AI predicts global warming's impact on extreme weather

Artificial intelligence (AI) is transforming our understanding of climate change, particularly about how global warming influences extreme weather events.

Unprecedented heatwaves have scorched the United States and other parts of the globe in recent years, highlighting the urgent need for accurate methods to measure this impact.

Scientists have been on a relentless search for ways to quantify the influence of global warming on these extreme phenomena.

AI uncovers global warming’s impact

Now, a game-changing methodology has emerged from a collaborative study at Stanford University and Colorado State University.

The innovative approach leverages AI to rapidly and cost-effectively determine how much global warming has contributed to recent heatwaves in the U.S. and beyond.

This method could revolutionize climate change studies. It also holds significant potential for guiding adaptation strategies. Additionally, it supports legal actions related to climate-induced damages.

“We’ve seen the impacts that extreme weather events can have on human health, infrastructure, and ecosystems,” said study lead author Jared Trok, a PhD student in Earth system science at the Stanford Doerr School of Sustainability.

“To design effective solutions, we need to better understand the extent to which global warming drives changes in these extreme events.”

Efficient, low-cost prediction method

The concerted efforts of researchers from Stanford and Colorado State University have resulted in an efficient, low-cost method for studying the impact of global warming on individual extreme weather events. The intriguing element is the use of artificial intelligence in their methodology.

“We’ve shown that machine learning is a powerful and efficient new tool for studying the impact of global warming on historical weather events,” said Trok.

“We hope that this study helps promote future research into using AI to improve our understanding of how human emissions influence extreme weather, helping us better prepare for future extreme events.”

Varying levels of global warming

Trok and his co-authors trained AI models to predict daily maximum temperatures based on regional weather conditions and the global mean temperature.

For training the AI models, they utilized an extensive database of climate model simulations extending from 1850 to 2100.

Once trained and verified, the AI models were tested with real-world weather conditions from specific heatwaves to predict the severity of these events under varying levels of global warming.

This innovative application of AI allowed the researchers to estimate how climate change influenced the frequency and severity of historical weather events.

Making a case: Texas heat wave of 2023

The first case study for this groundbreaking method was the Texas heatwave in 2023, which led to a record number of heat-related deaths in the state that year.

The results? Global warming increased the severity of the heatwave by 1.18 to 1.42 degrees Celsius (2.12 to 2.56 Fahrenheit).

The researchers also found that their new technique accurately predicted the magnitude of record-setting heatwaves in other parts of the world, and the results were consistent with previously published studies of those events.

“Machine learning creates a powerful new bridge between the actual meteorological conditions that cause a specific extreme weather event and the climate models that enable us to run more generalized virtual experiments on the Earth system,” said study senior author Professor Noah Diffenbaugh.

“AI hasn’t solved all the scientific challenges, but this new method is a really exciting advance that I think will get adopted for a lot of different applications.”

Predicting the unpredictable

Using this AI tool, researchers took a step further into the future. They concluded that similar weather patterns could lead to recurring severe heatwaves if global temperatures rise to 2.0°C above pre-industrial levels.

Global warming is currently inching towards 1.3°C above pre-industrial standards. Events similar to some of the worst heatwaves in Europe, Russia, and India over the past 45 years could happen multiple times per decade under these conditions.

The new AI method addresses some limitations of existing approaches – including those previously developed at Stanford – by using actual historical weather data when predicting the effect of global warming on extreme events.

The technique does not require expensive new climate model simulations because the AI can be trained using existing simulations.

Together, these innovations will enable accurate, low-cost analyses of extreme events in more parts of the world, which is crucial for developing effective climate adaptation strategies. The research also opens up new possibilities for fast, real-time analysis of the contribution of global warming to extreme weather.

The future of AI in meteorology

The team plans to extend the application of this method to a broader range of extreme weather events and fine-tune their AI networks for more accurate predictions.

“We’ve shown that machine learning is a powerful and efficient new tool for studying the impact of global warming on historical weather events,” said Trok.

“We hope that this study helps promote future research into using AI to improve our understanding of how human emissions influence extreme weather, helping us better prepare for future extreme events.”

The study is published in the journal Science Advances.

—–

Like what you read? Subscribe to our newsletter for engaging articles, exclusive content, and the latest updates. 

Check us out on EarthSnap, a free app brought to you by Eric Ralls and Earth.com.

—–