Hybrid dry–hot Extremes prediction and AdapTation

Half a million people die due to heat stress every year. These numbers keep rising as climate continues to change. Heatwaves are becoming more frequent and severe, and disproportionally synchronised with droughts. Droughts reduce the ability of the land surface to cool down via evaporation, further enhancing heatwave temperatures.

Nonetheless, how these compound drought–heatwave events spatially propagate, and their future lethality, remains unclear.

Counterintuitive findings now indicate that drought can even dampen heatwave deadliness by reducing air humidity.Consequently, our ability to forecast dry–hot events and their impacts on human health remains limited.

Subseasonal timescales, between two weeks and two months, have traditionally been a blind spot: conventional weather forecast models are not tailored to these scales.

However, the adoption of Artificial Intelligence (AI) may hold the key to fill this gap and reliably predict the upcoming occurrence of heat stress episodes weeks in advance. This would bring enormous societal benefits by enabling emergency planning.

In this project, we will explore an innovative way to generate subseasonal forecasts of droughts and heatwaves, and their consequent human heat stress episodes. A 'hybrid' approach will be embraced, i.e., an approach based on physics-based models combined with AI algorithms.

Building upon this approach, we will deepen our understanding of the climatic drivers of human heat stress, and explore the future benefits of land-based adaptation practices designed to attenuate these events, including afforestation, crop selection, and large-scale irrigation.

Altogether, HEAT will foster our preparedness and resilience to future heat stress episodes – by improving their prediction, investigating the mechanisms that trigger them globally, and providing realistic and effective land-adaptation strategies to mitigate them – while heralding the adoption of hybrid approaches in climate science.