Global Models¶
-
Benchmarking atmospheric circulation variability in an AI emulator, ACE2, and a hybrid model, NeuralGCM¶
Physics-based atmosphere-land models with prescribed sea surface temperature have notable successes but also biases in their ability to represent atmospheric variability compared to observations....Physics-based atmosphere-land models with prescribed sea surface temperature have notable successes but also biases in their ability to represent atmospheric variability compared to observations. Recently, AI emulators and hybrid models have emerged with the potential to overcome these biases, but still require systematic evaluation against metrics grounded in fundamental atmospheric dynamics. Here, we evaluate the representation of four atmospheric variability benchmarking metrics in a fully data-driven AI emulator (ACE2-ERA5) and hybrid model (NeuralGCM). The hybrid model and emulator can capture the spectra of large-scale tropical waves and extratropical eddy-mean flow interactions, including critical levels. However, both struggle to capture the timescales associated with quasi-biennial oscillation (QBO, \(\sim 28\) months) and Southern annular mode propagation (\(\sim 150\) days). These dynamical metrics serve as an initial benchmarking tool to inform AI model development and understand their limitations, which may be essential for out-of-distribution applications (e.g., extrapolating to unseen climates). more
-
Zephyrus: An Agentic Framework for Weather Science¶
Foundation models for weather science are pre-trained on vast amounts of structured numerical data and outperform traditional weather forecasting systems. However, these models lack language-based...Foundation models for weather science are pre-trained on vast amounts of structured numerical data and outperform traditional weather forecasting systems. However, these models lack language-based reasoning capabilities, limiting their utility in interactive scientific workflows. Large language models (LLMs) excel at understanding and generating text but cannot reason about high-dimensional meteorological datasets. We bridge this gap by building the first agentic framework for weather science. Our framework includes a Python code-based environment for agents (ZephyrusWorld) to interact with weather data, featuring tools including a WeatherBench 2 dataset indexer, geolocator for geocoding from natural language, weather forecasting, climate simulation capabilities, and a climatology module for querying precomputed climatological statistics (e.g., means, extremes, and quantiles) across multiple timescales. We design Zephyrus, a multi-turn LLM-based weather agent that iteratively analyzes weather datasets, observes results, and refines its approach through conversational feedback loops. We accompany the agent with a new benchmark, ZephyrusBench, with a scalable data generation pipeline that constructs diverse question-answer pairs across weather-related tasks, from basic lookups to advanced forecasting, extreme event detection, and counterfactual reasoning. Experiments on this benchmark demonstrate the strong performance of Zephyrus agents over text-only baselines, outperforming them by up to 44 percentage points in correctness. However, the hard tasks are still difficult even with frontier LLMs, highlighting the challenging nature of our benchmark and suggesting room for future development. Our codebase and benchmark are available at https://github.com/Rose-STL-Lab/Zephyrus. more
-
Deep learning the sources of MJO predictability: a spectral view of learned features¶
The Madden-Julian oscillation (MJO) is a planetary-scale, intraseasonal tropical rainfall phenomenon crucial for global weather and climate; however, its dynamics and predictability remain poorly...The Madden-Julian oscillation (MJO) is a planetary-scale, intraseasonal tropical rainfall phenomenon crucial for global weather and climate; however, its dynamics and predictability remain poorly understood. Here, we leverage deep learning (DL) to investigate the sources of MJO predictability, motivated by a central difference in MJO theories: which spatial scales are essential for driving the MJO? We first develop a deep convolutional neural network (DCNN) to forecast the MJO indices (RMM and ROMI). Our model predicts RMM and ROMI up to 21 and 33 days, respectively, achieving skills comparable to leading subseasonal-to-seasonal models such as NCEP. To identify the spatial scales most relevant for MJO forecasting, we conduct spectral analysis of the latent feature space and find that large-scale patterns dominate the learned signals. Additional experiments show that models using only large-scale signals as the input have the same skills as those using all the scales, supporting the large-scale view of the MJO. Meanwhile, we find that small-scale signals remain informative: surprisingly, models using only small-scale input can still produce skillful forecasts up to 1-2 weeks ahead. We show that this is achieved by reconstructing the large-scale envelope of the small-scale activities, which aligns with the multi-scale view of the MJO. Altogether, our findings support that large-scale patterns--whether directly included or reconstructed--may be the primary source of MJO predictability. more
-
The Equilibrium Response of Atmospheric Machine-Learning Models to Uniform Sea Surface Temperature Warming¶
Machine learning models for the global atmosphere that are capable of producing stable, multi-year simulations of Earth's climate have recently been developed. However, the ability of these ML models...Machine learning models for the global atmosphere that are capable of producing stable, multi-year simulations of Earth's climate have recently been developed. However, the ability of these ML models to generalize beyond the training distribution remains an open question. In this study, we evaluate the climate response of several state-of-the-art ML models (ACE2-ERA5, NeuralGCM, and cBottle) to a uniform sea surface temperature warming, a widely used benchmark for evaluating climate change. We assess each ML model's performance relative to a physics-based general circulation model (NOAA's Geophysical Fluid Dynamics Laboratory AM4) across key diagnostics, including surface air temperature, precipitation, temperature and wind profiles, and top-of-atmosphere radiation. While the ML models reproduce key aspects of the physical model response, particularly the response of precipitation, some exhibit notable departures from robust physical responses, including radiative responses and land region warming. Our results highlight the promise and current limitations of ML models for climate change applications and suggest that further improvements are needed for robust out-of-sample generalization. more
