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.

Executive Summary The UT-GraphCast Hindcast Dataset (1979-2024) is a comprehensive global weather forecast archive generated using the Google DeepMind GraphCast Operational model. Developed by researchers at The University of Texas at Austin and published under the WCRP umbrella, this dataset provides daily 15 day deterministic forecasts at 00 UTC on a 0.25 0.25 global grid ( 25 km) for a 45-year period. It predicts more than a dozen key atmospheric and surface variables on 37 vertical levels, delivering a full medium-range forecast in under one minute on modern hardware. This new hindcast archive enables retrospective studies of historical weather, climate variability, and extreme events with unprecedented spatial and temporal detail. Preliminary validation shows that GraphCast forecasts generally reproduce ERA5 conditions with high fidelity and skill comparable or superior to conventional numerical models up to 10-15 days. In particular, GraphCast is known to outperform the state-of-the-art ECMWF IFS High-Resolution model (HRES) [Lam et al., 2023] on most verification targets, and to predict severe events (e.g., tropical cyclones, atmospheric rivers, heatwaves) with excellent accuracy. These benchmarks suggest that the GraphCast hindcast will be a valuable tool for climate and weather research.

Atmospheric predictability research has long held that the limit of skillful deterministic weather forecasts is about 14 days. We challenge this limit using GraphCast, a machine-learning weather model, by optimizing forecast initial conditions using gradient-based techniques for twice-daily forecasts spanning 2020. This approach yields an average error reduction of 86% at 10 days, with skill lasting beyond 30 days. Mean optimal initial-condition perturbations reveal large-scale, spatially coherent corrections to ERA5, primarily reflecting an intensification of the Hadley circulation. Forecasts using GraphCast-optimal initial conditions in the Pangu-Weather model achieve a 21% error reduction, peaking at 4 days, indicating that analysis corrections reflect a combination of both model bias and a reduction in analysis error. These results demonstrate that, given accurate initial conditions, skillful deterministic forecasts are consistently achievable far beyond two weeks, challenging long-standing assumptions about the limits of atmospheric predictability.

Accurate Subseasonal-to-Seasonal (S2S) climate forecasting is pivotal for decision-making including agriculture planning and disaster preparedness but is known to be challenging due to its chaotic nature. Although recent data-driven models have shown promising results, their performance is limited by inadequate consideration of geometric inductive biases. Usually, they treat the spherical weather data as planar images, resulting in an inaccurate representation of locations and spatial relations. In this work, we propose the geometric-inspired Circular Transformer (CirT) to model the cyclic characteristic of the graticule, consisting of two key designs: (1) Decomposing the weather data by latitude into circular patches that serve as input tokens to the Transformer; (2) Leveraging Fourier transform in self-attention to capture the global information and model the spatial periodicity. Extensive experiments on the Earth Reanalysis 5 (ERA5) re-analysis dataset demonstrate our model yields a significant improvement over the advanced data-driven models, including PanguWeather and GraphCast, as well as skillful ECMWF systems. Additionally, we empirically show the effectiveness of our model designs and high-quality prediction over spatial and temporal dimensions. The code link is: https://github.com/compasszzn/CirT . Subseasonal-to-seasonal (S2S) forecasting, which predicts meteorological variables 2 to 6 weeks in advance, is crucial for agriculture, resource allocation, and disaster preparedness (e.g., heatwaves and droughts) (Mouatadid et al., 2024). Despite its high socioeconomic benefits, such a task has long been considered a "predictability desert" (Vitart et al., 2012) due to the chaotic nature of the atmosphere. Compared with medium-range (up to 15 days) and seasonal predictions (3-6 months) (Vitart et al., 2017), the S2S timescale is long enough to lose much of the memory of atmospheric initial conditions, while it is too short for slowly evolving earth system components such as the ocean that strongly influence the atmosphere (Black et al., 2017; Phakula et al., 2024).

Data-driven machine learning models for weather forecasting have made transformational progress in the last 1-2 years, with state-of-the-art ones now outperforming the best physics-based models for a wide range of skill scores. Given the strong links between weather and climate modelling, this raises the question whether machine learning models could also revolutionize climate science, for example by informing mitigation and adaptation to climate change or to generate larger ensembles for more robust uncertainty estimates. Here, we show that current state-of-the-art machine learning models trained for weather forecasting in present-day climate produce skillful forecasts across different climate states corresponding to pre-industrial, present-day, and future 2.9K warmer climates. This indicates that the dynamics shaping the weather on short timescales may not differ fundamentally in a changing climate. It also demonstrates out-of-distribution generalization capabilities of the machine learning models that are a critical prerequisite for climate applications. Nonetheless, two of the models show a global-mean cold bias in the forecasts for the future warmer climate state, i.e. they drift towards the colder present-day climate they have been trained for. A similar result is obtained for the pre-industrial case where two out of three models show a warming. We discuss possible remedies for these biases and analyze their spatial distribution, revealing complex warming and cooling patterns that are partly related to missing ocean-sea ice and land surface information in the training data. Despite these current limitations, our results suggest that data-driven machine learning models will provide powerful tools for climate science and transform established approaches by complementing conventional physics-based models.

