditional Numerical Models in Predicting Sudden-Turning Typhoons¶
Given the interpretability, accuracy, and stability of numerical weather prediction (NWP) models, current operational weather forecasting relies heavily on the NWP approach. In the past two years,...Given the interpretability, accuracy, and stability of numerical weather prediction (NWP) models, current operational weather forecasting relies heavily on the NWP approach. In the past two years, the rapid development of Artificial Intelligence (AI) has provided an alternative solution for medium-range (1-10 days) weather forecasting. Bi et al. (2023) (hereafter Bi23) introduced the first AI-based weather prediction (AIWP) model in China, named Pangu-Weather, which offers fast prediction without compromising accuracy. In their work, Bi23 made notable claims regarding its effectiveness in extreme weather predictions. However, this claim lacks persuasiveness because the extreme nature of the two tropical cyclones (TCs) examples presented in Bi23, namely Typhoon Kong-rey and Typhoon Yutu, stems primarily from their intensities rather than their moving paths. Their claim may mislead into another meaning which is that Pangu-Weather works well in predicting unusual typhoon paths, which was not explicitly analyzed. Here, we reassess Pangu-Weather's ability to predict extreme TC trajectories from 2020-2024. Results reveal that while Pangu-Weather overall outperforms NWP models in predicting tropical cyclone (TC) tracks, it falls short in accurately predicting the rarely observed sudden-turning tracks, such as Typhoon Khanun in 2023. We argue that current AIWP models still lag behind traditional NWP models in predicting such rare extreme events in medium-range forecasts. more
-
ClimateLLM: Efficient Weather Forecasting via Frequency-Aware Large Language Models¶
Weather forecasting is crucial for public safety, disaster prevention and mitigation, agricultural production, and energy management, with global relevance. Although deep learning has significantly...Weather forecasting is crucial for public safety, disaster prevention and mitigation, agricultural production, and energy management, with global relevance. Although deep learning has significantly advanced weather prediction, current methods face critical limitations: (i) they often struggle to capture both dynamic temporal dependencies and short-term abrupt changes, making extreme weather modeling difficult; (ii) they incur high computational costs due to extensive training and resource requirements; (iii) they have limited adaptability to multi-scale frequencies, leading to challenges when separating global trends from local fluctuations. To address these issues, we propose ClimateLLM, a foundation model for weather forecasting. It captures spatiotemporal dependencies via a cross-temporal and cross-spatial collaborative modeling framework that integrates Fourier-based frequency decomposition with Large Language Models (LLMs) to strengthen spatial and temporal modeling. Our framework uses a Mixture-of-Experts (MoE) mechanism that adaptively processes different frequency components, enabling efficient handling of both global signals and localized extreme events. In addition, we introduce a cross-temporal and cross-spatial dynamic prompting mechanism, allowing LLMs to incorporate meteorological patterns across multiple scales effectively. Extensive experiments on real-world datasets show that ClimateLLM outperforms state-of-the-art approaches in accuracy and efficiency, as a scalable solution for global weather forecasting. more
-
Learning low-dimensional representations of ensemble forecast fields using autoencoder-based methods¶
Large-scale numerical simulations often produce high-dimensional gridded data that is challenging to process for downstream applications. A prime example is numerical weather prediction, where...Large-scale numerical simulations often produce high-dimensional gridded data that is challenging to process for downstream applications. A prime example is numerical weather prediction, where atmospheric processes are modeled using discrete gridded representations of the physical variables and dynamics. Uncertainties are assessed by running the simulations multiple times, yielding ensembles of simulated fields as a high-dimensional stochastic representation of the forecast distribution. The high-dimensionality and large volume of ensemble datasets poses major computing challenges for subsequent forecasting stages. Data-driven dimensionality reduction techniques could help to reduce the data volume before further processing by learning meaningful and compact representations. However, existing dimensionality reduction methods are typically designed for deterministic and single-valued inputs, and thus cannot handle ensemble data from multiple randomized simulations. In this study, we propose novel dimensionality reduction approaches specifically tailored to the format of ensemble forecast fields. We present two alternative frameworks, which yield low-dimensional representations of ensemble forecasts while respecting their probabilistic character. The first approach derives a distribution-based representation of an input ensemble by applying standard dimensionality reduction techniques in a member-by-member fashion and merging the member representations into a joint parametric distribution model. The second approach achieves a similar representation by encoding all members jointly using a tailored variational autoencoder. We evaluate and compare both approaches in a case study using 10 years of temperature and wind speed forecasts over Europe. The approaches preserve key spatial and statistical characteristics of the ensemble and enable probabilistic reconstructions of the forecast fields. more
