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.

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.

Machine learning (ML)-based weather models have rapidly risen to prominence due to their greater accuracy and speed than traditional forecasts based on numerical weather prediction (NWP), recently outperforming traditional ensembles in global probabilistic weather forecasting. This paper presents FGN, a simple, scalable and flexible modeling approach which significantly outperforms the current state-of-the-art models. FGN generates ensembles via learned model-perturbations with an ensemble of appropriately constrained models. It is trained directly to minimize the continuous rank probability score (CRPS) of per-location forecasts. It produces state-of-the-art ensemble forecasts as measured by a range of deterministic and probabilistic metrics, makes skillful ensemble tropical cyclone track predictions, and captures joint spatial structure despite being trained only on marginals.

A new machine-learning weather prediction model called GenCast can outperform the best traditional forecasting systems in at least some situations, according to a paper by Google DeepMind researchers published last month in Nature. Using a diffusion model approach similar to artificial intelligence (AI) image generators, the system generates multiple forecasts to capture the complex behaviour of the atmosphere. It does so with a fraction of the time and computing resources required for traditional approaches. The weather predictions we use in practice are produced by running multiple numerical simulations of the atmosphere. Each simulation starts from a slightly different estimate of the current weather.

Getting caught out in the rain might soon be a thing of the past thanks to a powerful new AI weather forecaster. Google DeepMind has unveiled an AI-powered weather model called GenCast which it claims is faster and more accurate than traditional forecasts. Compared to the top-performing supercomputer Google's GenCast model was more accurate across 99.8 per cent of predictions up to 15 days in advance. According to Google, this will not only help commuters decide whether to bring an umbrella but also spot natural disasters like Typhoons before it is too late. Normally, weather agencies like the Met Office predict the weather by using huge supercomputers to crunch the complex maths which simulates the climate.

When Helene made landfall in Florida earlier this year, 234 people lost their lives to the worst hurricane to strike the US mainland since Katarina in 2005. It's natural disasters like that, and their growing intensity due to climate change, that have pushed scientists to develop more accurate weather forecasting systems. On Wednesday, Google's DeepMind division announced what may go down as the most significant advancement in the field in nearly eight decades of work. According to DeepMind, GenCast is not only better at providing daily and extreme weather forecasts than its previous AI weather program, but it also outperforms the best forecasting system in use right now, one that's maintained by the European Center for Medium-Range Weather Forecasts (ECMWF). In tests comparing the 15-day forecasts the two systems generated for weather in 2019, GenCast was, on average, more accurate than ECMWF's ENS system 97.2 percent of the time.

Google DeepMind isn't the only big tech firm that is applying AI to weather forecasting. And in 2023 Huawei developed its Pangu-Weather model, which trained on 39 years of data. It produces deterministic forecasts--those providing a single number rather than a range, like a prediction that tomorrow will have a temperature of 30 F or 0.7 inches of rainfall. GenCast differs from Pangu-Weather in that it produces probabilistic forecasts--likelihoods for various weather outcomes rather than precise predictions. For example, the forecast might be "There is a 40% chance of the temperature hitting a low of 30 F" or "There is a 60% chance of 0.7 inches of rainfall tomorrow."

Probabilistic weather forecasting is critical for decision-making in high-impact domains such as flood forecasting, energy system planning or transportation routing, where quantifying the uncertainty of a forecast -- including probabilities of extreme events -- is essential to guide important cost-benefit trade-offs and mitigation measures. Traditional probabilistic approaches rely on producing ensembles from physics-based models, which sample from a joint distribution over spatio-temporally coherent weather trajectories, but are expensive to run. An efficient alternative is to use a machine learning (ML) forecast model to generate the ensemble, however state-of-the-art ML forecast models for medium-range weather are largely trained to produce deterministic forecasts which minimise mean-squared-error. Despite improving skills scores, they lack physical consistency, a limitation that grows at longer lead times and impacts their ability to characterize the joint distribution. We introduce GenCast, a ML-based generative model for ensemble weather forecasting, trained from reanalysis data. It forecasts ensembles of trajectories for 84 weather variables, for up to 15 days at 1 degree resolution globally, taking around a minute per ensemble member on a single Cloud TPU v4 device. We show that GenCast is more skillful than ENS, a top operational ensemble forecast, for more than 96\% of all 1320 verification targets on CRPS and Ensemble-Mean RMSE, while maintaining good reliability and physically consistent power spectra. Together our results demonstrate that ML-based probabilistic weather forecasting can now outperform traditional ensemble systems at 1 degree, opening new doors to skillful, fast weather forecasts that are useful in key applications.