Google DeepMind’s GenCast: A New AI Model for Weather Forecasting
Weather forecasting is one of the most complex tasks that scientists and researchers tackle every day. With the help of technology, especially artificial intelligence (AI), the accuracy of weather forecasts has improved significantly in recent years. One such example is Google DeepMind’s new AI model called GenCast, which has been found to be accurate enough to compete with traditional weather forecasting methods.
Competing with Traditional Weather Forecasting
In a recently published research paper, it was found that GenCast outperformed the leading forecast model, ENS (European Centre for Medium-Range Weather Forecasts), when tested on data from 2019. According to the researchers at Google DeepMind, GenCast is one of several AI weather forecasting models being developed that might lead to more accurate forecasts.
"Weather basically touches every aspect of our lives… it’s also one of the big scientific challenges, predicting the weather," says Ilan Price, a senior research scientist at DeepMind. "Google DeepMind has a mission to advance AI for the benefit of humanity. And I think this is one important way, one important contribution on that front."
How GenCast Works
GenCast is a machine learning model trained on weather data from 1979 to 2018. The model learns to recognize patterns in the four decades of historical data and uses that to make predictions about what might happen in the future. This is very different from how traditional models like ENS work, which still rely on supercomputers to solve complex equations in order to simulate the physics of the atmosphere.
Both GenCast and ENS produce ensemble forecasts, which offer a range of possible scenarios. When it comes to predicting the path of a tropical cyclone, for example, GenCast was able to give an additional 12 hours of advance warning on average. GenCast was generally better at predicting cyclone tracks, extreme weather, and wind power production up to 15 days in advance.
Advantages of GenCast
One of the advantages of GenCast is its speed. It can produce one 15-day forecast in just eight minutes using a single Google Cloud TPU v5. Physics-based models like ENS might need several hours to do the same thing. GenCast bypasses all the equations ENS has to solve, which is why it takes less time and computational power to produce a forecast.
"Computationally, it’s orders of magnitude more expensive to run traditional forecasts compared to a model like Gencast," Price says.
Limitations of GenCast
There are still improvements that GenCast can make, including potentially scaling up to a higher resolution. Moreover, GenCast puts out predictions at 12-hour intervals compared to traditional models that typically do so in shorter intervals. That can make a difference for how these forecasts can be used in the real world (to assess how much wind power will be available, for instance).
Future of Weather Forecasting
While there’s growing interest in how AI can be used to improve forecasts, it still has to prove itself. "People are looking at it," says Stephen Mullens, an assistant instructional professor of meteorology at the University of Florida who was not involved in the GenCast research. "I don’t think that the meteorological community as a whole is bought and sold on it."
Mullens adds, "We are trained scientists who think in terms of physics… and because AI fundamentally isn’t that, then there’s still an element where we’re kind of wrapping our heads around, is this good? And why?"
Conclusion
GenCast is a significant step forward in the development of AI-powered weather forecasting models. While it has its limitations, it has been found to be accurate enough to compete with traditional weather forecasting methods. As more research is done on GenCast and other AI models like it, we can expect to see even more improvements in the accuracy of weather forecasts.
Open-Source Code
Forecasters can check out GenCast for themselves; DeepMind released the code for its open-source model. Price says he sees GenCast and more improved AI models being used in the real world alongside traditional models. "Once these models get into the hands of practitioners, it further builds trust and confidence," Price says.
"We really want this to have a kind of widespread social impact."
Comments
22 Comments
- This is great news for anyone who’s ever been caught off guard by unexpected weather conditions.
- While I’m excited about the potential of AI in improving weather forecasting, I do think it’s essential to address the limitations and challenges mentioned above.
- It will be fascinating to see how GenCast evolves and improves over time.
Related Articles
- "The Future of Weather Forecasting: How AI is Changing the Game"
- "AI-Powered Weather Forecasting: What You Need to Know"
- "How Machine Learning is Revolutionizing Weather Prediction"