-
Physically Consistent Global Atmospheric Data Assimilation with Machine Learning in Latent Space¶
Data assimilation (DA) integrates observations with model forecasts to produce optimized atmospheric states, whose physical consistency is critical for stable weather forecasting and reliable climate...Data assimilation (DA) integrates observations with model forecasts to produce optimized atmospheric states, whose physical consistency is critical for stable weather forecasting and reliable climate research. Traditional Bayesian DA methods enforce these nonlinear, flow-dependent physical constraints through empirical and tunable covariance structures, but with limited accuracy and robustness. Here, we introduce Latent Data Assimilation (LDA), a framework that performs Bayesian DA in a latent space learned from multivariate global atmospheric data via an autoencoder. We demonstrate that the autoencoder can largely capture nonlinear physical relationships, enabling LDA to produce balanced analyses without explicitly modeling physical constraints. Assimilation in latent space also improves both analysis quality and forecast skill compared to traditional model-space DA, under both idealized and real observational settings. Furthermore, LDA exhibits strong robustness across latent dimensions and remains effective even when the autoencoder is trained on inaccurate but physically realistic forecasts, highlighting its flexibility for real-world applications. more
-
Enhancing Near Real Time AI-NWP Hurricane Forecasts: Improving Explainability and Performance Through Physics-Based Models and Land Surface Feedback¶
Hurricane track forecasting remains a significant challenge due to the complex interactions between the atmosphere, land, and ocean. Although AI-based numerical weather prediction models, such as...Hurricane track forecasting remains a significant challenge due to the complex interactions between the atmosphere, land, and ocean. Although AI-based numerical weather prediction models, such as Google Graphcast operation, have significantly improved hurricane track forecasts, they currently function as atmosphere-only models, omitting critical land and ocean interactions. To investigate the impact of land feedback, we conducted independent simulations using the physics-based Hurricane WRF experimental model to assess how soil moisture variations influence storm trajectories. Our results show that land surface conditions significantly alter storm paths, demonstrating the importance of land-atmosphere coupling in hurricane prediction. Although recent advances have introduced AI-based atmosphere-ocean coupled models, a fully functional AI-driven atmosphere-land-ocean model does not yet exist. Our findings suggest that AI-NWP models could be further improved by incorporating land surface interactions, improving both forecast accuracy and explainability. Developing a fully coupled AI-based weather model would mark a critical step toward more reliable and physically consistent hurricane forecasting, with direct applications for disaster preparedness and risk mitigation. more
-
Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function¶
Recent advancements in data-driven weather forecasting models have delivered deterministic models that outperform the leading operational forecast systems based on traditional, physics-based models....Recent advancements in data-driven weather forecasting models have delivered deterministic models that outperform the leading operational forecast systems based on traditional, physics-based models. However, these data-driven models are typically trained with a mean squared error loss function, which causes smoothing of fine scales through a "double penalty" effect. We develop a simple, parameter-free modification to this loss function that avoids this problem by separating the loss attributable to decorrelation from the loss attributable to spectral amplitude errors. Fine-tuning the GraphCast model with this new loss function results in sharp deterministic weather forecasts, an increase of the model's effective resolution from 1,250km to 160km, improvements to ensemble spread, and improvements to predictions of tropical cyclone strength and surface wind extremes. more
-
Improving Tropical Cyclone Forecasting With Video Diffusion Models¶