-
Multidata Causal Discovery for Statistical Hurricane Intensity Forecasting¶
Improving statistical forecasts of tropical cyclone (TC) intensity is limited by complex nonlinear interactions and difficulty in identifying relevant predictors. Conventional methods prioritize...Improving statistical forecasts of tropical cyclone (TC) intensity is limited by complex nonlinear interactions and difficulty in identifying relevant predictors. Conventional methods prioritize correlation or fit, often overlooking confounding variables and limiting generalizability to unseen TCs. To address this, we leverage a multidata causal discovery framework with a replicated dataset based on Statistical Hurricane Intensity Prediction Scheme (SHIPS) using ERA5 meteorological reanalysis. We conduct experiments to identify and select predictors causally linked to TC intensity changes. We then train multiple linear regression models to compare causal feature selection with correlation, random forest feature importance, and no feature selection, across five forecast lead times from 1 to 5 days (24 to 120 hours). Causal feature selection consistently outperforms on unseen test cases, especially for lead times shorter than 3 days. Top causal features include vertical shear, mid-tropospheric potential vorticity and surface moisture conditions, which are physically significant yet often underutilized in TC intensity predictions. We build an extended predictor set (SHIPS+) by adding selected features to the standard SHIPS predictors. SHIPS+ yields increased short-term predictive skill at lead times of 24, 48, and 72 hours. Adding nonlinearity using a multilayer perceptron further extends skill to longer lead times, despite our framework being purely regional and not requiring global forecast data. Operational SHIPS tests confirm that three of the six added causally discovered predictors improve forecast skill, with the largest gains at longer lead times. Our results demonstrate that causal discovery improves TC intensity prediction and pave the way toward more empirical forecasts. more
-
Swift: An Autoregressive Consistency Model for Efficient Weather Forecasting¶
Diffusion models offer a physically grounded framework for probabilistic weather forecasting, but their typical reliance on slow, iterative solvers during inference makes them impractical for...Diffusion models offer a physically grounded framework for probabilistic weather forecasting, but their typical reliance on slow, iterative solvers during inference makes them impractical for subseasonal-to-seasonal (S2S) applications where long lead-times and domain-driven calibration are essential. To address this, we introduce Swift, a single-step consistency model that, for the first time, enables autoregressive finetuning of a probability flow model with a continuous ranked probability score (CRPS) objective. This eliminates the need for multi-model ensembling or parameter perturbations. Results show that Swift produces skillful 6-hourly forecasts that remain stable for up to 75 days, running \(39\times\) faster than state-of-the-art diffusion baselines while achieving forecast skill competitive with the numerical-based, operational IFS ENS. This marks a step toward efficient and reliable ensemble forecasting from medium-range to seasonal-scales. more
-
A Weather Foundation Model for the Power Grid¶
Weather foundation models (WFMs) have recently set new benchmarks in global forecast skill, yet their concrete value for the weather-sensitive infrastructure that powers modern society remains...Weather foundation models (WFMs) have recently set new benchmarks in global forecast skill, yet their concrete value for the weather-sensitive infrastructure that powers modern society remains largely unexplored. In this study, we fine-tune Silurian AI's 1.5B-parameter WFM, Generative Forecasting Transformer (GFT), on a rich archive of Hydro-Québec asset observations--including transmission-line weather stations, wind-farm met-mast streams, and icing sensors--to deliver hyper-local, asset-level forecasts for five grid-critical variables: surface temperature, precipitation, hub-height wind speed, wind-turbine icing risk, and rime-ice accretion on overhead conductors. Across 6-72 h lead times, the tailored model surpasses state-of-the-art NWP benchmarks, trimming temperature mean absolute error (MAE) by 15%, total-precipitation MAE by 35%, and lowering wind speed MAE by 15%. Most importantly, it attains an average precision score of 0.72 for day-ahead rime-ice detection, a capability absent from existing operational systems, which affords several hours of actionable warning for potentially catastrophic outage events. These results show that WFMs, when post-trained with small amounts of high-fidelity, can serve as a practical foundation for next-generation grid-resilience intelligence. more
-
DPSformer: A long-tail-aware model for improving heavy rainfall prediction¶
