Machine Learning‐Based Detection of Weather Fronts and Associated Extreme Precipitation in Historical and Future Climates

Extreme precipitation events, including those associated with weather fronts, have wide‐ranging impacts across the world. Here we use a deep learning algorithm to identify weather fronts in high resolution Community Earth System Model (CESM) simulations over the contiguous United States (CONUS), and evaluate the results using observational and reanalysis products. We further compare results between CESM simulations using present‐day and future climate forcing, to study how these features might change with climate change. We find that detected front frequencies in CESM have seasonally varying spatial patterns and responses to climate change and are found to be associated with modeled changes in large scale circulation such as the jet stream. We also associate the detected fronts with precipitation and find that total and extreme frontal precipitation mostly decreases with climate change, with some seasonal and regional differences. Decreases in Northern Hemisphere summer frontal precipitation are largely driven by changes in the frequency of different front types, especially cold and stationary fronts. On the other hand, Northern Hemisphere winter exhibits some regional increases in frontal precipitation that are largely driven by changes in frontal precipitation intensity. While CONUS mean and extreme precipitation generally increase during all seasons in these climate change simulations, the likelihood of frontal extreme precipitation decreases, demonstrating that extreme precipitation has seasonally varying sources and mechanisms that will continue to evolve with climate change. Extreme precipitation can have devastating impacts on communities and ecosystems around the world. One source of extreme precipitation is weather fronts, or the boundaries between different types of air masses which can also give rise to high winds, rain, and thunderstorms. Machine learning can be used to automatically detect weather fronts in observations and model simulations. In this work, we use a machine learning algorithm to detect weather fronts in a climate model, and compare present day fronts with those detected in simulations with future climate change. We also compare detected fronts with total and extreme precipitation, to better understand sources of extreme precipitation and how they are changing with climate change. A deep learning algorithm is applied to detect weather fronts in climate model simulations over the contiguous United StatesDetected fronts have seasonally varying spatial patterns of front frequencies and responses to climate changeTotal and extreme precipitation associated with fronts mostly decreases with climate change, largely driven by changes in fronts A deep learning algorithm is applied to detect weather fronts in climate model simulations over the contiguous United States Detected fronts have seasonally varying spatial patterns of front frequencies and responses to climate change Total and extreme precipitation associated with fronts mostly decreases with climate change, largely driven by changes in fronts