Having flexed its muscles in predicting kidney injury, toppling Go champions and solving 50-year-old science problems, artificial intelligence company DeepMind is now dipping its toes in weather forecasting. The company's latest tool is designed to predict oncoming precipitation through what's known as nowcasting, and the vast majority of meteorologists found it to be more accurate than current methods in early testing.
The science of precipitation nowcasting focuses on predicting rain within the next one to two hours, and is of real importance in areas such as outdoor events, aviation and emergency planning. DeepMind set out to develop a machine-learning tool that can bring a new level of precision to these efforts, by making use of high-precision radar data that tracks precipitation every five minutes at a 1-km (0.62-mile) resolution.
It did so by using a generative modeling approach, which analyzes the past 20 minutes of observed radar and then makes predictions for the upcoming 90 minutes. The tool focuses on medium to heavy rain events, which have the greatest impact on people and the economy, and the team found it offered significant performance gains over current methods.
This testing involved assessments with more than 50 trained meteorologists from the UK Met Office. DeepMind's Deep Generative Model of Rain tool was rated as the superior option in 89 percent of cases compared to current widely-used nowcasting methods. DeepMind now plans to build on these results by improving the accuracy on both longer-term predictions and on rare and intense rain events.
A paper describing the research was published in the journal Nature.
Source: DeepMind