Accurate and timely forecasting of heavy rainfall remains a critical challenge for modern society. Precipitation exhibits a highly imbalanced distribution: most observations record no or light rain,...Accurate and timely forecasting of heavy rainfall remains a critical challenge for modern society. Precipitation exhibits a highly imbalanced distribution: most observations record no or light rain, while heavy rainfall events are rare. Such an imbalanced distribution obstructs deep learning models from effectively predicting heavy rainfall events. To address this challenge, we treat rainfall forecasting explicitly as a long-tailed learning problem, identifying the insufficient representation of heavy rainfall events as the primary barrier to forecasting accuracy. Therefore, we introduce DPSformer, a long-tail-aware model that enriches representation of heavy rainfall events through a high-resolution branch. For heavy rainfall events $ \geq $ 50 mm/6 h, DPSformer lifts the Critical Success Index (CSI) of a baseline Numerical Weather Prediction (NWP) model from 0.012 to 0.067. For the top 1% coverage of heavy rainfall events, its Fraction Skill Score (FSS) exceeds 0.45, surpassing existing methods. Our work establishes an effective long-tailed paradigm for heavy rainfall prediction, offering a practical tool to enhance early warning systems and mitigate the societal impacts of extreme weather events. more
-
Evaluation of Machine and Deep Learning Techniques for Cyclone Trajectory Regression and Status Classification by Time Series Data¶
Accurate cyclone forecasting is essential for minimizing loss of life, infrastructure damage, and economic disruption. Traditional numerical weather prediction models, though effective, are...Accurate cyclone forecasting is essential for minimizing loss of life, infrastructure damage, and economic disruption. Traditional numerical weather prediction models, though effective, are computationally intensive and prone to error due to the chaotic nature of atmospheric systems. This study proposes a machine learning (ML) approach to forecasting tropical cyclone trajectory and status using time series data from the National Hurricane Center, including recently added best track wind radii. A two-stage ML pipeline is developed: a regression model first predicts cyclone features maximum wind speed, minimum pressure, trajectory length, and directional change using a sliding window of historical data. These outputs are then input into classification models to predict the cyclone's categorical status. Gradient boosting regression and three classifiers random forest (RF), support vector machine (SVM), and multilayer perceptron (MLP) are evaluated. After hyperparameter tuning and synthetic minority oversampling (SMOTE), the RF classifier achieves the highest performance with 93% accuracy, outperforming SVM and MLP across precision, recall, and F1 score. The RF model is particularly robust in identifying minority cyclone statuses and minimizing false negatives. Regression results yield low mean absolute errors, with pressure and wind predictions within about 2.2 mb and 2.4 kt, respectively. These findings demonstrate that ML models, especially ensemble-based classifiers, offer an effective, scalable alternative to traditional forecasting methods, with potential for real-time cyclone prediction and integration into decision support systems. more
-
Forecasting the Future with Yesterday's Climate: Temperature Bias in AI Weather and Climate Models¶
AI-based climate and weather models have rapidly gained popularity, providing faster forecasts with skill that can match or even surpass that of traditional dynamical models. Despite this success,...AI-based climate and weather models have rapidly gained popularity, providing faster forecasts with skill that can match or even surpass that of traditional dynamical models. Despite this success, these models face a key challenge: predicting future climates while being trained only with historical data. In this study, we investigate this issue by analyzing boreal winter land temperature biases in AI weather and climate models. We examine two weather models, FourCastNet V2 Small (FourCastNet) and Pangu Weather (Pangu), evaluating their predictions for 2020-2025 and Ai2 Climate Emulator version 2 (ACE2) for 1996-2010. These time periods lie outside of the respective models' training sets and are significantly more recent than the bulk of their training data, allowing us to assess how well the models generalize to new, i.e. more modern, conditions. We find that all three models produce cold-biased mean temperatures, resembling climates from 15-20 years earlier than the period they are predicting. In some regions, like the Eastern U.S., the predictions resemble climates from as much as 20-30 years earlier. Further analysis shows that FourCastNet's and Pangu's cold bias is strongest in the hottest predicted temperatures, indicating limited training exposure to modern extreme heat events. In contrast, ACE2's bias is more evenly distributed but largest in regions, seasons, and parts of the temperature distribution where climate change has been most pronounced. These findings underscore the challenge of training AI models exclusively on historical data and highlight the need to account for such biases when applying them to future climate prediction. more
-
Task-Adaptive Parameter-Efficient Fine-Tuning for Weather Foundation Models¶
While recent advances in machine learning have equipped Weather Foundation Models (WFMs) with substantial generalization capabilities across diverse downstream tasks, the escalating computational...While recent advances in machine learning have equipped Weather Foundation Models (WFMs) with substantial generalization capabilities across diverse downstream tasks, the escalating computational requirements associated with their expanding scale increasingly hinder practical deployment. Current Parameter-Efficient Fine-Tuning (PEFT) methods, designed for vision or language tasks, fail to address the unique challenges of weather downstream tasks, such as variable heterogeneity, resolution diversity, and spatiotemporal coverage variations, leading to suboptimal performance when applied to WFMs. To bridge this gap, we introduce WeatherPEFT, a novel PEFT framework for WFMs incorporating two synergistic innovations. First, during the forward pass, Task-Adaptive Dynamic Prompting (TADP) dynamically injects the embedding weights within the encoder to the input tokens of the pre-trained backbone via internal and external pattern extraction, enabling context-aware feature recalibration for specific downstream tasks. Furthermore, during backpropagation, Stochastic Fisher-Guided Adaptive Selection (SFAS) not only leverages Fisher information to identify and update the most task-critical parameters, thereby preserving invariant pre-trained knowledge, but also introduces randomness to stabilize the selection. We demonstrate the effectiveness and efficiency of WeatherPEFT on three downstream tasks, where existing PEFT methods show significant gaps versus Full-Tuning, and WeatherPEFT achieves performance parity with Full-Tuning using fewer trainable parameters. The code of this work is available at https://github.com/ShileiCao/WeatherPEFT. more
