Climate and Earth System Dynamics Group Noah Diffenbaugh

Impacts of Climate Change on Extreme Weather

 

Schematic showing how partial dependence analysis is used to derive the nonlinear relationship between soil moisture and temperature that has been learned by a neural network. (1) We take a single 500 mbar geopotential height input map and (2) we combine this single map with every possible soil moisture anomaly input map sorted from driest to wettest. (3) We then use a trained neural network to predict temperature for these new input combinations. (4) We repeat steps (1–3) and average the behavior across all summertime GPH patterns to obtain the nonlinear SM-T coupling relationship.

 

Jared Trok is a PhD student studying the impacts of climate change and land-atmosphere interactions on extreme weather. His current research uses explainable artificial intelligence to gain new insights into these processes.

Extreme weather events (heatwaves, floods, etc.) cause widespread economic losses and pose a serious risk for humans and infrastructure. Climate change is expected to influence both the frequency and intensity of these extreme events, in part, by influencing land-atmosphere interactions which play an important role in driving extreme weather. Jared uses explainable artificial intelligence techniques to analyze climate data and quantify how extreme weather is influenced by these changing processes. By improving our understanding of how extreme weather will change in the coming decades, he hopes to guide future adaption and mitigation techniques to avoid the worst consequences of climate change.

Related Publications & News