AI: Elon Musk warns against Google's DeepMind progress
We use your sign-up to provide content in ways you’ve consented to and to improve our understanding of you. This may include adverts from us and 3rd parties based on our understanding. You can unsubscribe at any time. More info
Experts at Google-owned London artificial intelligence (AI) lab DeepMind have made a major step forward in the way weather can be reported. As well as tomorrow’s conditions, Meteorologists often try to predict the weather over the coming hours during the day. Along with the University of Exeter, researchers have developed a “precipitation nowcasting” system.
The AI makes predictions based on the previous 20 minutes of high-resolution radar data.
It then forecasts medium to heavy rainfall for the next 90 minutes.
Current techniques are largely driven by powerful numerical weather prediction (NWP) using mathematical equations to estimate the chances of rain and other types of weather based on the movement of fluids in the atmosphere.
Speaking on the current methods, Suman Ravuri, co-lead on the project, said: “These models are really amazing from six hours up to about two weeks in terms of weather prediction, but there is an area – especially around zero to two hours – in which the models perform particularly poorly.”
The new model ranked first for accuracy and usefulness in 89 percent of cases in comparison.
Dubbed DGMR (Deep Generative Model of Rainfall), it uses a type of machine learning called generative modelling, which is able to produce new data points after being trained on existing ones.
Experts hope it will be able to predict the chance of precipitation across the next one to two hours.
It has already been given the nod of approval from more than 50 meteorologists at the Met Office in the UK.
In a statement, DeepMind said: “This collaboration between environmental science and AI focuses on value for decision-makers, opening up new avenues for the nowcasting of rain, and points to the opportunities for AI in supporting our response to the challenges of decision-making in an environment under constant change.”
The researchers behind DGMR describe making short “radar movies” that generate future radar patterns from past radar patterns.
DeepMind senior scientist Shakir Mohamed said: “It’s very early days but this trial shows that AI could be a powerful tool, enabling forecasters to spend less time trawling through ever-growing piles of prediction data and instead focus on better understanding the implications of their forecasts.
“This will be integral for mitigating the adverse effects of climate change today, supporting adaptation to changing weather patterns and potentially saving lives.”
Royal navy launches first drone from aircraft carrier [REPORT]
Germany faces worse gas crisis as Britain outsmarts Putin [INSIGHT]
‘Forget UK fuel crisis!’ China energy shortage to spark global impact [REVEAL]
The team say there is still a lot of work to be done, but they hope that the use of AI will help to move forward the accuracy of weather forecasting even more.
Their statement added: “No method is without limitations, and more work is needed to improve the accuracy of long-term predictions and accuracy on rare and intense events.
“Future work will require us to develop additional ways of assessing performance, and further specialising these methods for specific real-world applications.”
The research has been published in Nature.
Source: Read Full Article