-
Accurate typhoon intensity forecasts using a non-iterative spatiotemporal transformer model¶
Accurate forecasting of tropical cyclone (TC) intensity - particularly during periods of rapid intensification and rapid weakening - remains a challenge for operational meteorology, with high-stakes...Accurate forecasting of tropical cyclone (TC) intensity - particularly during periods of rapid intensification and rapid weakening - remains a challenge for operational meteorology, with high-stakes implications for disaster preparedness and infrastructure resilience. Recent advances in machine learning have yielded notable progress in TC prediction; however, most existing systems provide forecasts that degrade rapidly in extreme regimes and lack long-range consistency. Here we introduce TIFNet, a transformer-based forecasting model that generates non-iterative, 5-day intensity trajectories by integrating high-resolution global forecasts with a historical-evolution fusion mechanism. Trained on reanalysis data and fine-tuned with operational data, TIFNet consistently outperforms operational numerical models across all forecast horizons, delivering robust improvements across weak, strong, and super typhoon categories. In rapid intensity change regimes - long regarded as the most difficult to forecast - TIFNet reduces forecast error by 29-43% relative to current operational baselines. These results represent a substantial advance in artificial-intelligence-based TC intensity forecasting, especially under extreme conditions where traditional models consistently underperform. more
-
Mesh Interpolation Graph Network for Dynamic and Spatially Irregular Global Weather Forecasting¶
Graph neural networks have shown promising results in weather forecasting, which is critical for human activity such as agriculture planning and extreme weather preparation. However, most studies...Graph neural networks have shown promising results in weather forecasting, which is critical for human activity such as agriculture planning and extreme weather preparation. However, most studies focus on finite and local areas for training, overlooking the influence of broader areas and limiting their ability to generalize effectively. Thus, in this work, we study global weather forecasting that is irregularly distributed and dynamically varying in practice, requiring the model to generalize to unobserved locations. To address such challenges, we propose a general Mesh Interpolation Graph Network (MIGN) that models the irregular weather station forecasting, consisting of two key designs: (1) learning spatially irregular data with regular mesh interpolation network to align the data; (2) leveraging parametric spherical harmonics location embedding to further enhance spatial generalization ability. Extensive experiments on an up-to-date observation dataset show that MIGN significantly outperforms existing data-driven models. Besides, we show that MIGN has spatial generalization ability, and is capable of generalizing to previous unseen stations. more
-
S\(^2\)Transformer: Scalable Structured Transformers for Global Station Weather Forecasting¶
Global Station Weather Forecasting (GSWF) is a key meteorological research area, critical to energy, aviation, and agriculture. Existing time series forecasting methods often ignore or...Global Station Weather Forecasting (GSWF) is a key meteorological research area, critical to energy, aviation, and agriculture. Existing time series forecasting methods often ignore or unidirectionally model spatial correlation when conducting large-scale global station forecasting. This contradicts the intrinsic nature underlying observations of the global weather system, limiting forecast performance. To address this, we propose a novel Spatial Structured Attention Block in this paper. It partitions the spatial graph into a set of subgraphs and instantiates Intra-subgraph Attention to learn local spatial correlation within each subgraph, and aggregates nodes into subgraph representations for message passing among the subgraphs via Inter-subgraph Attention -- considering both spatial proximity and global correlation. Building on this block, we develop a multiscale spatiotemporal forecasting model S\(^2\)Transformer by progressively expanding subgraph scales. The resulting model is both scalable and able to produce structured spatial correlation, and meanwhile, it is easy to implement. The experimental results show that it can achieve performance improvements up to 16.8% over time series forecasting baselines at low running costs. more
-
Graph-based Neural Space Weather Forecasting¶
Accurate space weather forecasting is crucial for protecting our increasingly digital infrastructure. Hybrid-Vlasov models, like Vlasiator, offer physical realism beyond that of current operational...Accurate space weather forecasting is crucial for protecting our increasingly digital infrastructure. Hybrid-Vlasov models, like Vlasiator, offer physical realism beyond that of current operational systems, but are too computationally expensive for real-time use. We introduce a graph-based neural emulator trained on Vlasiator data to autoregressively predict near-Earth space conditions driven by an upstream solar wind. We show how to achieve both fast deterministic forecasts and, by using a generative model, produce ensembles to capture forecast uncertainty. This work demonstrates that machine learning offers a way to add uncertainty quantification capability to existing space weather prediction systems, and make hybrid-Vlasov simulation tractable for operational use. more
