Long-range weather model updates

The first generation of AI weather models is now approaching maturity and utility, thanks to European Centre for Medium-Range Weather Forecasts - ECMWF and its release of the #opensource AIFS model, which contains many more useful weather parameters, updates faster, is mostly quite accurate, and can be run by users on their own small hardware. This first generation is slightly improving on something that physics-based models already did very well at - making a global gridded forecast at medium resolution (~10-50km grid; 3-6hr steps), which updates a few times per day. An amazing achievement in just two years to nearly replicate physics-based models that were refined for 5 decades. Some researchers and companies will continue to iterate on this first generation of models, until they get to full feature parity and resolution with the physics-based models. A better mousetrap. Others will push the envelope, and take #ai weather model development to the places where the physics-based models really struggled: ⏳Much faster updates: From 1/3/6/12 hourly updates, to updating every 5/10/15 minutes. 🛰️Data assimilation: Actually using all the observational data, rather than only the data that the physics-based models can work with. 📐Finer resolution: Being able to resolve the weather that matters, which can be as small as a tornado, going down to 10 metre to 1 km scales There is already some great early progress on these avenues. What does this mean for the consumers of weather data? I would say to push your data and software suppliers hard on what they are doing to leverage these new model capabilities in the products they make. I would also say for #datascience teams, be wary of “let’s use one of these open source models and do it ourselves” - since at best you end up with just one of the raw ingredients that your supplier(s) use. What does this mean for the #weather enterprise? Distribution models and business models and moats will change very quickly. Value will accrete to primary data collection/archival and management, and to end use cases, rather than the middle of the stack. At the very least you should be deeply thinking and openly debating what it means for you, and making investments. Stephan Rasp Daniel Rothenberg Ryan Keisler Bas Steunebrink Dr. Jesper Dramsch

NOAA Research Air Resources Laboratory’s (ARL) HYSPLIT model is one of the most extensively used atmospheric transport and dispersion models in the scientific community. HYSPLIT, used for over 25 years with many updates throughout that time, can be used to forecast dispersion of chemical releases into the atmosphere, smoke from wildfires, ash from volcanic eruptions, and even balloons that may be drifting over our country. The most recent update, HYSPLIT v9, has now been approved for implementation into the National Weather Service's National Centers for Environmental Prediction operations. HYSPLIT v9 provides significant enhancement to the code, the addition of a transfer coefficient matrix capability (which represents the amount of materials moving from one area into another) for volcanic ash and radiological releases, and stronger integration with global weather prediction models.  #NOAA #research https://lnkd.in/ePkVkGBn

Weather forecasting is complicated and relies on physics-based equations and the nuanced expertise of trained forecasters. These general circulation models, which run multiple numerical simulations of the atmosphere, need a lot of computing power that is available only at high-performance supercomputing facilities. Google’s DeepMind has introduced an AI-based diffusion model called GenCast which uses machine learning to generate ensemble-based forecasts. The model provides probability-driven projections instead of the usual deterministic “one outcome fits all” approach. https://buff.ly/4g86bNw The model is efficient in anticipating extreme weather events, “even those outside the data it was trained on”. The model is trained on historical weather data from 1979 to 2018, and computation speed is its strong suit. GenCast requires only 8 minutes to generate forecasts. The model needs to be more accurate - for now it provides updates every 12 hours. In this era of climate change, the ability to predict unprecedented and severe events, quickly, is all the more crucial. GenCast surpassed the European Centre for Medium-Range Weather Forecasts (ECMWF) ensemble in 97% of evaluated metrics. This includes accurately tracking tropical cyclones and forecasting extreme events. The integration of AI in weather forecasting will complement, not replace, the work of human meteorologists. #deepmind #google #AL #ML #weather #forecasting #predictive #analytics #meteorology #GenCast #climate #climatechange