Tropical cyclone (TC) forecasting is crucial for disaster preparedness and mitigation. While recent deep learning approaches have shown promise, existing methods often treat TC evolution as a series...Tropical cyclone (TC) forecasting is crucial for disaster preparedness and mitigation. While recent deep learning approaches have shown promise, existing methods often treat TC evolution as a series of independent frame-to-frame predictions, limiting their ability to capture long-term dynamics. We present a novel application of video diffusion models for TC forecasting that explicitly models temporal dependencies through additional temporal layers. Our approach enables the model to generate multiple frames simultaneously, better capturing cyclone evolution patterns. We introduce a two-stage training strategy that significantly improves individual-frame quality and performance in low-data regimes. Experimental results show our method outperforms the previous approach of Nath et al. by 19.3% in MAE, 16.2% in PSNR, and 36.1% in SSIM. Most notably, we extend the reliable forecasting horizon from 36 to 50 hours. Through comprehensive evaluation using both traditional metrics and Fréchet Video Distance (FVD), we demonstrate that our approach produces more temporally coherent forecasts while maintaining competitive single-frame quality. Code accessible at https://github.com/Ren-creater/forecast-video-diffmodels. more
-
QGAPHEnsemble : Combining Hybrid QLSTM Network Ensemble via Adaptive Weighting for Short Term Weather Forecasting¶
Accurate weather forecasting holds significant importance, serving as a crucial tool for decision-making in various industrial sectors. The limitations of statistical models, assuming independence...Accurate weather forecasting holds significant importance, serving as a crucial tool for decision-making in various industrial sectors. The limitations of statistical models, assuming independence among data points, highlight the need for advanced methodologies. The correlation between meteorological variables necessitate models capable of capturing complex dependencies. This research highlights the practical efficacy of employing advanced machine learning techniques proposing GenHybQLSTM and BO-QEnsemble architecture based on adaptive weight adjustment strategy. Through comprehensive hyper-parameter optimization using hybrid quantum genetic particle swarm optimisation algorithm and Bayesian Optimization, our model demonstrates a substantial improvement in the accuracy and reliability of meteorological predictions through the assessment of performance metrics such as MSE (Mean Squared Error) and MAPE (Mean Absolute Percentage Prediction Error). The paper highlights the importance of optimized ensemble techniques to improve the performance the given weather forecasting task. more
-
Deep Learning and Foundation Models for Weather Prediction: A Survey¶
Physics-based numerical models have been the bedrock of atmospheric sciences for decades, offering robust solutions but often at the cost of significant computational resources. Deep learning (DL)...Physics-based numerical models have been the bedrock of atmospheric sciences for decades, offering robust solutions but often at the cost of significant computational resources. Deep learning (DL) models have emerged as powerful tools in meteorology, capable of analyzing complex weather and climate data by learning intricate dependencies and providing rapid predictions once trained. While these models demonstrate promising performance in weather prediction, often surpassing traditional physics-based methods, they still face critical challenges. This paper presents a comprehensive survey of recent deep learning and foundation models for weather prediction. We propose a taxonomy to classify existing models based on their training paradigms: deterministic predictive learning, probabilistic generative learning, and pre-training and fine-tuning. For each paradigm, we delve into the underlying model architectures, address major challenges, offer key insights, and propose targeted directions for future research. Furthermore, we explore real-world applications of these methods and provide a curated summary of open-source code repositories and widely used datasets, aiming to bridge research advancements with practical implementations while fostering open and trustworthy scientific practices in adopting cutting-edge artificial intelligence for weather prediction. The related sources are available at https://github.com/JimengShi/ DL-Foundation-Models-Weather. more
-
Improving AI weather prediction models using global mass and energy conservation schemes¶
Artificial Intelligence (AI) weather prediction (AIWP) models are powerful tools for medium-range forecasts but often lack physical consistency, leading to outputs that violate conservation laws....Artificial Intelligence (AI) weather prediction (AIWP) models are powerful tools for medium-range forecasts but often lack physical consistency, leading to outputs that violate conservation laws. This study introduces a set of novel physics-based schemes designed to enforce the conservation of global dry air mass, moisture budget, and total atmospheric energy in AIWP models. The schemes are highly modular, allowing for seamless integration into a wide range of AI model architectures. Forecast experiments are conducted to demonstrate the benefit of conservation schemes using FuXi, an example AIWP model, modified and adapted for 1.0-degree grid spacing. Verification results show that the conservation schemes can guide the model in producing forecasts that obey conservation laws. The forecast skills of upper-air and surface variables are also improved, with longer forecast lead times receiving larger benefits. Notably, large performance gains are found in the total precipitation forecasts, owing to the reduction of drizzle bias. The proposed conservation schemes establish a foundation for implementing other physics-based schemes in the future. They also provide a new way to integrate atmospheric domain knowledge into the design and refinement of AIWP models. more
