Search papers, labs, and topics across Lattice.
WeatherNext 3 significantly enhances global weather forecasting by generating hourly forecasts with high spatial and temporal resolution, utilizing low-latency geostationary satellite data. This model not only matches the performance of traditional physics-based models but also directly incorporates satellite-derived observations, allowing for improved predictions of precipitation and temperature across various geographical contexts. The results demonstrate a marked reduction in forecasting error compared to existing global models, particularly when evaluated against previously unseen data.
WeatherNext 3 achieves state-of-the-art probabilistic medium-range forecasting by integrating real-time satellite data, outperforming traditional models in accuracy and resolution.
State-of-the-art AI weather models have shown impressive medium-range forecast skill and computational efficiency, but suffer two key shortcomings: their forecasts have lower spatial and temporal resolution than the best physics-based models and they are exclusively initialized with and trained on analysis data. As a result, they cannot directly make use of observations, and any biases in the analysis are inherited by the forecast. WeatherNext 3 addresses these shortcomings and establishes a new state-of-the-art for probabilistic medium-range forecasting skill. First, WeatherNext 3 generates new forecasts every hour (rather than every 6 hours like traditional global models) by ingesting low-latency geostationary satellite data. Second, WeatherNext 3's temporal and spatial resolution are on par with physics-based global models, with hourly time steps and 0.1 degree resolution for single-level variables, including solar radiation and cloud cover. Third, WeatherNext 3 moves beyond traditional analysis variables by learning to predict satellite-derived precipitation estimates, as well as tropical cyclone and station observations. Modelling sparse station data allows WeatherNext 3 to make 2m temperature and dewpoint predictions at any location and time, conditioned on local geographical features, with substantially lower error than competing global models, even when evaluated against unseen stations. Together, WeatherNext 3's capabilities move operational AI-based weather forecasting beyond emulating the traditionally distinct stages of data assimilation, forecasting and post-processing, which helps to further push the frontier of performance and granularity for global weather prediction.