-
An update to ECMWF's machine-learned weather forecast model AIFS¶
We present an update to ECMWF's machine-learned weather forecasting model AIFS Single with several key improvements. The model now incorporates physical consistency constraints through bounding...We present an update to ECMWF's machine-learned weather forecasting model AIFS Single with several key improvements. The model now incorporates physical consistency constraints through bounding layers, an updated training schedule, and an expanded set of variables. The physical constraints substantially improve precipitation forecasts and the new variables show a high level of skill. Upper-air headline scores also show improvement over the previous AIFS version. The AIFS has been fully operational at ECMWF since the 25th of February 2025. more
-
Training-Free Data Assimilation with GenCast¶
Data assimilation is widely used in many disciplines such as meteorology, oceanography, and robotics to estimate the state of a dynamical system from noisy observations. In this work, we propose a...Data assimilation is widely used in many disciplines such as meteorology, oceanography, and robotics to estimate the state of a dynamical system from noisy observations. In this work, we propose a lightweight and general method to perform data assimilation using diffusion models pre-trained for emulating dynamical systems. Our method builds on particle filters, a class of data assimilation algorithms, and does not require any further training. As a guiding example throughout this work, we illustrate our methodology on GenCast, a diffusion-based model that generates global ensemble weather forecasts. more
-
Technical overview and architecture of the FastNet Machine Learning weather prediction model, version 1.0¶
We present FastNet version 1.0, a data-driven medium range numerical weather prediction (NWP) model based on a Graph Neural Network architecture, developed jointly between the Alan Turing Institute...We present FastNet version 1.0, a data-driven medium range numerical weather prediction (NWP) model based on a Graph Neural Network architecture, developed jointly between the Alan Turing Institute and the Met Office. FastNet uses an encode-process-decode structure to produce deterministic global weather predictions out to 10 days. The architecture is independent of spatial resolution and we have trained models at 1\(^{\circ}\) and 0.25\(^{\circ}\) resolution, with a six hour time step. FastNet uses a multi-level mesh in the processor, which is able to capture both short-range and long-range patterns in the spatial structure of the atmosphere. The model is pre-trained on ECMWF's ERA5 reanalysis data and then fine-tuned on additional autoregressive rollout steps, which improves accuracy over longer time horizons. We evaluate the model performance at 1.5\(^{\circ}\) resolution using 2022 as a hold-out year and compare with the Met Office Global Model, finding that FastNet surpasses the skill of the current Met Office Global Model NWP system using a variety of evaluation metrics on a number of atmospheric variables. Our results show that both our 1\(^{\circ}\) and 0.25\(^{\circ}\) FastNet models outperform the current Global Model and produce results with predictive skill approaching those of other data-driven models trained on 0.25\(^{\circ}\) ERA5. more
-
FastNet: Improving the physical consistency of machine-learning weather prediction models through loss function design¶
Machine learning weather prediction (MLWP) models have demonstrated remarkable potential in delivering accurate forecasts at significantly reduced computational cost compared to traditional numerical...Machine learning weather prediction (MLWP) models have demonstrated remarkable potential in delivering accurate forecasts at significantly reduced computational cost compared to traditional numerical weather prediction (NWP) systems. However, challenges remain in ensuring the physical consistency of MLWP outputs, particularly in deterministic settings. This study presents FastNet, a graph neural network (GNN)-based global prediction model, and investigates the impact of alternative loss function designs on improving the physical realism of its forecasts. We explore three key modifications to the standard mean squared error (MSE) loss: (1) a modified spherical harmonic (MSH) loss that penalises spectral amplitude errors to reduce blurring and enhance small-scale structure retention; (2) inclusion of horizontal gradient terms in the loss to suppress non-physical artefacts; and (3) an alternative wind representation that decouples speed and direction to better capture extreme wind events. Results show that while the MSH and gradient-based losses alone may slightly degrade RMSE scores, when trained in combination the model exhibits very similar MSE performance to an MSE-trained model while at the same time significantly improving spectral fidelity and physical consistency. The alternative wind representation further improves wind speed accuracy and reduces directional bias. Collectively, these findings highlight the importance of loss function design as a mechanism for embedding domain knowledge into MLWP models and advancing their operational readiness. more
-
FlowCast-ODE: Continuous Hourly Weather Forecasting with Dynamic Flow Matching and ODE Integration¶