-
OMG-HD: A High-Resolution AI Weather Model for End-to-End Forecasts from Observations¶
In recent years, Artificial Intelligence Weather Prediction (AIWP) models have achieved performance comparable to, or even surpassing, traditional Numerical Weather Prediction (NWP) models by...In recent years, Artificial Intelligence Weather Prediction (AIWP) models have achieved performance comparable to, or even surpassing, traditional Numerical Weather Prediction (NWP) models by leveraging reanalysis data. However, a less-explored approach involves training AIWP models directly on observational data, enhancing computational efficiency and improving forecast accuracy by reducing the uncertainties introduced through data assimilation processes. In this study, we propose OMG-HD, a novel AI-based regional high-resolution weather forecasting model designed to make predictions directly from observational data sources, including surface stations, radar, and satellite, thereby removing the need for operational data assimilation. Our evaluation shows that OMG-HD outperforms both the European Centre for Medium-Range Weather Forecasts (ECMWF)'s high-resolution operational forecasting system, IFS-HRES, and the High-Resolution Rapid Refresh (HRRR) model at lead times of up to 12 hours across the contiguous United States (CONUS) region. We achieve up to a 13% improvement on RMSE for 2-meter temperature, 17% on 10-meter wind speed, 48% on 2-meter specific humidity, and 32% on surface pressure compared to HRRR. Our method shows that it is possible to use AI-driven approaches for rapid weather predictions without relying on NWP-derived weather fields as model input. This is a promising step towards using observational data directly to make operational forecasts with AIWP models. more
-
Assimilating Observed Surface Pressure into ML Weather Prediction Models¶
There has been a recent surge in development of accurate machine learning (ML) weather prediction models, but evaluation of these models has mainly been focused on medium-range forecasts, not their...There has been a recent surge in development of accurate machine learning (ML) weather prediction models, but evaluation of these models has mainly been focused on medium-range forecasts, not their performance in cycling data assimilation (DA) systems. Cycling DA provides a statistically optimal estimate of model initial conditions, given observations and previous model forecasts. Here, real surface pressure observations are assimilated into several popular ML models using an ensemble Kalman filter, where accurate ensemble covariance estimation is essential to constrain unobserved state variables from sparse observations. In this cycling DA system, deterministic ML models accumulate small-scale noise until they diverge. Mitigating this noise with a spectral filter can stabilize the system, but with larger errors than traditional models. Perturbation experiments illustrate that these models do not accurately represent short-term error growth, leading to poor estimation of cross-variable covariances. more
-
AIFS-CRPS: Ensemble forecasting using a model trained with a loss function based on the Continuous Ranked Probability Score¶
Over the last three decades, ensemble forecasts have become an integral part of forecasting the weather. They provide users with more complete information than single forecasts as they permit to...Over the last three decades, ensemble forecasts have become an integral part of forecasting the weather. They provide users with more complete information than single forecasts as they permit to estimate the probability of weather events by representing the sources of uncertainties and accounting for the day-to-day variability of error growth in the atmosphere. This paper presents a novel approach to obtain a weather forecast model for ensemble forecasting with machine-learning. AIFS-CRPS is a variant of the Artificial Intelligence Forecasting System (AIFS) developed at ECMWF. Its loss function is based on a proper score, the Continuous Ranked Probability Score (CRPS). For the loss, the almost fair CRPS is introduced because it approximately removes the bias in the score due to finite ensemble size yet avoids a degeneracy of the fair CRPS. The trained model is stochastic and can generate as many exchangeable members as desired and computationally feasible in inference. For medium-range forecasts AIFS-CRPS outperforms the physics-based Integrated Forecasting System (IFS) ensemble for the majority of variables and lead times. For subseasonal forecasts, AIFS-CRPS outperforms the IFS ensemble before calibration and is competitive with the IFS ensemble when forecasts are evaluated as anomalies to remove the influence of model biases. more
-
GraphDOP: Towards skilful data-driven medium-range weather forecasts learnt and initialised directly from observations¶