Weather forecasting is a vitally important tool for tasks ranging from planning day to day activities to disaster response planning. However, modeling weather has proven to be challenging task due to its chaotic and unpredictable nature. Each variable, from temperature to precipitation to wind, all influence the path the environment will take. As a result, all models tend to rapidly lose accuracy as the temporal range of their forecasts increase. Classical forecasting methods use a myriad of physics-based, numerical, and stochastic techniques to predict the change in weather variables over time. However, such forecasts often require a very large amount of data and are extremely computationally expensive. Furthermore, as climate and global weather patterns change, classical models are substantially more difficult and time-consuming to update for changing environments. Fortunately, with recent advances in deep learning and publicly available high quality weather datasets, deploying learning methods for estimating these complex systems has become feasible. The current state-of-the-art deep learning models have comparable accuracy to the industry standard numerical models and are becoming more ubiquitous in practice due to their adaptability. Our group seeks to improve upon existing deep learning based forecasting methods by increasing spatial resolutions of global weather predictions. Specifically, we are interested in performing super resolution (SR) on GraphCast temperature predictions by increasing the global precision from 1 degree of accuracy to 0.5 degrees, which is approximately 111km and 55km respectively.

As Chile's electric power sector advances toward a future powered by renewable energy, accurate forecasting of renewable generation is essential for managing grid operations. The integration of renewable energy sources is particularly challenging due to the operational difficulties of managing their power generation, which is highly variable compared to fossil fuel sources, delaying the availability of clean energy. To mitigate this, we quantify the impact of increasing intermittent generation from wind and solar on thermal power plants in Chile and introduce a hybrid wind speed forecasting methodology which combines two custom ML models for Chile. The first model is based on TiDE, an MLP-based ML model for short-term forecasts, and the second is based on a graph neural network, GraphCast, for medium-term forecasts up to 10 days. Our hybrid approach outperforms the most accurate operational deterministic systems by 4-21% for short-term forecasts and 5-23% for medium-term forecasts and can directly lower the impact of wind generation on thermal ramping, curtailment, and system-level emissions in Chile.

This work describes a process for efficiently fine-tuning the GraphCast data-driven forecast model to simulate another analysis system, here the Global Deterministic Prediction System (GDPS) of Environment and Climate Change Canada (ECCC). Using two years of training data (July 2019 -- December 2021) and 37 GPU-days of computation to tune the 37-level, quarter-degree version of GraphCast, the resulting model significantly outperforms both the unmodified GraphCast and operational forecast, showing significant forecast skill in the troposphere over lead times from 1 to 10 days. This fine-tuning is accomplished through abbreviating DeepMind's original training curriculum for GraphCast, relying on a shorter single-step forecast stage to accomplish the bulk of the adaptation work and consolidating the autoregressive stages into separate 12hr, 1d, 2d, and 3d stages with larger learning rates. Additionally, training over 3d forecasts is split into two sub-steps to conserve host memory while maintaining a strong correlation with training over the full period.

Remarkable progress in the development of Deep Learning Weather Prediction (DLWP) models positions them to become competitive with traditional numerical weather prediction (NWP) models. Indeed, a wide number of DLWP architectures -- based on various backbones, including U-Net, Transformer, Graph Neural Network (GNN), and Fourier Neural Operator (FNO) -- have demonstrated their potential at forecasting atmospheric states. However, due to differences in training protocols, forecast horizons, and data choices, it remains unclear which (if any) of these methods and architectures are most suitable for weather forecasting and for future model development. Here, we step back and provide a detailed empirical analysis, under controlled conditions, comparing and contrasting the most prominent DLWP models, along with their backbones. We accomplish this by predicting synthetic two-dimensional incompressible Navier-Stokes and real-world global weather dynamics. In terms of accuracy, memory consumption, and runtime, our results illustrate various tradeoffs. For example, on synthetic data, we observe favorable performance of FNO; and on the real-world WeatherBench dataset, our results demonstrate the suitability of ConvLSTM and SwinTransformer for short-to-mid-ranged forecasts. For long-ranged weather rollouts of up to 365 days, we observe superior stability and physical soundness in architectures that formulate a spherical data representation, i.e., GraphCast and Spherical FNO. In addition, we observe that all of these model backbones ``saturate,'' i.e., none of them exhibit so-called neural scaling, which highlights an important direction for future work on these and related models.

This project presents an extension to the GraphCast model, a state-of-the-art graph neural network (GNN) for global weather forecasting, by integrating solar energy production forecasting capabilities. The proposed approach leverages the weather forecasts generated by GraphCast and trains a neural network model to predict the ratio of actual solar output to potential solar output based on various weather conditions. The model architecture consists of an input layer corresponding to weather features (temperature, humidity, dew point, wind speed, rain, barometric pressure, and altitude), two hidden layers with ReLU activations, and an output layer predicting solar radiation. The model is trained using a mean absolute error loss function and Adam optimizer. The results demonstrate the model's effectiveness in accurately predicting solar radiation, with its convergence behavior, decreasing training loss, and accurate prediction of solar radiation patterns suggesting successful learning of the underlying relationships between weather conditions and solar radiation. The integration of solar energy production forecasting with GraphCast offers valuable insights for the renewable energy sector, enabling better planning and decision-making based on expected solar energy production. Future work could explore further model refinements, incorporation of additional weather variables, and extension to other renewable energy sources.