Accurate hourly weather forecasting is critical for numerous applications. Recent deep learning models have demonstrated strong capability on 6-hour intervals, yet achieving accurate and stable...Accurate hourly weather forecasting is critical for numerous applications. Recent deep learning models have demonstrated strong capability on 6-hour intervals, yet achieving accurate and stable hourly predictions remains a critical challenge. This is primarily due to the rapid accumulation of errors in autoregressive rollouts and temporal discontinuities within the ERA5 data's 12-hour assimilation cycle. To address these issues, we propose FlowCast-ODE, a framework that models atmospheric state evolution as a continuous flow. FlowCast-ODE learns the conditional flow path directly from the previous state, an approach that aligns more naturally with physical dynamic systems and enables efficient computation. A coarse-to-fine strategy is introduced to train the model on 6-hour data using dynamic flow matching and then refined on hourly data that incorporates an Ordinary Differential Equation (ODE) solver to achieve temporally coherent forecasts. In addition, a lightweight low-rank AdaLN-Zero modulation mechanism is proposed and reduces model size by 15% without compromising accuracy. Experiments demonstrate that FlowCast-ODE outperforms strong baselines, yielding lower root mean square error (RMSE) and better energy conservation, which reduces blurring and preserves more fine-scale spatial details. It also shows comparable performance to the state-of-the-art model in forecasting extreme events like typhoons. Furthermore, the model alleviates temporal discontinuities associated with assimilation cycle transitions. more
-
Data-Efficient Ensemble Weather Forecasting with Diffusion Models¶
Although numerical weather forecasting methods have dominated the field, recent advances in deep learning methods, such as diffusion models, have shown promise in ensemble weather forecasting....Although numerical weather forecasting methods have dominated the field, recent advances in deep learning methods, such as diffusion models, have shown promise in ensemble weather forecasting. However, such models are typically autoregressive and are thus computationally expensive. This is a challenge in climate science, where data can be limited, costly, or difficult to work with. In this work, we explore the impact of curated data selection on these autoregressive diffusion models. We evaluate several data sampling strategies and show that a simple time stratified sampling approach achieves performance similar to or better than full-data training. Notably, it outperforms the full-data model on certain metrics and performs only slightly worse on others while using only 20% of the training data. Our results demonstrate the feasibility of data-efficient diffusion training, especially for weather forecasting, and motivates future work on adaptive or model-aware sampling methods that go beyond random or purely temporal sampling. more
-
How does an AI Weather Model Learn to Forecast Extreme Weather?¶
In a warming climate with more frequent severe weather, artificial intelligence (AI) weather models have the potential to provide cheaper, faster, and more accurate forecasts of high-impact weather...In a warming climate with more frequent severe weather, artificial intelligence (AI) weather models have the potential to provide cheaper, faster, and more accurate forecasts of high-impact weather events. To realize this potential, there is a need for more research on how models learn extreme events and how that learning might be improved. We investigate how a spherical Fourier neural operator model (SFNO) learns extreme weather by saving every checkpoint throughout training and analyzing a collection of 9 extreme weather events including heatwaves, atmospheric rivers, and tropical cyclones. The SFNO learns heatwaves similarly to other weather days, but we find evidence that the model learns information about atmospheric river and tropical cyclone forecasts that it loses later in training. We propose a possible training strategy to improve the forecasting of extreme events by retaining information from earlier training checkpoints, and provide initial evidence of its utility. more
-
MoWE : A Mixture of Weather Experts¶
Data-driven weather models have recently achieved state-of-the-art performance, yet progress has plateaued in recent years. This paper introduces a Mixture of Experts (MoWE) approach as a novel...Data-driven weather models have recently achieved state-of-the-art performance, yet progress has plateaued in recent years. This paper introduces a Mixture of Experts (MoWE) approach as a novel paradigm to overcome these limitations, not by creating a new forecaster, but by optimally combining the outputs of existing models. The MoWE model is trained with significantly lower computational resources than the individual experts. Our model employs a Vision Transformer-based gating network that dynamically learns to weight the contributions of multiple "expert" models at each grid point, conditioned on forecast lead time. This approach creates a synthesized deterministic forecast that is more accurate than any individual component in terms of Root Mean Squared Error (RMSE). Our results demonstrate the effectiveness of this method, achieving up to a 10% lower RMSE than the best-performing AI weather model on a 2-day forecast horizon, significantly outperforming individual experts as well as a simple average across experts. This work presents a computationally efficient and scalable strategy to push the state of the art in data-driven weather prediction by making the most out of leading high-quality forecast models. more
-
Seasonal forecasting using the GenCast probabilistic machine learning model¶
Machine-learnt weather prediction (MLWP) models are now well established as being competitive with conventional numerical weather prediction (NWP) models in the medium range. However, there is still...Machine-learnt weather prediction (MLWP) models are now well established as being competitive with conventional numerical weather prediction (NWP) models in the medium range. However, there is still much uncertainty as to how this performance extends to longer timescales, where interactions with slower components of the earth system become important. We take GenCast, a state-of-the-art probabilistic MLWP model, and apply it to the task of seasonal forecasting with prescribed sea surface temperature (SST), by providing anomalies persisted over climatology (GenCast-Persisted) or forcing with observations (GenCast-Forced). The forecasts are compared to the European Centre for Medium-Range Weather Forecasts seasonal forecasting system, SEAS5. Our results indicate that, despite being trained at short timescales, GenCast-Persisted produces much of the correct precipitation patterns in response to El Niño and