Google’s GraphCast Uses Machine Learning to Forecast Weather
AI can now outperform conventional weather forecasting – in under a minute, too
A new era in weather forecasting has arrived – fuelled by artificial intelligence. Google DeepMind, Google’s AI research laboratory, is developing a machine learning model that it says can accurately predict weather in seconds – not hours – and outperforms 90% of the targets used by the world’s best weather prediction systems.
The AI marks a “turning point” for weather forecasting and decision-making, the scientists at Google DeepMind say.
How does AI weather forecasting work?
Called GraphCast, Google DeepMind’s AI weather forecasting model has been trained on almost 40 years of historical weather data to improve its accuracy, explains the publisher, Science.
Training the AI took four weeks and 32 computers. But the algorithm this produced can predict weather up to 10 days away in less than one minute on a single desktop computer. GraphCast’s accuracy significantly beats current weather systems on 90% of 1,380 metrics.
The AI is also better at forecasting severe weather events, including extreme temperatures and the tracking of tropical cyclones, as the Google DeepMind scientists explain in their Science journal paper.
How does conventional weather forecasting work?
Weather forecasting currently involves powerful supercomputers – high performance computers – making complex calculations based on observations from weather stations, satellites and buoys.
This is a costly and time-consuming process. Specifically, it takes six hours for the European Centre for Medium-Range Weather Forecasts in Italy to produce the world’s most accurate weather forecasts, Google DeepMind scientists explain. This process repeats every six hours, typically four times a day, every day.
The supercomputers use an approach called “numerical weather prediction”, an intensive process which involves cracking the governing equations of weather.
GraphCast AI’s specifications
GraphCast AI is a machine learning-based method for medium-range global weather forecasting, developed by DeepMind and Google.
It uses graph neural networks (GNNs) to learn the complex physical dynamics of fluids and other materials from reanalysis data.
GraphCast AI can predict hundreds of weather variables, over 10 days at 0.25 degree resolution globally, in under one minute. It outperforms the most accurate operational deterministic systems on 90% of 1380 verification targets, and its forecasts support better severe event prediction, including tropical cyclones, atmospheric rivers, and extreme temperatures.
Industry impacts
GraphCast AI has significant implications for the products industry, as it can help improve decision-making across many social and economic domains that depend on accurate and efficient weather forecasting.
For example, GraphCast AI can help optimize crop yields, reduce energy consumption, enhance public health, and mitigate the impacts of natural disasters.
GraphCast AI also demonstrates the promise of machine learning for modeling complex dynamical systems, and opens up new possibilities for exploring other domains such as climate change, air quality, and traffic flow.
Trend Themes
1. AI Weather Forecasting – GraphCast AI uses machine learning to forecast weather and has implications for decision-making across various industries.
2. Graph Neural Networks – GraphCast AI utilizes graph neural networks to learn the complex dynamics of fluids and materials.
3. Improved Decision-making – GraphCast AI improves decision-making by providing accurate and efficient weather forecasts that can optimize crop yields, reduce energy consumption, enhance public health, and mitigate the impacts of natural disasters.
Industry Implications
1. Products Industry – GraphCast AI has implications for the products industry as it can improve decision-making across economic domains that rely on accurate weather forecasting.
2. Climate Change – GraphCast AI opens up new possibilities for exploring domains such as climate change, allowing for better understanding and prediction of climate patterns.
3. Air Quality – GraphCast AI’s machine learning capabilities can be leveraged to improve air quality monitoring and prediction, benefiting industries related to environmental health and pollution control.
Why is AI better at predicting the weather?
To improve the accuracy of this traditional weather forecasting approach, more costly computing power must be deployed. But the Google DeepMind scientists say GraphCast can predict weather more cheaply and accurately using historical weather data. Most specifically:
- the AI can identify patterns in the data that are not easy to see in equations. It can then use these findings to improve the accuracy of weather forecasts.
- GraphCast is also about 1,000 times cheaper in terms of energy efficiency than conventional weather forecasting methods, reports the Financial Times.
sources: WEF
cover image: Brian McGowan via Unsplash
author: Barbara Marcotulli
Maker Faire Rome – The European Edition has been committed since its very first editions to make innovation accessible and usable to all, with the aim of not leaving anyone behind. Its blog is always updated and full of opportunities and inspiration for makers, makers, startups, SMEs and all the curious ones who wish to enrich their knowledge and expand their business, in Italy and abroad.
Follow us, subscribe to our newsletter: we promise to let just the right content for you to reach your inbox.
