Google DeepMind has introduced GraphCast, a machine learning algorithm for weather prediction, claiming superior accuracy to the European Centre for Medium-Range Weather Forecasts (ECMWF) system. GraphCast, running on a desktop, outperformed ECMWF on over 99% of weather variables in 90% of test regions. Despite being a "black box" model, lacking explainability, it delivered 10-day forecasts faster and more accurately than traditional methods. Trained on 38 years of global weather data, GraphCast showcased efficiency in predicting extreme events. While not replacing current tools, it complements them, offering faster predictions and aiding climate pattern analysis, contributing to broader environmental research. Pioneering the use of AI in weather forecasting will benefit billions of people in their everyday lives. But Google DeepMind's wider research is not just about anticipating weather — it's about understanding the broader patterns of our climate.
Google DeepMind has introduced GraphCast, a machine learning algorithm for weather prediction, claiming superior accuracy to the European Centre for Medium-Range Weather Forecasts (ECMWF) system. GraphCast, running on a desktop, outperformed ECMWF on over 99% of weather variables in 90% of test regions. Despite being a "black box" model, lacking explainability, it delivered 10-day forecasts faster and more accurately than traditional methods. Trained on 38 years of global weather data, GraphCast showcased efficiency in predicting extreme events. While not replacing current tools, it complements them, offering faster predictions and aiding climate pattern analysis, contributing to broader environmental research. Pioneering the use of AI in weather forecasting will benefit billions of people in their everyday lives. But Google DeepMind's wider research is not just about anticipating weather — it's about understanding the broader patterns of our climate.