La Niña events, with several erroneous patterns in GenCast-Persisted corrected with GenCast-Forced. The uncertainty in precipitation response, as represented by the ensemble, compares favourably to SEAS5. Whilst SEAS5 achieves superior skill in the tropics for 2-metre temperature and mean sea level pressure (MSLP), GenCast-Persisted achieves significantly higher skill in some areas in higher latitudes, including mountainous areas, with notable improvements for MSLP in particular; this is reflected in a higher correlation with the observed NAO index. Reliability diagrams indicate that GenCast-Persisted is overconfident compared to SEAS5, whilst GenCast-Forced produces well-calibrated seasonal 2-metre temperature predictions. These results provide an indication of the potential of MLWP models similar to GenCast for the ‘full’ seasonal forecasting problem, where the atmospheric model is coupled to ocean, land and cryosphere models. more
-
Distillation of CNN Ensemble Results for Enhanced Long-Term Prediction of the ENSO Phenomenon¶
The accurate long-term forecasting of the El Nino Southern Oscillation (ENSO) is still one of the biggest challenges in climate science. While it is true that short-to medium-range performance has...The accurate long-term forecasting of the El Nino Southern Oscillation (ENSO) is still one of the biggest challenges in climate science. While it is true that short-to medium-range performance has been improved significantly using the advances in deep learning, statistical dynamical hybrids, most operational systems still use the simple mean of all ensemble members, implicitly assuming equal skill across members. In this study, we demonstrate, through a strictly a-posteriori evaluation , for any large enough ensemble of ENSO forecasts, there is a subset of members whose skill is substantially higher than that of the ensemble mean. Using a state-of-the-art ENSO forecast system cross-validated against the 1986-2017 observed Nino3.4 index, we identify two Top-5 subsets one ranked on lowest Root Mean Square Error (RMSE) and another on highest Pearson correlation. Generally across all leads, these outstanding members show higher correlation and lower RMSE, with the advantage rising enormously with lead time. Whereas at short leads (1 month) raises the mean correlation by about +0.02 (+1.7%) and lowers the RMSE by around 0.14 °C or by 23.3% compared to the All-40 mean, at extreme leads (23 months) the correlation is raised by +0.43 (+172%) and RMSE by 0.18 °C or by 22.5% decrease. The enhancements are largest during crucial ENSO transition periods such as SON and DJF, when accurate amplitude and phase forecasting is of greatest socio-economic benefit, and furthermore season-dependent e.g., mid-year months such as JJA and MJJ have incredibly large RMSE reductions. This study provides a solid foundation for further investigations to identify reliable clues for detecting high-quality ensemble members, thereby enhancing forecasting skill. more
-
MAUSAM: An Observations-focused assessment of Global AI Weather Prediction Models During the South Asian Monsoon¶
Accurate weather forecasts are critical for societal planning and disaster preparedness. Yet these forecasts remain challenging to produce and evaluate, especially in regions with sparse...Accurate weather forecasts are critical for societal planning and disaster preparedness. Yet these forecasts remain challenging to produce and evaluate, especially in regions with sparse observational coverage. Current evaluation of artificial intelligence (AI) weather prediction relies primarily on reanalyses, which can obscure important deficiencies. Here we present MAUSAM (Measuring AI Uncertainty during South Asian Monsoon), an evaluation of seven leading AI-based forecasting systems - FourCastNet, FourCastNet-SFNO, Pangu-Weather, GraphCast, Aurora, AIFS, and GenCast - during the South Asian Monsoon, using ground-based weather stations, rain gauge networks, and geostationary satellite imagery. The AI models demonstrate impressive forecast skill during monsoon across a broad range of variables, ranging from large-scale surface temperature and winds to precipitation, cloud cover, and subseasonal to seasonal eddy statistics, highlighting the strength of data-driven weather prediction. However, the models still exhibit systematic errors at finer scales like the underprediction of extreme precipitation, divergent cyclone tracks, and the mesoscale kinetic energy spectra, highlighting avenues for future improvement. A comparison against observations reveals forecast errors up to 15-45% larger than those relative to reanalysis and traditional forecasts, indicating that reanalysis-centric benchmarks can overstate forecast skill. Of the models assessed, AIFS achieves the most consistent representation of atmospheric variables, with GraphCast and GenCast also showing strong skill. The analysis presents a framework for evaluating AI weather models on regional prediction and highlights both the promise and current limitations of AI weather prediction in data-sparse regions, underscoring the importance of observational evaluation for future operational adoption. more
-
Exploring Quantum Machine Learning for Weather Forecasting¶
Weather forecasting plays a crucial role in supporting strategic decisions across various sectors, including agriculture, renewable energy production, and disaster management. However, the inherently...Weather forecasting plays a crucial role in supporting strategic decisions across various sectors, including agriculture, renewable energy production, and disaster management. However, the inherently dynamic and chaotic behavior of the atmosphere presents significant challenges to conventional predictive models. On the other hand, introducing quantum computing simulation techniques to the forecasting problems constitutes a promising alternative to overcome these challenges. In this context, this work explores the emerging intersection between quantum machine learning (QML) and climate forecasting. We present the implementation of a Quantum Neural Network (QNN) trained on real meteorological data from NASA's Prediction of Worldwide Energy Resources (POWER) database. The results show that QNN has the potential to outperform a classical Recurrent Neural Network (RNN) in terms of accuracy and adaptability to abrupt data shifts, particularly in wind speed prediction. Despite observed nonlinearities and architectural sensitivities, the QNN demonstrated robustness in handling temporal variability and faster convergence in temperature prediction. These findings highlight the potential of quantum models in short and medium term climate prediction, while also revealing key challenges and future directions for optimization and broader applicability. more
