The GraphCast Al model, developed by Google DeepMind, uses a machine-learning model that has learned from more than 40 years of weather forecasts.
It outperformed the conventional forecasting method in 90% of the 1,380 metrics used, which included temperature, pressure, wind speed and direction, and humidity at different levels of the atmosphere, Google DeepMind said in a peer-reviewed paper.
Developed by Google’s AI company DeepMind in London, GraphCast outperforms conventional and AI-based approaches at most global weather-forecasting tasks. Researchers first trained the model using estimates of past global weather made from 1979 to 2017 by physical models. This allowed GraphCast to learn links between weather variables such as air pressure, wind, temperature and humidity.
The trained model uses the ‘current’ state of global weather and weather estimates from 6 hours earlier to predict the weather 6 hours ahead. Earlier predictions are fed back into the model, enabling it to make estimates further into the future.
The standard conventional method called numerical weather prediction (NWP) uses mathematical models based on physical principles. These physical models crunch weather data from buoys , satellites and weather stations worldwide using supercomputers. The calculations accurately map out how heat, air and water vapour move through the atmosphere, but they are expensive and energy-intensive to run.
DeepMind researchers found that GraphCast could use global weather estimates from 2018 to make forecasts up to 10 days ahead in less than a minute, and the predictions were more accurate than the European Centre for Medium-Range Weather Forecasts (ECMWF)'s High RESolution forecasting system (HRES) — one version of the UK's NWP — which takes hours to forecast. Notably, ECMWF provides world-leading weather predictions up to 15 days in advance.
The GraphCast model can run from a desktop computer and makes more accurate predictions than conventional models in minutes rather than hours.
“GraphCast currently is leading the race amongst the AI models,” says computer scientist Aditya Grover at University of California, Los Angeles.
The model is described in Science on 14 November.
In the troposphere, which is the part of the atmosphere closest to the surface that affects us all the most, GraphCast outperforms HRES on more than 99% of the 12,00 measurements done by Deepmind researchers.
Across all levels of the atmosphere, GraphCast model outperformed HRES on 90% of weather predictions.
Earlier in last month, IndianWeb2.com reported that researchers from the Universities of California at Berkeley and Santa Cruz, and the Technical University of Munich, unveiled the Recurrent Earthquake foreCAST (RECAST), a deep learning model for improved earthquake forecasting.
“GraphCast currently is leading the race amongst the AI models,” says computer scientist Aditya Grover at University of California, Los Angeles.
The model is described in Science on 14 November.
In the troposphere, which is the part of the atmosphere closest to the surface that affects us all the most, GraphCast outperforms HRES on more than 99% of the 12,00 measurements done by Deepmind researchers.
Across all levels of the atmosphere, GraphCast model outperformed HRES on 90% of weather predictions.
Earlier in last month, IndianWeb2.com reported that researchers from the Universities of California at Berkeley and Santa Cruz, and the Technical University of Munich, unveiled the Recurrent Earthquake foreCAST (RECAST), a deep learning model for improved earthquake forecasting.
Advertisements