Cloud Hosting

Extreme heatwaves like those that struck Western Europe last summer could be predicted weeks in advance in the future using artificial intelligence.

Because heatwaves are rare and difficult to anticipate, it has historically been difficult to prepare for the likes of wildfires and the health implications for people and animals when they strike.

However, French scientists have now unveiled an AI system to predict them, using so-called "deep learning".

Machine learning is where AI evolves with minimal human interference, while deep learning is an offset of machine learning that uses artificial neural networks to mimic the human brain.

The AI used by the Claude Bernard University Lyon researchers uses environmental conditions such as soil moisture and the state of the atmosphere to measure the probability of an extreme heatwave up to a month before its arrival.

They trained the technology on 8,000 years of weather data, simulated by a climate model from the University of Hamburg.

The AI can make predictions in a matter of seconds, and can also be used to predict rare phenomena difficult to anticipate using traditional climate forecasts and climate models, the researchers said.

As global warming intensifies, extreme heatwaves are likely to become more frequent.

The Intergovernmental Panel on Climate Change (IPCC), a UN-backed body of global climate scientists, including Maynooth University professor Peter Thorne, said last month that more than a century of burning fossil fuels has led to global warming of 1.1C above pre-industrial levels, resulting in more frequent and more intense extreme weather events in every region of the world.

Every increment of warming results in rapidly escalating hazards, such as more intense heatwaves, heavier rainfall, and other weather extremes.

Almost half of the worlds population lives in regions highly vulnerable to climate change, where in the last decade, deaths from floods, droughts, and storms were 15 times higher.

Last summer, much of Europe was brought to its knees by heatwaves as the continent experienced one of its worst environmental and human catastrophes in years, with several countries beset by wildfires.

A report from Christian Aid calculated that drought caused by the extreme heat across Europe during the summer was likely to have cost 20bn and 20,000 deaths in excess of normal, with wildfires and agricultural losses particularly acute.

Wildfires across Europe proved costly not just in monetary terms, but also regarding emissions. Emissions from June to August were the highest summer total wildfire output estimated for the EU plus Britain in the last 15 years.

France, Spain, Germany, and Slovenia experienced their highest summer wildfire emissions for at least the last 20 years, the EU's climate change service Copernicus said.

Copernicus said in January that Europes summer was the hottest in recorded history by a clear margin, with all countries across the entire continent bar one experiencing annual temperatures above the 30-year average.

Autumn was the third warmest on record, only beaten by 2020 and 2006, while winter temperatures in 2022 were about 1C above average, ranking amongst the 10 warmest.

The continent experienced its second warmest June ever recorded at about 1.6C above average.

Read the rest here:
Artificial intelligence to help predict extreme heatwaves - Irish Examiner