-
Huracan: A skillful end-to-end data-driven system for ensemble data assimilation and weather prediction¶
Over the past few years, machine learning-based data-driven weather prediction has been transforming operational weather forecasting by providing more accurate forecasts while using a mere fraction...Over the past few years, machine learning-based data-driven weather prediction has been transforming operational weather forecasting by providing more accurate forecasts while using a mere fraction of computing power compared to traditional numerical weather prediction (NWP). However, those models still rely on initial conditions from NWP, putting an upper limit on their forecast abilities. A few end-to-end systems have since been proposed, but they have yet to match the forecast skill of state-of-the-art NWP competitors. In this work, we propose Huracan, an observation-driven weather forecasting system which combines an ensemble data assimilation model with a forecast model to produce highly accurate forecasts relying only on observations as inputs. Huracan is not only the first to provide ensemble initial conditions and end-to-end ensemble weather forecasts, but also the first end-to-end system to achieve an accuracy comparable with that of ECMWF ENS, the state-of-the-art NWP competitor, despite using a smaller amount of available observation data. Notably, Huracan matches or exceeds the continuous ranked probability score of ECMWF ENS on 80.2% of the variable and lead time combinations. Our work is a major step forward in end-to-end data-driven weather prediction and opens up opportunities for further improving and revolutionizing operational weather forecasting. more
-
Global Forecasting of Tropical Cyclone Intensity Using Neural Weather Models¶
Numerical Weather Prediction (NWP) models that integrate coupled physical equations forward in time are the traditional tools for simulating atmospheric processes and forecasting weather. With recent...Numerical Weather Prediction (NWP) models that integrate coupled physical equations forward in time are the traditional tools for simulating atmospheric processes and forecasting weather. With recent advancements in deep learning, AI-based Weather Prediction models that rely on neural network architectures\(\unicode{x2013}\)Neural Weather Models (NeWMs)\(\unicode{x2013}\)have emerged as competent medium-range NWP emulators, with performances that compare favorably to state-of-the-art NWP models. However, they are commonly trained on reanalyses with limited spatial resolution (e.g., 0.25° horizontal grid spacing), which smooths out key features of weather systems. For example, tropical cyclones (TCs)\(\unicode{x2013}\)among the most impactful weather events due to their devastating effects on human activities\(\unicode{x2013}\)are challenging to forecast, as extrema are smoothed in deterministic forecasts at 0.25° resolution. To address this, we use our best observational estimates of wind gusts and minimum sea level pressure to train a hierarchy of post-processing models on NeWM outputs. Applied to Pangu-Weather and FourCastNet v2, the post-processing models produce accurate and reliable forecasts of TC intensity up to five days ahead. Our post-processing algorithm is tracking-independent, preventing full misses, and we demonstrate that even linear models extract predictive information from NeWM outputs beyond what is encoded in their initial conditions. While spatial masking improves probabilistic forecast consistency, we do not find clear advantages of convolutional architectures over simple multilayer perceptrons for our NeWM post-processing purposes. Overall, by combining the efficiency of NeWMs with a lightweight, tracking-independent postprocessing framework, our approach improves the accessibility of global TC intensity forecasts, marking a step toward their democratization. more
-
Intelligent Shanghai Typhoon Model (ISTM): A generative probabilistic emulator for typhoon hybrid modeling¶
To address the systematic underestimation of typhoon intensity in artificial intelligence weather prediction (AIWP) models, we propose the Intelligent Shanghai Typhoon Model (ISTM): a unified...To address the systematic underestimation of typhoon intensity in artificial intelligence weather prediction (AIWP) models, we propose the Intelligent Shanghai Typhoon Model (ISTM): a unified regional-to-typhoon generative probabilistic forecasting system based on a two-stage UNet-Diffusion framework. ISTM learns a downscaling mapping from 4 years of 25 km ERA5 reanalysis to a 9 km high resolution typhoon reanalysis dataset, enabling the generation of kilometer-scale near-surface variables and maximum radar reflectivity from coarse resolution fields. The evaluation results show that the two-stage UNet-Diffusion model significantly outperforms both ERA5 and the baseline UNet regression in capturing the structure and intensity of surface winds and precipitation. After fine-tuning, ISTM can effectively map AIFS forecasts, an advanced AIWP model, to high-resolution forecasts from AI-physics hybrid Shanghai Typhoon Model, substantially enhancing typhoon intensity predictions while preserving track accuracy. This positions ISTM as an efficient AI emulator of hybrid modeling system, achieving fast and physically consistent downscaling. The proposed framework establishes a unified pathway for the co-evolution of AIWP and physics-based numerical models, advancing next-generation typhoon forecasting capabilities. more