WHEN floods ripped through parts of Europe last month, the scale of destruction took people by surprise because the intense rains had been predicted by forecasting systems enhanced with artificial intelligence (AI).
But forewarned did not mean forearmed. Though the rains were accurately predicted, the effects in the deluged areas were not — a fact that highlights the difficulties of dealing with ever more common extreme weather.
AI has supercharged weather forecasting, using a range of statistical tools to analyse years of historical data and predict patterns, and at a lower cost than traditional weather predictions.
For example, Google-funded GraphCast, a machine learning-based method trained from reanalysis data, was found to outperform traditional models.
But there are still gaps in knowledge, in how the information is used and in investment to strengthen data gathering models, experts say.
"A good use of the AI-based weather forecasts would be to complement and enhance our forecasting toolbox, perhaps by allowing us to produce larger ensembles of forecasts that enable accurate assessment and interpretation of the likelihood of extreme events," said Andrew Charlton-Perez, professor of meteorology at the University of Reading in Britain.
Since January, the European Centre for Medium-Range Weather Forecasts (ECMWF) that provides predictions four times per day to European countries, has been using the Artificial Intelligence/Integrated Forecasting System.
This data-driven forecasting model makes multiple predictions rapidly and delivers long-term forecasts of weather events like cyclones and heatwaves.
The ECMWF readings ahead of the September floods were accurate.
Thomas Wostal, press officer for meteorological observatory GeoSphere Austria, said their numerical models — including the ECMWF's predictions — foresaw 300-400mm of rain locally, which came to pass.
But even with accurate forecasts, scientists say communication is key, especially when extreme weather is becoming more frequent.
"I think what happened with (the recent floods) ... is that it's so rare — a one in 150- to 200-year event — that even if the weather models capture it, there's a reasonable degree of uncertainty," said Shruti Nath, a postdoctoral research assistant in predicting weather and climate at Oxford University.
"You have to produce the warning in a way that is communicative, in the degree of severity it could possibly have on people, then people could see the cost of inaction versus the cost of action is actually much greater."
Extreme heat, drought, wildfires and flooding will worsen in Europe even under optimistic global warming scenarios and affect living conditions throughout the continent, the European Environment Agency says.
Some tech entrepreneurs say Europe is not ready.
Jonas Torland, co-founder of Norway-based 7Analytics, which develops models for predicting floods and landslides, said governments and businesses in the United States had risk managers who were more accustomed to assessing environmental hazards, while in Europe, authorities lacked readiness.
The writer is from Reuters