Researchers at Stanford and Colorado State University used machine learning to determine how much global warming has influenced extreme weather events in the U.S. and elsewhere in recent years. Their approach could change how scientists study and predict the impact of climate change on extreme weather.
Researchers at Stanford and Colorado State University have developed a rapid, low-cost approach for studying how individual extreme weather events have been affected by global warming. Their method, detailed in a Aug. 21 study in Science Advances, uses machine learning to determine how much global warming has contributed to heat waves in the U.S. and elsewhere in recent years. The approach proved highly accurate and could change how scientists study and predict the impact of climate change on a range of extreme weather events. The results can also help to guide climate adaptation strategies and are relevant for lawsuits that seek to collect compensation for damages caused by climate change.
"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."
Trok and his co-authors trained AI models to predict daily maximum temperatures based on the regional weather conditions and the global mean temperature. For training the AI models, they used data from a large database of climate model simulations extending from 1850 to 2100. But once the AI models were trained and verified, the researchers used the actual weather conditions from specific real-world heat waves to predict how hot the heat waves would have been if the exact same weather conditions occurred but at different levels of global warming. They then compared these predictions at different global warming levels to estimate how climate change influenced the frequency and severity of historical weather events.
Case studies and beyond
The researchers first put their AI method to work analyzing the 2023 Texas heat wave, which contributed to a record number of heat-related deaths in the state that year. The team found that global warming made the historic heat wave 1.18 to 1.42 degrees Celsius (2.12 to 2.56 F) hotter than it would have been without climate change. The researchers also found that their new technique accurately predicted the magnitude of record-setting heat waves in other parts of the world, and that the results were consistent with previously published studies of those events.
Based on this, the researchers used the AI to predict how severe heat waves could become if the same weather patterns that caused previous record-breaking heat waves instead occurred under higher levels of global warming. They found that events equal to some of the worst heat waves in Europe, Russia, and India over the past 45 years could happen multiple times per decade if global temperatures reach 2.0 C above pre-industrial levels. Global warming is currently approaching 1.3 C above pre-industrial levels.
"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 Noah Diffenbaugh, the Kara J Foundation Professor and professor of Earth system science in the Stanford Doerr School of Sustainability. "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."
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. It 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. It also opens up new possibilities for fast, real-time analysis of the contribution of global warming to extreme weather.
The team plans to apply their method to a wider range of extreme weather events and refine the AI networks to improve their predictions, including using new approaches to quantify the full range of uncertainty in the AI 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."