When floods hit parts of Europe in September, the scale of the destruction took people by surprise. There should not be intense rainfall, as it was predicted by sophisticated forecasting systems enhanced with artificial intelligence.
But pre-warning did not mean being armed. Although the rainfall was accurately predicted, it did not impact inundated areas – a fact that consistently highlights the difficulties of dealing with more common extreme weather.
AI has supercharged weather forecasting, using a range of statistical tools to analyze years of historical data and predict patterns, and at a lower cost than traditional numerical weather forecasts.
AI technology can make more specific predictions before events occur in complex areas such as urban floods or mountainous terrain.
For example, Google-funded GraphQL, a machine learning-based method trained directly from reanalysis data, was found to outperform traditional models. Reanalysis data relies on past forecasts rerun with modern forecast models to provide the most complete picture of past weather and climate.
But experts say there is still a knowledge gap in the use of information and investment to strengthen data aggregation models.
“In some cases and for some variables, AI models can beat physics-based models, but in other cases the opposite is true,” said Andrew Charlton-Perez, a professor of meteorology at the University of Reading in the UK.
One issue is that the effectiveness of an AI model is only as good as the information fed into it. If input data is sparse, or extreme events occur more frequently at different times of the year or in different regions, predicting weather-related disasters becomes more challenging.
Charlton-Perez said, “A good use of AI-based weather forecasts would be to complement and enhance our forecasting toolbox, perhaps allowing us to produce larger ensembles of forecasts that would enable us to accurately assess and interpret the probability of extreme events.” Is.”
communication is key
Since January, the European Center for Medium-Range Weather Forecasts (ECMWF), an independent organization that provides forecasts to European countries four times per day, has been using the Artificial Intelligence/Integrated Forecast System (AIFS).
This data-driven forecasting model makes multiple predictions rapidly and gives long-term forecasts of weather events like cyclones and heatwaves.
Experts say ECMWF’s readings before the September floods were accurate.
Thomas Vostal, press officer for meteorological observatory Geosphere Austria, told Context/Thomson Reuters Foundation that their numerical models – which also include ECMWF predictions – had predicted 300–400 millimeters (11.8–15.7 in) of rainfall locally , which came true.
But even with accurate forecasts, scientists say communication is key, especially in an era when climate change means extreme weather is becoming more frequent.
Shruti said, “I think what happened with (the recent floods)… is so rare – a one in 150 to 200 years event – that even if the weather models capture it, it has a lot to do with it.” There is uncertainty till now.” Nath is a postdoctoral research assistant in weather and climate prediction at the University of Oxford.
“You have to warn in a way that is communicable, in terms of the degree of severity that it could potentially have on people, then people can see that the cost of inaction versus the cost of action is really, really high. Then they really put Will give (in) more resources,” she said.
Europe behind the curve?
A report from the European Environment Agency warns that Europe faces urgent climate risks that are outstripping policies and adaptation actions.
The EEA says that even under optimistic global warming scenarios, extreme heat, drought, wildfires and floods will worsen in Europe and affect living conditions across the continent.
After the floods, Janez Lenarcik, the European Commissioner for Crisis Management, said that the disaster was not an anomaly.
“These extreme weather events that used to be once in a lifetime events are now an almost annual occurrence. The global reality of climate change has entered the everyday lives of Europeans,” he said.
Some tech entrepreneurs say Europe isn’t ready.
Jonas Torland, co-founder of Norway-based 7Analytics, which develops models to predict floods and landslides, said that governments and businesses in the United States had risk managers who were more accustomed to assessing environmental threats, whereas In Europe, authorities lacked promptness.
“We often see substantial spending with minimal data support to make informed decisions,” Torland, whose models are used in the cities of Oslo, Bergen and Kristiansand, told the Thomson Reuters Foundation.
“Although AI is a critical component of these models, unfortunately, governments are not investing in or purchasing these advanced AI solutions,” he said, adding that he believes governments “are relying on their legacy data providers and advisors.” “Stick.”
Data processing is also a challenge as these complex AI models need to run updates every hour as the forecast changes.
This requires both a lot of computing power and a lot of time – especially at the more microscopic scales.
The 1-by-1 meter grid, which 7Analytics uses for its predictions, is 100 times more detailed than a 10-by-10 meter grid, but requires 100 times more time to process.
Higher computing power also means that huge amounts of energy and water are required, which makes AI models part of the problem because they are increasing planet-heating emissions causing a climate emergency.
Some big technology companies like Microsoft and Google are exploring the use of nuclear energy to run their huge data storage centers.
Other scientists emphasize that beyond refining their forecasting capabilities, authorities need to invest in physical solutions, such as developing areas where floodwaters can be safely stored, and Early warning system.
Given the possibility of more intense climate change-induced floods, they also need to meet their commitments to reduce development and limit emissions in flood-prone areas.
“It’s not a question of data or technology or knowledge. It’s a question of implementation, of political will,” Friedrich Otto, a senior lecturer at Imperial College London, said in an emailed response to questions.
“As long as the world continues to burn fossil fuels, the root cause of climate change, extreme weather events will continue to intensify, killing people and destroying homes. To stop this trend, we must replace oil, gas and coal with renewable energy. needs to change.”
(Except for the headline, this story has not been edited by NDTV staff and is published from a syndicated feed.)