We introduce GraphDOP, a new data-driven, end-to-end forecast system developed at the European Centre for Medium-Range Weather Forecasts (ECMWF) that is trained and initialised exclusively from Earth...We introduce GraphDOP, a new data-driven, end-to-end forecast system developed at the European Centre for Medium-Range Weather Forecasts (ECMWF) that is trained and initialised exclusively from Earth System observations, with no physics-based (re)analysis inputs or feedbacks. GraphDOP learns the correlations between observed quantities - such as brightness temperatures from polar orbiters and geostationary satellites - and geophysical quantities of interest (that are measured by conventional observations), to form a coherent latent representation of Earth System state dynamics and physical processes, and is capable of producing skilful predictions of relevant weather parameters up to five days into the future. more
-
ArchesWeather & ArchesWeatherGen: a deterministic and generative model for efficient ML weather forecasting¶
Weather forecasting plays a vital role in today's society, from agriculture and logistics to predicting the output of renewable energies, and preparing for extreme weather events. Deep learning...Weather forecasting plays a vital role in today's society, from agriculture and logistics to predicting the output of renewable energies, and preparing for extreme weather events. Deep learning weather forecasting models trained with the next state prediction objective on ERA5 have shown great success compared to numerical global circulation models. However, for a wide range of applications, being able to provide representative samples from the distribution of possible future weather states is critical. In this paper, we propose a methodology to leverage deterministic weather models in the design of probabilistic weather models, leading to improved performance and reduced computing costs. We first introduce ArchesWeather, a transformer-based deterministic model that improves upon Pangu-Weather by removing overrestrictive inductive priors. We then design a probabilistic weather model called ArchesWeatherGen based on flow matching, a modern variant of diffusion models, that is trained to project ArchesWeather's predictions to the distribution of ERA5 weather states. ArchesWeatherGen is a true stochastic emulator of ERA5 and surpasses IFS ENS and NeuralGCM on all WeatherBench headline variables (except for NeuralGCM's geopotential). Our work also aims to democratize the use of deterministic and generative machine learning models in weather forecasting research, with academic computing resources. All models are trained at 1.5° resolution, with a training budget of \(\sim\)9 V100 days for ArchesWeather and \(\sim\)45 V100 days for ArchesWeatherGen. For inference, ArchesWeatherGen generates 15-day weather trajectories at a rate of 1 minute per ensemble member on a A100 GPU card. To make our work fully reproducible, our code and models are open source, including the complete pipeline for data preparation, training, and evaluation, at https://github.com/INRIA/geoarches . more
-
Metastability, atmospheric midlatitude circulation regimes and large-scale teleconnection: a data-driven approach¶
The low-frequency variability of the mid-latitude atmosphere involves complex nonlinear and chaotic dynamical processes posing predictability challenges. It is characterized by sporadically...The low-frequency variability of the mid-latitude atmosphere involves complex nonlinear and chaotic dynamical processes posing predictability challenges. It is characterized by sporadically recurring, often long-lived patterns of atmospheric circulation of hemispheric scale known as weather regimes. The evolution of these circulation regimes in addition to their link to large-scale teleconnections can help extend the limits of atmospheric predictability. They also play a key role in sub- and inter-seasonal weather forecasting. Their identification and modeling remains an issue, however, due to their intricacy, including a clear conceptual picture. In recent years, the concept of metastability has been developed to explain regimes formation. This suggests an interpretation of circulation regimes as communities of states in which the atmospheric system remains in their neighborhood for abnormally longer than typical baroclinic timescales. Here we develop a new and effective method to identify such communities by constructing and analyzing an operator of the system's evolution via hidden Markov model (HMM). The method makes use of graph theory and is based on probabilistic approach to partition the HMM transition matrix into weakly interacting blocks -- communities of hidden states -- associated with regimes. The approach involves nonlinear kernel principal component mapping to consistently embed the system state space for HMM building. Application to northern winter hemisphere using geopotential heights from reanalysis yields four persistent and recurrent circulation regimes. Statistical and dynamical characteristics of these circulation regimes and surface impacts are discussed. In particular, unexpected high correlations are obtained with EL-Nino Southern Oscillation and Pacific decadal oscillation with lead times of up to one year. more
-
Jacobian-Enforced Neural Networks (JENN) for Improved Data Assimilation Consistency in Dynamical Models¶
Machine learning-based weather models have shown great promise in producing accurate forecasts but have struggled when applied to data assimilation tasks, unlike traditional numerical weather...Machine learning-based weather models have shown great promise in producing accurate forecasts but have struggled when applied to data assimilation tasks, unlike traditional numerical weather prediction (NWP) models. This study introduces the Jacobian-Enforced Neural Network (JENN) framework, designed to enhance DA consistency in neural network (NN)-emulated dynamical systems. Using the Lorenz 96 model as an example, the approach demonstrates improved applicability of NNs in DA through explicit enforcement of Jacobian relationships. The NN architecture includes an input layer of 40 neurons, two hidden layers with 256 units each employing hyperbolic tangent activation functions, and an output layer of 40 neurons without activation. The JENN framework employs a two-step training process: an initial phase using standard prediction-label pairs to establish baseline forecast capability, followed by a secondary phase incorporating a customized loss function to enforce accurate Jacobian relationships. This loss function combines root mean square error (RMSE) between predicted and true state values with additional RMSE terms for tangent linear (TL) and adjoint (AD) emulation results, weighted to balance forecast accuracy and Jacobian sensitivity. To ensure consistency, the secondary training phase uses additional pairs of TL/AD inputs and labels calculated from the physical models. Notably, this approach does not require starting from scratch or structural modifications to the NN, making it readily applicable to pretrained models such as GraphCast, NeuralGCM, Pangu, or FuXi, facilitating their adaptation for DA tasks with minimal reconfiguration. Experimental results demonstrate that the JENN framework preserves nonlinear forecast performance while significantly reducing noise in the TL and AD components, as well as in the overall Jacobian matrix. more
-
Smoothing and spatial verification of global fields¶
Forecast verification plays a crucial role in the development cycle of operational numerical weather prediction models. At the same time, verification remains a challenge as the traditionally used...Forecast verification plays a crucial role in the development cycle of operational numerical weather prediction models. At the same time, verification remains a challenge as the traditionally used non-spatial forecast quality metrics exhibit certain drawbacks, with new spatial metrics being developed to address these problems. Some of these new metrics are based on smoothing, with one example being the widely used Fraction Skill Score (FSS) and its many derivatives. However, while the FSS has been used by many researchers in limited area domains, there are no examples of it being used in a global domain yet. The issue is due to the increased computational complexity of smoothing in a global domain, with its inherent spherical geometry and non-equidistant and/or irregular grids. At the same time, there clearly exists a need for spatial metrics that could be used in the global domain as the operational global models continue to be developed and improved, along with the new machine-learning-based models. Here, we present two new methodologies for smoothing in a global domain that are potentially fast enough to make the smoothing of high-resolution global fields feasible. Both approaches also consider the variability of grid point area sizes and can handle missing data appropriately. This, in turn, makes the calculation of smoothing-based metrics, such as FSS and its derivatives, in a global domain possible, which we demonstrate by evaluating the performance of operational high-resolution global precipitation forecasts provided by the European Centre for Medium-Range Weather Forecasts. more
-
Exploring the Use of Machine Learning Weather Models in Data Assimilation¶
The use of machine learning (ML) models in meteorology has attracted significant attention for their potential to improve weather forecasting efficiency and accuracy. GraphCast and NeuralGCM, two...The use of machine learning (ML) models in meteorology has attracted significant attention for their potential to improve weather forecasting efficiency and accuracy. GraphCast and NeuralGCM, two promising ML-based weather models, are at the forefront of this innovation. However, their suitability for data assimilation (DA) systems, particularly for four-dimensional variational (4DVar) DA, remains under-explored. This study evaluates the tangent linear (TL) and adjoint (AD) models of both GraphCast and NeuralGCM to assess their viability for integration into a DA framework. We compare the TL/AD results of GraphCast and NeuralGCM with those of the Model for Prediction Across Scales - Atmosphere (MPAS-A), a well-established numerical weather prediction (NWP) model. The comparison focuses on the physical consistency and reliability of TL/AD responses to perturbations. While the adjoint results of both GraphCast and NeuralGCM show some similarity to those of MPAS-A, they also exhibit unphysical noise at various vertical levels, raising concerns about their robustness for operational DA systems. The implications of this study extend beyond 4DVar applications. Unphysical behavior and noise in ML-derived TL/AD models could lead to inaccurate error covariances and unreliable ensemble forecasts, potentially degrading the overall performance of ensemble-based DA systems, as well. Addressing these challenges is critical to ensuring that ML models, such as GraphCast and NeuralGCM, can be effectively integrated into operational DA systems, paving the way for more accurate and efficient weather predictions. more